# skills-tree - Doramagic AI Context Pack > Positioning: a pre-install experience and judgment asset. It helps the host AI get off to a good start, but it does not mean the project has already been installed, run, or validated. ## Sufficiency Principle - **Sufficiency over compression**: The AI Context Pack should be sufficient for the host AI to understand the project's value, capability boundaries, entrypoints, risks, and evidence sources before starting work; it may be layered, but it does not aim for the shortest possible summary. - **Compression policy**: Compress only noise and duplication, never context that affects judgment or the quality of the work. ## How the Host AI Should Use This You are reading the AI Context Pack that Doramagic compiled for skills-tree. Treat it as pre-work context: help the user understand who it fits, what it can do, how to start, what must be verified after install, and where the risks are. Do not claim that you have already installed, run, or executed the target project. ## Claim Consumption Rules - **Fact source**: Repo Evidence + Claim/Evidence Graph; the Human Wiki only supplies salience, terminology, and narrative structure. - **Minimum status for a fact**: `supported` - `supported`: May be used as a project fact, but the answer must cite the claim_id and evidence path. - `weak`: Usable only as a low-confidence lead; the user must be asked to keep verifying. - `inferred`: Usable only for risk notes or open questions; must not be packaged as a project fact. - `unverified`: Must not be used as fact; state clearly that evidence is insufficient. - `contradicted`: Must show the conflicting sources and must not force a single version on the user's behalf. ## Who It Fits Best - **Developers already using host AIs such as Claude/Codex/Cursor/Gemini**: The README or plugin config mentions multiple host AIs. Evidence: `README.md` Claim: `clm_0002` supported 0.86 ## What It Can Do - **Command-Line Startup or Install Flow** (Verify after install): The project documentation contains runnable commands; real use requires running them in a local or host environment. Evidence: `README.md`, `meta/MCP_QUICKSTART.md` Claim: `clm_0001` supported 0.86 ## How to Start - `pip install skills-tree` Evidence: `README.md` Claim: `clm_0003` supported 0.86 - `git clone https://github.com/SamoTech/skills-tree.git` Evidence: `README.md` Claim: `clm_0004` supported 0.86 - `git clone https://github.com/SamoTech/skills-tree` Evidence: `meta/MCP_QUICKSTART.md` Claim: `clm_0004` supported 0.86, `clm_0005` unverified 0.25 - `pip install -e .[dev]` Evidence: `meta/MCP_QUICKSTART.md` Claim: `clm_0006` unverified 0.25 ## Continue-or-Stop Decision Card - **Current recommendation**: Trial role matching first - **Why**: This project is more of a role library; the core risk is picking the wrong role or treating role copy as execution capability. Trial role matching with Prompt Preview first, then decide whether to sandbox-import it. ### 30-Second Read - **What to do now**: Trial role matching first - **Minimum safe next step**: Trial role matching with Prompt Preview first; import in isolation only once satisfied - **Do not trust yet**: Role quality and task fit cannot be trusted directly. - **Continuing will touch**: Role selection bias, Command execution, Local environment or project files ### What You Can Trust Now - **Target-audience signal: Developers already using host AIs such as Claude/Codex/Cursor/Gemini** (supported): Backed by a supported claim or project evidence, but that still is not the same as real install results. Evidence: `README.md` Claim: `clm_0002` supported 0.86 - **Capability exists: Command-Line Startup or Install Flow** (supported): You can trust that the project contains signals of this capability; whether it fits your specific task still needs trial or after-install verification. Evidence: `README.md`, `meta/MCP_QUICKSTART.md` Claim: `clm_0001` supported 0.86 - **There are Quick Start / install-command signals** (supported): You can trust that the docs mention a startup or install entrypoint; do not run it directly in your primary environment because of that. Evidence: `README.md` Claim: `clm_0003` supported 0.86 ### What You Cannot Trust Yet - **Role quality and task fit cannot be trusted directly.** (unverified): A role library proves there are many roles; it does not prove each one fits your specific task or that a role produces high-quality results. - **Do not treat role copy as real execution capability.** (unverified): Before install you can only judge whether the role description and task profile match; you cannot prove it can complete the task inside the host AI. - **Real output quality cannot be trusted before install.** (unverified): Prompt Preview can only show how it guides you; it cannot prove result quality in the real project. - **Host AI version compatibility cannot be trusted before install.** (unverified): Host loading rules and version differences across Claude, Cursor, Codex, Gemini, and others must be verified in a real environment. - **That it will not pollute your existing host AI's behavior cannot be trusted directly.** (inferred): Skill, plugin, and AGENTS/CLAUDE/GEMINI instructions may change the host AI's default behavior. - **Safe rollback cannot be assumed by default.** (unverified): Unless the project clearly provides uninstall and recovery instructions, verify in an isolated environment first. - **After a real install, is it compatible with the user's current host AI version?** (unverified): Compatibility can only be verified in the actual host environment. - **Does the project's output quality meet the user's specific task?** (unverified): The pre-install preview can only show flow and boundaries; it cannot replace real evaluation. ### What Continuing Will Touch - **Role selection bias**: The user's judgment about which expert role should handle the task. Why: Picking the wrong role makes the AI answer from the wrong expert perspective, wasting time or misleading decisions. - **Command execution**: Package managers, network downloads, the local plugin directory, project config, or the user's home directory. Why: Running the very first command can already change your environment; decide whether it is worth running first. Evidence: `README.md`, `meta/MCP_QUICKSTART.md` - **Local environment or project files**: Install results, plugin caches, project config, or local dependency directories. Why: The write scope and rollback path cannot be proven before install and need isolated verification. Evidence: `README.md`, `meta/MCP_QUICKSTART.md` - **Host AI context**: The AI Context Pack, Prompt Preview, Skill routing, risk rules, and project facts. Why: Importing context affects the host AI's later judgment, so avoid packaging unverified items as facts. ### Minimum Safe Next Steps - **Run Prompt Preview first**: Use an interactive trial to verify the task profile and role match first; do not import the whole role library up front. (applies when: Applies to any project, especially when output quality is unknown.) - **Trial-install only in an isolated directory or a test account**: Avoid letting install commands pollute your primary host AI, real projects, or home directory. (applies when: When there are signals of command execution, plugin config, or local writes.) - **After install, verify just one minimal task**: Verify loading, compatibility, output quality, and rollback first, then decide whether to use it deeply. (applies when: When moving from a trial into a real workflow.) ### Exit Plan - **Preserve the pre-install state**: Record the original host config and project state so you can later judge whether it is recoverable. - **Keep a record of the original role selection**: If output goes off-topic, you can return to the task-profiling stage and reselect a role instead of pushing on with the wrong one. - **Record the install commands and written paths**: Without clear uninstall instructions, you at least need to know which directories or configs to clean up manually. - **If there is no rollback path, do not enter your primary environment**: No rollback is a blocker before continuing; do not proceed on trust or luck. ## What Can Only Be Previewed - Explain who the project fits and what it can do - Demonstrate a typical conversation flow based on project docs - Help the user decide whether it is worth installing or researching further ## What Must Be Verified After Install - Actually installing the Skill, plugin, or CLI - Running scripts, modifying local files, or accessing external services - Verifying real output quality, performance, and compatibility ## Boundary & Risk Decision Card - **Mistaking the pre-install preview for a real run**: The user may overestimate how much configuration, permission, and compatibility verification the project has already done. Mitigation: Clearly separate prompt_preview_can_do from runtime_required. Claim: `clm_0007` inferred 0.45 - **Command execution will modify the local environment**: Install commands may write to the user's home directory, the host plugin directory, or project configuration. Mitigation: Run in an isolated environment or a test account first. Evidence: `README.md`, `meta/MCP_QUICKSTART.md` Claim: `clm_0008` supported 0.86, `clm_0009` supported 0.86, `clm_0010` contradicted 0.20 - **Source document conflict: skill_count**: The project documentation states inconsistent counts; the AI Context Pack must warn the user not to treat any single number as a verified fact. Mitigation: Flag it as unverified in both the Human Manual and the AI Context Pack rather than forcing a single number. Evidence: `meta/ROADMAP.md`, `meta/CHANGELOG.md`, `README.md`, `docs/api.md` et al. Claim: `clm_0008` supported 0.86, `clm_0009` supported 0.86, `clm_0010` contradicted 0.20 - **Source file conflict skill_count**: multiple values `15, 16, 17, 20, 23, 50, 120, 197, 223, 361, 367, 368, 377` found; verify before real use. - **To confirm**: After a real install, is it compatible with the user's current host AI version?. Why: Compatibility can only be verified in the actual host environment. - **To confirm**: Does the project's output quality meet the user's specific task?. Why: The pre-install preview can only show flow and boundaries; it cannot replace real evaluation. - **To confirm**: Do the install commands require network access, permissions, or global writes?. Why: This affects install risk in both enterprise and personal environments. ## Pre-Work Working Context ### Loading Order - First read how_to_use.host_ai_instruction to establish the boundaries of this pre-install judgment asset. - Read claim_graph_summary to confirm facts come from the Claim/Evidence Graph, not the Human Wiki narrative. - Then read intended_users, capabilities, and quick_start_candidates to judge whether the user is a match. - When you need to carry out a concrete task, check role_skill_index first, then evidence_index. - For real install, file modification, network access, performance, or compatibility questions, turn to risk_card and boundaries.runtime_required. ### Task Routes - **Command-Line Startup or Install Flow**: State that this is an after-install capability first, then give a pre-install checklist. Boundary: Must be verified after a real install or run. Evidence: `README.md`, `meta/MCP_QUICKSTART.md` Claim: `clm_0001` supported 0.86 ### Context Scale - Total files: 2268 - Important-file coverage: 40/2268 - Evidence index entries: 80 - Role / Skill entries: 62 ### Handling Insufficient Evidence - **missing_evidence**: State that evidence is insufficient and ask the user for the target file, a README section, or after-install verification records; do not fill in facts. - **out_of_scope_request**: State that the task is beyond the current AI Context Pack's evidence scope and suggest the user check the Human Manual or verify after a real install. - **runtime_request**: Provide a pre-install checklist and command sources, but do not run commands for the user or claim they have been run. - **source_conflict**: Show the conflicting sources side by side, mark them as unverified, and do not force a single version. ## Prompt Recipes ### Fit assessment - Goal: Judge whether this project fits the user's current task. - Expected output: A fit conclusion, key reasons, evidence citations, what can be previewed before install, what must be verified after install, and a next-step recommendation. ```text Based on the AI Context Pack for skills-tree, ask me 3 necessary questions first, then judge whether it fits my task. The answer must cover: who it fits, what it can do, what it cannot do, whether it is worth installing, and where the evidence comes from. Every project fact must cite evidence_refs, source_paths, or a claim_id. ``` ### Pre-install experience - Goal: Let the user feel the core workflow before installing, while avoiding packaging the preview as real capability or a marketing promise. - Expected output: An experience script with boundary labels, an after-install verification checklist, and a cautious recommendation; with no real-run promises or strong marketing language. ```text Treat skills-tree as a pre-install experience asset, not an already-installed tool or a real runtime environment. Output exactly four parts: 1. Ask me 3 necessary questions first. 2. Give an "experience script": use the three labels [Previewable before install], [Must verify after install], and [Insufficient evidence] to show how it might guide the workflow. 3. Give an after-install verification checklist: list which capabilities can only be confirmed after a real install, real host loading, and a real project run. 4. Give a cautious recommendation: only "worth researching/trialing further", "add information before deciding", or "not recommended to continue"; do not endorse the project. Hard boundaries: - Do not claim you have installed, run, executed tests, modified files, or produced real results. - Do not write promise-like phrasing such as "auto-adapts", "guarantees passing", "perfect fit", or "strongly recommend installing". - If you describe how it works after install, you must use a conditional such as "if installed successfully and the host loads the Skill correctly, it might...". - The experience script may only be written as "example lines / hypothetical flow": use "might ask / might suggest / might show", not "has written, has generated, has passed, is running, is generating". - Prompt Preview does not hand out install commands; if the user is ready to trial, only prompt them to read Quick Start and the Risk Card first and to verify in an isolated environment. - Every project fact must come from a supported claim, evidence_refs, or source_paths; inferred/unverified items can only be risks or open questions. ``` ### Role / Skill selection - Goal: Pick the best-matching asset from the project's roles or Skills. - Expected output: A list of candidate roles or Skills, each with an applicable scenario, evidence paths, risk boundary, and whether after-install verification is needed. ```text Read role_skill_index and recommend 3-5 of the most relevant roles or Skills for my target task. For each recommendation, state the applicable scenario, likely output, risk boundary, and evidence_refs. ``` ### Risk pre-check - Goal: Identify environment, permission, rule-conflict, and quality risks before installing or adopting. - Expected output: A checklist of environment, permission, dependency, license, host-conflict, quality risk, and unknown items. ```text Based on risk_card, boundaries, and quick_start_candidates, give me a pre-install risk pre-check list. Do not run commands for me; only explain what I should check, why, and what impact a failure would have. ``` ### Host AI kickoff instruction - Goal: Turn the project context into a host AI instruction for the start of a conversation. - Expected output: A pre-work instruction with clear boundaries and clear evidence citations, suitable to copy to a host AI. ```text Based on the AI Context Pack for skills-tree, generate a pre-work instruction I can paste to my host AI. This instruction must obey not_runtime=true and must not claim the project has been installed, run, or produced real results. ``` ## Role / Skill Index - Indexed 62 role / Skill / project-doc entries. - **Skills Tree** (project_doc): πŸ“† This Week's Highlights β€” June 29, 2026 Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `README.md` - **badges/ β€” Deprecated** (project_doc): This directory is no longer active. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `badges/README.md` - **Benchmarks** (project_doc): Quantitative skill comparisons β€” real numbers, real trade-offs, so you can choose the right skill for your use case. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `benchmarks/README.md` - **Blueprints** (project_doc): Production-ready architectures β€” complete, deployable patterns for common agent system designs. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `blueprints/README.md` - **Skills Tree Examples** (project_doc): Runnable, production-quality examples demonstrating Skills Tree in real scenarios. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/README.md` - **i18n β€” Internationalization** (project_doc): This directory contains translated versions of skill files from skills/ . Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `i18n/README.md` - **Labs** (project_doc): Experimental & bleeding-edge skills β€” things that work but aren't yet standardized. Contribute early, shape the future. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `labs/README.md` - **Skill Paths** (project_doc): Curated learning tracks that guide you through building a specific type of AI agent β€” step by step, skill by skill. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `paths/README.md` - **Systems** (project_doc): Multi-skill workflows β€” complete, end-to-end agent implementations that combine 2+ skills to solve real problems. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `systems/README.md` - **Example: Enterprise Agent Orchestrator** (project_doc): Example: Enterprise Agent Orchestrator Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/enterprise-agent/README.md` - **Example: MCP Server** (project_doc): A Model Context Protocol server that exposes Skills Tree as tools available to Claude Desktop, Cursor, Cline, and any MCP-compatible AI host. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/mcp-server/README.md` - **Example: OpenAI Skill-Aware Agent** (project_doc): An OpenAI-powered agent that uses Skills Tree to dynamically select and apply the right skills for each user request. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/openai-agent/README.md` - **Example: RAG System with Skill Context** (project_doc): Example: RAG System with Skill Context Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/rag-system/README.md` - **Example: Recommendation Engine** (project_doc): A learning path recommender that uses Skills Tree's prerequisite dependency graph to generate personalized skill paths. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/recommendation-engine/README.md` - **Badge JSONs** (project_doc): This directory is served via GitHub Pages from main . Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `public/badges/README.md` - **πŸ‘οΈ Perception Skills** (project_doc): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-01-perception-README.json Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `skills/01-perception/README.md` - **🧠 Reasoning Skills** (project_doc): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-02-reasoning-README.json Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `skills/02-reasoning/README.md` - **🧠 Memory Skills** (project_doc): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-03-memory-README.json Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `skills/03-memory/README.md` - **⚑ Action Execution Skills** (project_doc): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-04-action-execution-README.json Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `skills/04-action-execution/README.md` - **πŸ’» Code Skills** (project_doc): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-05-code-README.json Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `skills/05-code/README.md` - **πŸ’¬ Communication Skills** (project_doc): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-06-communication-README.json Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `skills/06-communication/README.md` - **πŸ”§ Tool Use Skills** (project_doc): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-07-tool-use-README.json Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `skills/07-tool-use/README.md` - **🎭 Multimodal Skills** (project_doc): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-08-multimodal-README.json Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `skills/08-multimodal/README.md` - **πŸ€– Agentic Patterns** (project_doc): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-09-agentic-patterns-README.json Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `skills/09-agentic-patterns/README.md` - **πŸ–₯️ Computer Use Skills** (project_doc): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-10-computer-use-README.json Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `skills/10-computer-use/README.md` - **🌐 Web Skills** (project_doc): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-11-web-README.json Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `skills/11-web/README.md` - **πŸ“Š Data Skills** (project_doc): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-12-data-README.json Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `skills/12-data/README.md` - **🎨 Creative Skills** (project_doc): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-13-creative-README.json Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `skills/13-creative/README.md` - **πŸ”’ Security & Safety Skills** (project_doc): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-14-security-README.json Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `skills/14-security/README.md` - **🎼 Orchestration Skills** (project_doc): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-15-orchestration-README.json Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `skills/15-orchestration/README.md` - **🌐 Domain-Specific Skills** (project_doc): Canonical category prefix: 16-domain-specific Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `skills/16-domain-specific/README.md` - **πŸ› οΈ Infrastructure Skills** (project_doc): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-17-infrastructure-README.json Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `skills/17-infrastructure/README.md` - **Contributing** (project_doc): Thank you for contributing to Skills Tree! This guide covers everything you need to submit a high-quality contribution. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/contributing.md` - **Why Skills Tree?** (project_doc): The problem with AI agent development isn’t model intelligence β€” it’s skill chaos. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/WHY_SKILLS_TREE.md` - **Architecture** (project_doc): Skills Tree is designed as a layered system: a human-readable data layer Markdown files , a validation and tooling layer Python scripts , and a programmatic access layer CLI + Python API + MCP server . Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/architecture.md` - **Contributing to Skills Tree** (project_doc): The AI Agent Skill OS β€” built by the community, for the community. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `CONTRIBUTING.md` - **Examples** (project_doc): Runnable, production-quality examples demonstrating Skills Tree in real-world scenarios. All examples live in the examples/ https://github.com/SamoTech/skills-tree/tree/main/examples directory. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/EXAMPLES.md` - **Use Cases** (project_doc): Real-world applications of Skills Tree across AI agent systems. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/USE_CASES.md` - **Python API Reference** (project_doc): The skills tree Python package provides a clean API for programmatic access to the skill taxonomy. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/api.md` - **Benchmarks** (project_doc): All benchmarks in Skills Tree are reproducible: they include methodology, datasets, and test scripts. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/benchmarks.md` - **CLI Reference** (project_doc): Skills Tree ships with a command-line interface built with Typer https://typer.tiangolo.com/ . Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/cli.md` - **Skills Tree** (project_doc): The AI Agent Skill OS β€” 360+ skills, versioned, benchmarked, and openly evolving. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/index.md` - **Installation** (project_doc): Skills Tree requires Python 3.9 or higher. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/installation.md` - **πŸ† Contributors Leaderboard** (project_doc): Last updated: 2026-06-29 Counts merged PRs that added or improved a skill file. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/leaderboard.md` - **Quick Start** (project_doc): Get up and running with Skills Tree in under 5 minutes. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/quickstart.md` - **Roadmap** (project_doc): See the full tracking document: meta/ROADMAP.md https://github.com/SamoTech/skills-tree/blob/main/meta/ROADMAP.md Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/roadmap.md` - **It's Today Media Build Challenge β€” Submission README** (project_doc): It's Today Media Build Challenge β€” Submission README Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `meta/COMPETITION_SUBMISSION_README.md` - **MEDIA BUYING AGENT ARCHITECTURE.md** (project_doc): Initiative: INITIATIVE-020 Created: 2026-06-24 Status: REFERENCE Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `meta/MEDIA_BUYING_AGENT_ARCHITECTURE.md` - **VIRAL LOOP ARCHITECTURE.md** (project_doc): Initiative: INITIATIVE-012A carried forward Phase: 7 Status: COMPLETE Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `meta/VIRAL_LOOP_ARCHITECTURE.md` - **Skill Name** (project_doc): πŸ“‹ Instructions: Copy this file to the appropriate skills/XX-category/ folder, rename it to kebab-case.md , fill in every field, and delete this instruction block before submitting. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `meta/skill-template.md` - **Path: Computer Use Agent** (project_doc): Difficulty: ⭐⭐⭐ Advanced Skills: 5 Est. Time: ~4 hours Goal: Build an agent that controls a desktop UI β€” parsing the screen, planning actions, clicking, typing, and verifying outcomes. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `paths/computer-use-agent.md` - **Path: Build a Research Agent** (project_doc): Difficulty: ⭐⭐ Intermediate Skills: 5 Est. Time: ~3 hours Goal: Build an agent that autonomously searches the web, retrieves documents, and synthesises a cited answer. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `paths/research-agent.md` - **Code Reviewer System** (project_doc): Category: systems Level: intermediate Stability: stable Version: v1 Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `systems/code-reviewer.md` - **Coding Agent System** (project_doc): Type: system Complexity: High Status: Production-Ready Version: v1 Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `systems/coding-agent.md` - **Computer Use Agent System** (project_doc): Category: systems Level: advanced Stability: experimental Version: v1 Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `systems/computer-use-agent.md` - **Customer Support Bot System** (project_doc): Category: systems Level: intermediate Stability: stable Version: v1 Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `systems/customer-support-bot.md` - **Research Agent System** (project_doc): A multi-step autonomous research pipeline that: 1. Breaks a complex question into sub-questions 2. Searches the web for each sub-question 3. Synthesizes findings across sources 4. Produces a structured report with citations Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `systems/research-agent.md` - **Verification Record β€” Batch 1** (project_doc): Type: dependency-verify Date: 2026-04-14 Verified by: SamoTech Method: cross-checked PyPI metadata, official docs, and package changelogs Active CVEs at time of verification: none Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/verification/batch-1.md` - **Verification Record β€” Batch 2** (project_doc): Type: dependency-verify Date: 2026-04-14 Verified by: SamoTech Method: cross-checked PyPI metadata, official docs, and package changelogs Active CVEs at time of verification: none Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/verification/batch-2.md` - **Changelog** (project_doc): All notable changes to skills-tree are documented here. Format follows Keep a Changelog https://keepachangelog.com/en/1.0.0/ . Versioning follows Semantic Versioning https://semver.org/ . Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `CHANGELOG.md` - **Contributor Covenant Code of Conduct** (project_doc): Contributor Covenant Code of Conduct Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `CODE_OF_CONDUCT.md` - **EXECUTION STATUS** (project_doc): Repository: SamoTech/skills-tree Audit Date: June 14, 2026 Objective: Determine whether executable intelligence exists Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `EXECUTION_STATUS.md` ## Evidence Index - Indexed 80 evidence entries. - **Skills Tree** (documentation): πŸ“† This Week's Highlights β€” June 29, 2026 Evidence: `README.md` - **badges/ β€” Deprecated** (documentation): This directory is no longer active. Evidence: `badges/README.md` - **Benchmarks** (documentation): Quantitative skill comparisons β€” real numbers, real trade-offs, so you can choose the right skill for your use case. Evidence: `benchmarks/README.md` - **Blueprints** (documentation): Production-ready architectures β€” complete, deployable patterns for common agent system designs. Evidence: `blueprints/README.md` - **Skills Tree Examples** (documentation): Runnable, production-quality examples demonstrating Skills Tree in real scenarios. Evidence: `examples/README.md` - **i18n β€” Internationalization** (documentation): This directory contains translated versions of skill files from skills/ . Evidence: `i18n/README.md` - **Labs** (documentation): Experimental & bleeding-edge skills β€” things that work but aren't yet standardized. Contribute early, shape the future. Evidence: `labs/README.md` - **Skill Paths** (documentation): Curated learning tracks that guide you through building a specific type of AI agent β€” step by step, skill by skill. Evidence: `paths/README.md` - **Systems** (documentation): Multi-skill workflows β€” complete, end-to-end agent implementations that combine 2+ skills to solve real problems. Evidence: `systems/README.md` - **Example: Enterprise Agent Orchestrator** (documentation): Example: Enterprise Agent Orchestrator Evidence: `examples/enterprise-agent/README.md` - **Example: MCP Server** (documentation): A Model Context Protocol server that exposes Skills Tree as tools available to Claude Desktop, Cursor, Cline, and any MCP-compatible AI host. Evidence: `examples/mcp-server/README.md` - **Example: OpenAI Skill-Aware Agent** (documentation): An OpenAI-powered agent that uses Skills Tree to dynamically select and apply the right skills for each user request. Evidence: `examples/openai-agent/README.md` - **Example: RAG System with Skill Context** (documentation): Example: RAG System with Skill Context Evidence: `examples/rag-system/README.md` - **Example: Recommendation Engine** (documentation): A learning path recommender that uses Skills Tree's prerequisite dependency graph to generate personalized skill paths. Evidence: `examples/recommendation-engine/README.md` - **Badge JSONs** (documentation): This directory is served via GitHub Pages from main . Evidence: `public/badges/README.md` - **πŸ‘οΈ Perception Skills** (documentation): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-01-perception-README.json Evidence: `skills/01-perception/README.md` - **🧠 Reasoning Skills** (documentation): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-02-reasoning-README.json Evidence: `skills/02-reasoning/README.md` - **🧠 Memory Skills** (documentation): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-03-memory-README.json Evidence: `skills/03-memory/README.md` - **⚑ Action Execution Skills** (documentation): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-04-action-execution-README.json Evidence: `skills/04-action-execution/README.md` - **πŸ’» Code Skills** (documentation): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-05-code-README.json Evidence: `skills/05-code/README.md` - **πŸ’¬ Communication Skills** (documentation): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-06-communication-README.json Evidence: `skills/06-communication/README.md` - **πŸ”§ Tool Use Skills** (documentation): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-07-tool-use-README.json Evidence: `skills/07-tool-use/README.md` - **🎭 Multimodal Skills** (documentation): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-08-multimodal-README.json Evidence: `skills/08-multimodal/README.md` - **πŸ€– Agentic Patterns** (documentation): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-09-agentic-patterns-README.json Evidence: `skills/09-agentic-patterns/README.md` - **πŸ–₯️ Computer Use Skills** (documentation): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-10-computer-use-README.json Evidence: `skills/10-computer-use/README.md` - **🌐 Web Skills** (documentation): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-11-web-README.json Evidence: `skills/11-web/README.md` - **πŸ“Š Data Skills** (documentation): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-12-data-README.json Evidence: `skills/12-data/README.md` - **🎨 Creative Skills** (documentation): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-13-creative-README.json Evidence: `skills/13-creative/README.md` - **πŸ”’ Security & Safety Skills** (documentation): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-14-security-README.json Evidence: `skills/14-security/README.md` - **🎼 Orchestration Skills** (documentation): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-15-orchestration-README.json Evidence: `skills/15-orchestration/README.md` - **🌐 Domain-Specific Skills** (documentation): Canonical category prefix: 16-domain-specific Evidence: `skills/16-domain-specific/README.md` - **πŸ› οΈ Infrastructure Skills** (documentation): ! Dependency Status https://img.shields.io/endpoint?url=https://samotech.github.io/skills-tree/badges/skills-17-infrastructure-README.json Evidence: `skills/17-infrastructure/README.md` - **Contributing** (documentation): Thank you for contributing to Skills Tree! This guide covers everything you need to submit a high-quality contribution. Evidence: `docs/contributing.md` - **Why Skills Tree?** (documentation): The problem with AI agent development isn’t model intelligence β€” it’s skill chaos. Evidence: `docs/WHY_SKILLS_TREE.md` - **Architecture** (documentation): Skills Tree is designed as a layered system: a human-readable data layer Markdown files , a validation and tooling layer Python scripts , and a programmatic access layer CLI + Python API + MCP server . Evidence: `docs/architecture.md` - **Contributing to Skills Tree** (documentation): The AI Agent Skill OS β€” built by the community, for the community. Evidence: `CONTRIBUTING.md` - **License** (source_file): Copyright c 2026 Ossama Hashim https://github.com/SamoTech Evidence: `LICENSE` - **Examples** (documentation): Runnable, production-quality examples demonstrating Skills Tree in real-world scenarios. All examples live in the examples/ https://github.com/SamoTech/skills-tree/tree/main/examples directory. Evidence: `docs/EXAMPLES.md` - **Use Cases** (documentation): Real-world applications of Skills Tree across AI agent systems. Evidence: `docs/USE_CASES.md` - **Python API Reference** (documentation): The skills tree Python package provides a clean API for programmatic access to the skill taxonomy. Evidence: `docs/api.md` - **Benchmarks** (documentation): All benchmarks in Skills Tree are reproducible: they include methodology, datasets, and test scripts. Evidence: `docs/benchmarks.md` - **CLI Reference** (documentation): Skills Tree ships with a command-line interface built with Typer https://typer.tiangolo.com/ . Evidence: `docs/cli.md` - **Skills Tree** (documentation): The AI Agent Skill OS β€” 360+ skills, versioned, benchmarked, and openly evolving. Evidence: `docs/index.md` - **Installation** (documentation): Skills Tree requires Python 3.9 or higher. Evidence: `docs/installation.md` - **πŸ† Contributors Leaderboard** (documentation): Last updated: 2026-06-29 Counts merged PRs that added or improved a skill file. Evidence: `docs/leaderboard.md` - **Quick Start** (documentation): Get up and running with Skills Tree in under 5 minutes. Evidence: `docs/quickstart.md` - **Roadmap** (documentation): See the full tracking document: meta/ROADMAP.md https://github.com/SamoTech/skills-tree/blob/main/meta/ROADMAP.md Evidence: `docs/roadmap.md` - **It's Today Media Build Challenge β€” Submission README** (documentation): It's Today Media Build Challenge β€” Submission README Evidence: `meta/COMPETITION_SUBMISSION_README.md` - **MEDIA BUYING AGENT ARCHITECTURE.md** (documentation): Initiative: INITIATIVE-020 Created: 2026-06-24 Status: REFERENCE Evidence: `meta/MEDIA_BUYING_AGENT_ARCHITECTURE.md` - **VIRAL LOOP ARCHITECTURE.md** (documentation): Initiative: INITIATIVE-012A carried forward Phase: 7 Status: COMPLETE Evidence: `meta/VIRAL_LOOP_ARCHITECTURE.md` - **Skill Name** (documentation): πŸ“‹ Instructions: Copy this file to the appropriate skills/XX-category/ folder, rename it to kebab-case.md , fill in every field, and delete this instruction block before submitting. Evidence: `meta/skill-template.md` - **Path: Computer Use Agent** (documentation): Difficulty: ⭐⭐⭐ Advanced Skills: 5 Est. Time: ~4 hours Goal: Build an agent that controls a desktop UI β€” parsing the screen, planning actions, clicking, typing, and verifying outcomes. Evidence: `paths/computer-use-agent.md` - **Path: Build a Research Agent** (documentation): Difficulty: ⭐⭐ Intermediate Skills: 5 Est. Time: ~3 hours Goal: Build an agent that autonomously searches the web, retrieves documents, and synthesises a cited answer. Evidence: `paths/research-agent.md` - **Code Reviewer System** (documentation): Category: systems Level: intermediate Stability: stable Version: v1 Evidence: `systems/code-reviewer.md` - **Coding Agent System** (documentation): Type: system Complexity: High Status: Production-Ready Version: v1 Evidence: `systems/coding-agent.md` - **Computer Use Agent System** (documentation): Category: systems Level: advanced Stability: experimental Version: v1 Evidence: `systems/computer-use-agent.md` - **Customer Support Bot System** (documentation): Category: systems Level: intermediate Stability: stable Version: v1 Evidence: `systems/customer-support-bot.md` - **Research Agent System** (documentation): A multi-step autonomous research pipeline that: 1. Breaks a complex question into sub-questions 2. Searches the web for each sub-question 3. Synthesizes findings across sources 4. Produces a structured report with citations Evidence: `systems/research-agent.md` - **Verification Record β€” Batch 1** (documentation): Type: dependency-verify Date: 2026-04-14 Verified by: SamoTech Method: cross-checked PyPI metadata, official docs, and package changelogs Active CVEs at time of verification: none Evidence: `docs/verification/batch-1.md` - **Verification Record β€” Batch 2** (documentation): Type: dependency-verify Date: 2026-04-14 Verified by: SamoTech Method: cross-checked PyPI metadata, official docs, and package changelogs Active CVEs at time of verification: none Evidence: `docs/verification/batch-2.md` - The remaining 20 evidence entries are in `AI_CONTEXT_PACK.json` or `EVIDENCE_INDEX.json`. ## Rules the Host AI Must Follow - **Treat this asset as pre-work context, not a runtime environment.**: The AI Context Pack contains only an evidence-backed understanding of the project, not the project's executable state. Evidence: `README.md`, `badges/README.md`, `benchmarks/README.md` - **When answering the user, distinguish what can be previewed from what can only be verified after install.**: The consumer value of the pre-install experience comes from reducing bad installs and misjudgments, not from pretending to be a real run. Evidence: `README.md`, `badges/README.md`, `benchmarks/README.md` ## Questions the User Should Answer First - Which host AI or local environment do you plan to use it in? - Do you just want to experience the workflow first, or are you ready to actually install? - What matters most to you: install cost, output quality, or conflicts with your existing rules? ## Acceptance Checks - Every capability claim can be traced back to a file path in evidence_refs. - AI_CONTEXT_PACK.md does not package previews as a real run. - The user can understand who it fits, what it can do, how to start, and the risk boundaries within 3 minutes. --- ## Doramagic Context Augmentation The following sections strengthen the repository context for a host AI. Human Manual data is a reading route, and pitfall notes become operating constraints. ## Human Manual Outline Usage rule: this is only a reading route and salience signal, not factual authority. Concrete claims must still return to repo evidence or Claim Graph. Host AI hard rules: - Do not treat page titles, section order, summaries, or importance values as factual project evidence. - When explaining the Human Manual outline, state that it is only a reading route or salience signal. - Capability, installation, compatibility, runtime state, and risk claims must cite repo evidence, source paths, or Claim Graph. - **Project Overview & The 17-Category Skill Taxonomy**: importance `high` - source_paths: README.md, skills/01-perception/README.md, skills/02-reasoning/README.md, skills/03-memory/README.md, meta/skill-template.md - **System Architecture & Package Surfaces**: importance `high` - source_paths: docs/architecture.md, api/main.py, api/routes/skills.py, cli/main.py, mcp/server.py - **Systems, Blueprints, Paths & Labs**: importance `high` - source_paths: systems/README.md, systems/research-agent.md, systems/coding-agent.md, systems/code-reviewer.md, systems/computer-use-agent.md - **Validation, Governance, Examples & Contribution Workflows**: importance `high` - source_paths: tools/architect.py, tools/check_skill_quality.py, tools/extract_edges.py, tools/verify_taxonomy.py, tools/dependency_auditor.py ## Repo Inspection Evidence - repo_clone_verified: true - repo_inspection_verified: true - repo_commit: `3117cece76dc71f98ac7c8adbe30becf550c0cda` - inspected_files: `README.md`, `pyproject.toml`, `requirements.txt`, `docs/EXAMPLES.md`, `docs/USE_CASES.md`, `docs/WHY_SKILLS_TREE.md`, `docs/_config.yml`, `docs/api/graph.json`, `docs/api/skills-schema.json`, `docs/api/skills.json`, `docs/api/skills.yaml`, `docs/api.md`, `docs/architecture.md`, `docs/badges/skills-00-sandbox-pipeline-test.json`, `docs/badges/skills-01-perception-README.json`, `docs/badges/skills-01-perception-api-response-parsing.json`, `docs/badges/skills-01-perception-audio-transcription.json`, `docs/badges/skills-01-perception-binary-file-reading.json`, `docs/badges/skills-01-perception-calendar-parsing.json`, `docs/badges/skills-01-perception-chart-reading.json` Host AI hard rules: - Without repo_clone_verified=true, do not claim that the source code has been read. - Without repo_inspection_verified=true, do not write README, docs, or package-file conclusions as facts. - Without quick_start_verified=true, do not claim that the Quick Start path has run successfully. ## Doramagic Pitfall Constraints These rules come from Doramagic discovery, validation, or compilation findings. The host AI must treat them as operating constraints, not background notes. ### Constraint 1: Capability evidence risk requires verification - Trigger: README/documentation is current enough for a first validation pass. - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: capability.assumptions | https://github.com/SamoTech/skills-tree - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 2: Security or permission risk requires verification - Trigger: no_demo - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: downstream_validation.risk_items | https://github.com/SamoTech/skills-tree - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 3: Security or permission risk requires verification - Trigger: no_demo - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: risks.scoring_risks | https://github.com/SamoTech/skills-tree - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.