Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Agentic Distiller

    1

    Audit a local repo's license, scaffold it into an Agent Skills package, and validate the packaging. Local Python, no API key.

    $29

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Agentic Distiller

    Agentic Distiller

    Example session with this skill installed

    Use agentic-distiller. Distill the local repo fixtures/sample-todo-cli into a skill named todo-cli-maintainer, running the license preflight first.

    • Read your context and instructions
    • Compiled the agentic distiller

    Summary

    The bundled fixture passed all three stages: license audit, scaffold, validation.

    StageResult
    License auditmit, verdict permissive, DISTILL
    Scaffoldtodo-cli-maintainer/ with SKILL.md, examples/, references/, scripts/, templates/
    ValidationPASS: frontmatter valid, 4 resource files, 1 Python script, 0 compile errors, 0 restricted-license hits, 0 warnings
    python3 skills/github-repo-skill-distiller/scripts/distill_local_repo.py \
      --repo fixtures/sample-todo-cli \
      --name todo-cli-maintainer \
      --output /tmp/sku03-out
    

    This is the output of the bundled fixture run, not a customer project.

    Next steps

    Open the generated SKILL.md and fill in the workflows. The scaffold is a skeleton by design. Re-run validate_distilled_skill.py after editing.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Turn a local repository into an Agent Skills package, with a license check first

    Point it at a local repo. It runs a deterministic license preflight, scaffolds a SKILL.md package, and validates the result. Standard-library Python 3.9+ only.

    Who this is for: you use a local coding agent (Claude Code, Codex, Cursor, OpenCode) and want to turn a codebase or handbook into a reusable skill without pulling restricted-license code into a commercial package.

    What you get

    • github-repo-skill-distiller: audit_repo_for_distillation.py (verdicts DISTILL, INTERNAL_ONLY, NEEDS_REVIEW), init_distilled_skill.py (scaffold), validate_distilled_skill.py (frontmatter, Python syntax, copyleft leaks), and distill_local_repo.py (all three in one run).
    • book-skill-distiller: templates and a rubric for distilling a manuscript or domain handbook into small operational skills.
    • A golden fixture (fixtures/sample-todo-cli) that reproduces a PASS run.
    • INSTALL.md, FIXTURE.md, COMPATIBILITY.md, and a commercial single-user license.

    Read before you buy

    • Works on local paths. It does not clone remote repositories.
    • Scaffolding produces a skeleton. You or your agent still fill in the workflows.
    • The license verdict is a signal, not legal advice.
    • Verified: the Python CLI on macOS arm64. Not verified: skill discovery in Claude Code, Codex, Cursor and OpenCode (see COMPATIBILITY.md).
    • A free preflight-only version is on GitHub: qingsongcui/claude-code-skills.

    Produces a skeleton; you or your agent fill in the workflows. Works on local paths only and does not clone remote repositories. Requires Python 3.9+. Skill discovery in Claude Code, Codex, Cursor and OpenCode is not verified.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    Requires

    macOS
    Python

    Permissions

    Terminal / Shell
    Listed1 month ago
    Updated1 month ago

    What's inside

    Frequently Asked Questions

    It runs a license check, scaffolds a SKILL.md package from a manifest, and validates frontmatter, Python syntax and restricted-license terms in one command. You or your agent still write the real workflow content.

    The output follows the open Agent Skills format (a SKILL.md directory), which Claude Code, Codex, Cursor and OpenCode read. Skill discovery in those hosts is not verified for this package; see COMPATIBILITY.md. Confirm discovery in your own host before relying on auto-invocation.

    It reads the repository's LICENSE file and license metadata and returns DISTILL (permissive), INTERNAL_ONLY (copyleft, source-available or non-commercial terms) or NEEDS_REVIEW (unclear). The verdict is a license signal, not legal advice or a provenance check.

    Two skills (github-repo-skill-distiller and book-skill-distiller), four Python scripts, templates, a rubric, a golden fixture (fixtures/sample-todo-cli), and INSTALL, FIXTURE and COMPATIBILITY docs.

    Not directly. The repo distiller works on local code repositories. The book-skill-distiller gives you templates and a rubric that you or your agent apply to a handbook or manuscript; it does not parse PDFs or wikis for you.

    This skill requires a local environment with Python 3.9 or higher. While it automates the structure and safety checks, the final workflow logic may require a brief human review to fine-tune specific agent behaviors before deployment.

    New in Prompt & Skill Engineering