agentleFS
Sign inStart free
nakane1chomenakane1chome/claude-skills/skills/flesh-out/SKILL.md

flesh-out

Skill0 starsChanged 8 months agoUnlicenseView on GitHub

Transform raw/crude document drafts into structured content. Use when a document is a skeleton of ideas, notes, or stream-of-consciousness that needs generative expansion rather than review polish.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the raw content and identify the key concepts

    line 17
  2. Distinctive:

    Create hierarchy (headers, sub-sections)

    line 35
  3. Distinctive:

    Add diagrams or tables where relationships exist

    line 36
  4. Distinctive:

    Ensure consistent usage throughout

    line 41
  5. Distinctive:

    Add links to external references (verify each URL resolves before adding)

    line 42
  6. Distinctive:

    Check with the user where to update the glossary

    line 45
  7. Distinctive:

    Add terms that needed clarification

    line 46
  8. Distinctive:

    Update references with new links

    line 47

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

This skill is for generative work on crude/raw content at $ARGUMENTS - not polishing drafts.

Stop after each stage and have changes reviewed with user.

Note: The developer's raw content captures intent. The agent expands and structures but must preserve the developer's meaning. When uncertain about intent, ask - don't assume.

See responsibilities.md for the full agent/developer ownership matrix.

  1. Extract core ideas (developer leads)
    • Read the raw content and identify the key concepts
    • List what the developer appears to be saying (don't fix typos yet)
    • What is the document's function? (its type and role — e.g., design doc, tutorial, proposal)
    • What is the document's goal? (the concrete outcome it exists to produce — e.g., a working implementation, an adopted practice)
    • Identify gaps: "You mention X but don't explain Y - should I research this?"
    • Confirm understanding with developer before proceeding
  2. Research and expand (agent leads with approval)
    • Web search for external concepts if applicable
    • Find industry terminology for rough ideas
    • Identify related work the developer may want to reference
    • Propose expansions - developer approves what to include
    • Verify every reference before presenting: fetch URLs, confirm they resolve, confirm the source supports the claim. Do not present unverified links to the developer.
  3. Structure the content (agent leads with approval)
    • Determine appropriate document structure (based on template if available)
    • Organize ideas into logical sections
    • Does the structure serve the document's function and support its goal?
    • Create hierarchy (headers, sub-sections)
    • Add diagrams or tables where relationships exist
  4. Polish language (agent leads with approval)
    • Fix spelling, grammar, terminology
    • Expand acronyms on first use
    • Ensure consistent usage throughout
    • Add links to external references (verify each URL resolves before adding)
  5. Tidy up (agent leads with approval)
    • Check with the user where to update the glossary
    • Add terms that needed clarification
    • Update references with new links

When to Use This vs Other Skills

Document StateUse
Raw notes, bullet points, stream of consciousnessflesh-out
Typos, incomplete sentences, but has structurereview-steps
Structured but missing sectionsflesh-out (or discuss scope first)
Complete draft needing polishreview-steps
Complete draft needing critical evaluationstrong-edit

Key Difference from Review

Review improves what exists within its structure. Flesh-out creates structure from raw ideas.

Review a skeleton -> correct but incomplete document. Flesh-out a skeleton -> complete document.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free