agentleFS
sahil1115sahil1115/claude-skills/spec-cleanup/SKILL.MD

spec-cleanup

Skill2 starsChanged 4 months agoMITView on GitHub

Final-pass cleanup of specs/design docs to remove iteration

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Preserve Structure: Do not restructure the document, change heading levels, or merge sections unless absolutely necessary.

    line 14
  2. Distinctive:

    Dry & Technical Tone: Use direct, authoritative language.

    line 15
  3. Distinctive:

    No Hallucinations: Do not invent new features, requirements, or technical details to fill gaps.

    line 16
  4. Distinctive:

    Necessity: Every section is strictly necessary for the CURRENT design.

    line 27
  5. Distinctive:

    Cohesion: No section references another section that no longer exists.

    line 28
  6. Very specific:

    Links: All internal markdown links (text) point to valid, existing headings.

    line 30

≈ “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

Spec Cleanup

Rewrite the document as a standalone specification. The reader has never seen any previous version.

Constraints

  • Preserve Structure: Do not restructure the document, change heading levels, or merge sections unless absolutely necessary. Keep the original hierarchy.
  • Dry & Technical Tone: Use direct, authoritative language. No conversational filler, no meta-commentary ("This section details...", "As shown below...").
  • No Hallucinations: Do not invent new features, requirements, or technical details to fill gaps. If a section is empty after cleanup, delete it or flag it.

Remove

  • Historical Baggage: References to prior drafts, versions, or rejected alternatives ("previously", "instead of the old X", "unlike v1", "updated to", "(new)").
  • Phantom Comparisons: Comparisons against designs that no longer exist in the doc.
  • Orphaned Sections: Headings whose content was gutted by edits, or sections only meaningful relative to removed content.
  • Change Rationale: Justifications framed as change rationale ("we switched to X because the old approach..."). Restate as direct design rationale or move to DECISIONS.md.
  • Stale Artifacts: Outdated code snippets, deprecated config flags, or Mermaid/PlantUML diagrams that no longer match the current text.
  • Unresolved Placeholders: TODO, TBD, FIXME, or [Needs Review] markers. (If you cannot resolve them, move them to a dedicated "Open Questions" section at the end).

Verify

  • Necessity: Every section is strictly necessary for the CURRENT design.
  • Cohesion: No section references another section that no longer exists.
  • Terminology: Terminology is consistent throughout (renames fully propagated).
  • Links: All internal markdown links ([text](#anchor)) point to valid, existing headings.
  • Vibe Check: The doc reads as if written in one sitting by a single author.

Output

  1. The cleaned, standalone spec in Markdown.
  2. A brief ## Changelog & Relocations section at the very bottom listing:
    • Sections/content that were deleted.
    • Content that was moved (e.g., "Moved old auth rationale to DECISIONS.md").
    • Unresolved TODOs that were flagged.

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.