agentleFS
blackbenjaminblackbenjamin/etps/.claude/skills/project-documentation/SKILL.md

project-documentation

Skill1 starsChanged 11 months agoMITView on GitHub

Update and maintain project documentation including CLAUDE.md, API docs, architecture docs, and data model specs. Use when updating docs, documenting features, or after completing sprints.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. 0 are common, 11 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 11

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Update phase status (COMPLETE/IN PROGRESS)

    line 23
  2. Distinctive:

    Add new fields with types

    line 29
  3. Distinctive:

    Update JSON schema examples

    line 31
  4. Distinctive:

    Add to service map diagram

    line 36
  5. Distinctive:

    Add to API endpoints table

    line 38
  6. Very specific:

    Use backticks for code and file_paths

    line 57
  7. Distinctive:

    Use code blocks with language tags

    line 58
  8. Distinctive:

    Use tables for structured data

    line 59
  9. Distinctive:

    Keep line length reasonable (~80 chars)

    line 60
  10. Distinctive:

    Update docs immediately after changes

    line 64
  11. Very specific:

    Keep IMPLEMENTATION_PLAN.md current

    line 65
  12. Distinctive:

    Document all schema changes

    line 66
  13. Distinctive:

    Commit docs with related code changes

    line 68

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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

ETPS Documentation Management

Key Documents

DocumentPurposeUpdate When
CLAUDE.mdProject config for Claude CodeWorkflows change
ETPS_PRD.mdProduct Requirements (source of truth)Requirements change
docs/IMPLEMENTATION_PLAN.mdSprint roadmapSprint completes
docs/ARCHITECTURE.mdSystem architectureServices added
docs/DATA_MODEL.mdDatabase schemaModels change
docs/cover_letter_style_guide.mdAI writing rulesStyle rules change

Update Triggers

After Completing a Sprint

Update docs/IMPLEMENTATION_PLAN.md:

  • Mark completed tasks with [x]
  • Update phase status (COMPLETE/IN PROGRESS)
  • Update test count
  • Note any blockers or changes

After Changing Database Models

Update docs/DATA_MODEL.md:

  1. Add new fields with types
  2. Update relationships diagram
  3. Update JSON schema examples
  4. Increment version (e.g., v1.4.2 -> v1.4.3)

After Adding Services

Update docs/ARCHITECTURE.md:

  • Add to service map diagram
  • Document inputs/outputs
  • Add to API endpoints table

Version Numbering

Major.Minor.Patch
  │     │     └── Documentation clarifications
  │     └──────── New fields/entities
  └────────────── Breaking schema changes

Current Status

Documentation Style

  • Use backticks for code and file_paths
  • Use code blocks with language tags
  • Use tables for structured data
  • Keep line length reasonable (~80 chars)
  • Link between related documents

Best Practices

  1. Update docs immediately after changes
  2. Keep IMPLEMENTATION_PLAN.md current
  3. Document all schema changes
  4. Include examples in technical docs
  5. Commit docs with related code changes

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.