agentleFS
Sign inStart free
tofusitotofusito/multi-agents/skills/documentation/SKILL.md

documentation

Skill0 starsChanged 6 months agoMITView on GitHub

Technical documentation workflow for capturing work done — decisions, commands, issues, and resolutions — into structured Markdown notes saved to an Obsidian vault.

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 93 edited versions we read keep these.

  • 3

    Distinctive

    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:

    Never skip the replication checklist — it is the most valuable part for future reference

    line 65
  2. Distinctive:

    Do not push documents to any remote

    line 67
  3. Distinctive:

    Keep dynamic values (model IDs, config values, resource names) in their own table so they are easy to find when replicating

    line 68

“Common” is measured: kept by at least 6 in 10 of the 93 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

Workflow

  1. Determine output folder — use a short descriptor or project name (e.g. multi-agents, claude-api-refactor). Ask if unclear.
  2. Extract from conversation — goal, actions taken, decisions, problems, dynamic values, repos, branches.
  3. Fill gaps from git — only if conversation lacks detail: git log, git diff, recent commits.
  4. Write using the template below.
  5. Save to ~/writer/<folder-name>/<descriptive-name>.md. Create folder if needed.

Document template

---
tags: [#report, #<project>]
date: YYYY-MM-DD
status: active
---

# <Short description>

**Date:** YYYY-MM-DD | **Repos:** `<repos>` | **Context:** <brief context>

## Summary
One paragraph: what was done, key outcome, critical decisions.

## What Was Done
### 1. <First logical step>
**What:** description
**Why:** reason
**How:** commands run, files changed

### 2. <Next step>
...

## Dynamic Values
| Placeholder | Value | How to obtain |
|---|---|---|
| model id | `claude-sonnet-4-6` | anthropic docs |

## Issues Encountered
| # | Issue | Root Cause | Resolution |
|---|---|---|---|

## Replication Checklist
- [ ] Step 1 — with exact commands
- [ ] Step 2

## References
- Repo: https://github.com/...
- Docs: ...

Rules

  • Conversation content first, git history second
  • Never skip the replication checklist — it is the most valuable part for future reference
  • Flag gaps honestly as "needs confirmation" rather than guessing
  • Do not push documents to any remote
  • Keep dynamic values (model IDs, config values, resource names) in their own table so they are easy to find when replicating

Download now (ZIP)

  • Other versions103 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 103

    1. anthropics/knowledge-work-plugins★ 34ksame name
    2. comet-ml/opik★ 23ksame name
    3. mozilla-firefox/firefox★ 14ksame name
    4. microsoft/fast★ 9.7ksame name
    5. mufeedvh/code2prompt★ 7.7ksame name
    6. BrowserWorks/waterfox★ 6.4ksame name
    7. samchon/typia★ 5.9ksame name
    8. github/gh-aw★ 5.5ksame name
    9. epicenter-md/epicenter★ 4.8ksame name
    10. EpicenterHQ/epicenter★ 4.8ksame name

    93 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use project-preferences, response-style and 10 more.

    Other files people use alongside this one.

    Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
    • DepressionCenterSkill

      project-preferences

      Apply repository-specific preferences when planning, implementing, or reviewing changes in this project.

      Also in 4 projects that use this

    • DepressionCenterSkill

      response-style

      Write prose in plain, natural English. Apply to every response, design discussion, review comment, commit message, pull request, and document, in any task.

      Also in 4 projects that use this

    • BrowserWorksSkill

      accessibility-frontend-review

      Performs an accessibility code review of a local diff or Phabricator revision in the style of the Firefox accessibility team. Use this skill whenever the user asks to review a Phabricator patch or revision for accessibility issues, mentions a D-number (like D284142) in the context of accessibility review, asks "does this patch have any a11y issues", or wants to check a diff against accessibility guidelines. Also use it when the user says things like "can you review this for a11y", "check this patch", or "give me an accessibility review of D[number]". Invoke proactively when the user pastes a phabricator.services.mozilla.com URL or shares a revision ID alongside any accessibility concern. Invoke when questions about the following topics are raised: aria properties, aria roles, high contrast mode, forced colors, prefers contrast, focus order, screen readers, assistive technology.

      Also in 4 projects that use this

    • BrowserWorksSkill

      android-new-module

      Guide for creating new Android gradle modules in the android-components project.

      Also in 4 projects that use this

    • +8 more from BrowserWorks
  • In this repository7 other files it gives its agents.

Does it work?

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

Reviews can't be read right now.

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