agentleFS
6SNT-RADIO6SNT-RADIO/6SNT-Studio/skills/technical-documentation/SKILL.md

technical-documentation

Skill0 starsChanged 5 months agoMITView on GitHub

For the Technical Writer (10). Document reality (not the ideal) for two audiences (PO and AI); if code and docs differ, code wins; update before creating; less doc than product. Use it when closing stages.

33 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use clawhub-ban-appeals, clawhub-clawscan 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.
  • openclawSkill

    clawhub-ban-appeals

    Review ClawHub account-ban appeals, distinguish bans from moderation holds or blocked releases, and prepare an evidence-backed moderation decision. Route validated scanner inaccuracies to clawhub-clawscan.

    Also in 3 projects that use this

  • openclawSkill

    clawhub-clawscan

    Investigate ClawScan health alerts, diagnose scanner or ClawHub integration failures, prepare operational repairs, and route validated verdict inaccuracies upstream. Account ban appeals use clawhub-ban-appeals.

    Also in 3 projects that use this

  • FabienGreardSkill

    convex-acquire-domain

    Find and buy a domain for the current Convex app through Convex, then bind it (labs; spend action).

    Also in 3 projects that use this

  • +9 more from openclaw

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 31 edited versions we read keep these.

  • 2

    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:

    If the code says one thing and the docs say another, the code wins.

    line 12
  2. Distinctive:

    No aspirational documentation — only what exists today.

    line 13

“Common” is measured: kept by at least 6 in 10 of the 31 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

SKILL: technical-documentation

For: Agent 10 — TECHNICAL WRITER

Version: 1.0.0

Core principle

Documentation documents reality — not the ideal. If the code says one thing and the docs say another, the code wins. No aspirational documentation — only what exists today.

Audiences

Product Owner: README.md (start the project), operational runbooks, CHANGELOG.md. Criteria: clear language, no jargon, step by step, assuming no technical knowledge.

Executing AI: AGENTS.md (context + rules + constraints), CLAUDE.md/CODEX.md, API contracts, docstrings in critical modules. Criteria: explicit about what NOT to do, exact paths, no ambiguity.

Both: technical-operational runbooks, architecture decisions. Separate sections by audience — humans first, AI second.

Process

STEP 1 — Verify the existing: what's outdated, what's missing, what's extra. STEP 2 — Update before creating. Mark technical debt if it can't be updated. STEP 3 — Write only what doesn't exist and is necessary. Rule: 3 code files don't need 10 docs. STEP 4 — Declare technical debt explicitly if the code is badly built.

Minimal structure per document

README.md: What it is → Requirements → How to start → How it's used → Project structure. AGENTS.md: Identity → Immovable rules → Architecture → Current state → Workflow. API contracts: method/route, description, parameters, response, errors, constraints. Runbooks: title, when to use it, prerequisites, exact steps, what to do if it fails.

Signs of outdated documentation

⚠ References files that don't exist ⚠ Paths don't match the real structure ⚠ Commands that don't work when run ⚠ AGENTS.md rules that don't match real behavior

Good vs bad documentation

Good: a new person starts without asking, an AI modifies without breaking anything critical, paths and rules match reality. Bad: you have to read the code to understand the doc, instructions that don't work on every machine, doc longer than the code it documents.

Mistakes to avoid

× Documenting the ideal instead of reality × Leaving it outdated without marking it × Duplicating information across documents × Using jargon in PO documents × Omitting constraints in AGENTS.md × Producing more documentation than is consumed

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.