agentleFS
oberon-systemsoberon-systems/enggraph/skills/write-docs/SKILL.md

write-docs

Skill1 starsChanged 6 days agoMITView on GitHub

Write or edit documentation - service utilities, project, code, service, SOP or known-issue notes - in a lint-clean, runbook-first house style. Use whenever documentation is created, restructured or reviewed.

43 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use close-spec, design-with-images 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.
  • dzhngSkill

    close-spec

    When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec), archive it to specs/done/ and rewrite it from a build-plan into a durable rationale — the why, the principles, the invariants — pointing back to the real code for the how. Use when implementation has landed and the plan no longer matches what shipped, or the user says a feature/spec is finished. Pairs with [write-spec](../write-spec/SKILL.md) (the plan this closes) and [review](../review/SKILL.md) (run before closing).

    Also in 5 projects that use this

  • dzhngSkill

    design-with-images

    Explore UI and visual design with image generation, then iterate the real implementation against the user-selected concept. Use when brainstorming visual directions, offering mockup variants, or implementing an approved generated design; do not stop at the mockups or the first code approximation.

    Also in 5 projects that use this

  • transitive-bullshitSkill

    compare-screenshots

    Compare screenshots against the intended design, distinguishing approved references from historical baselines. Use for iterative implementation matching, before/after visual review, objective image telemetry, or checking a lone capture for flat, empty, or badly framed content.

    Also in 5 projects that use this

  • LucasMatuszewskiSkill

    audit-agents

    Audit and maintain agent configuration files (.claude/agents, AGENTS.md, CLAUDE.md, agent-memory). Checks for duplicates, outdated info, naming conflicts, wrong technical facts, and files over 200 lines. Fixes all issues and commits.

    Also in 5 projects that use this

  • wolverin0Skill

    audit-decisions

    Standardize remediation decisions, baseline-policy entries, and legal-review banners for accepted, deferred, or policy-blocked audit findings.

    Also in 4 projects that use this

  • rhnfzlSkill

    explore-unknowns

    Walk the user through mapping the unknowns of a task before, during, and after they build it, and hand them a four-quadrant map (settled ground, open decisions, taste, and landmines) they keep. Reach for this eagerly whenever a request is ambiguous or underspecified, the codebase or domain is unfamiliar, the user will "know it when they see it", a reference implementation must be understood before porting, a build-queue or architecture-changing task is about to start, a mid-build deviation needs capturing, or a finished change needs buy-in or verified understanding before merge. Trigger even when the skill is not named: "do a blindspot pass", "find my unknown unknowns", "interview me about this change", "brainstorm the approach for a task I am about to build", "help me scope this", "what am I missing here", "plan this before I build", "I know nothing about X in this codebase". When a territory profile is present it reads memory and the graph first and feeds the map into the build pipeline; without one it degrades to a plain general map. Not for trivial or mechanical tasks with clear acceptance criteria, single-fact lookups, pure debugging of a known symptom, or pure code review, those have their own tools. Do not use it to run the build itself; the map is the deliverable and implementation remains a separate task, whether it has not started or is already underway.

    Also in 5 projects that use this

  • +6 more from dzhng
  • Other versions43 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 43

    1. tldraw/tldraw★ 51ksame name
    2. tabler/tabler★ 42ksame name
    3. videojs/video.js★ 40ksame name
    4. PrefectHQ/prefect★ 24ksame name
    5. comet-ml/opik★ 23ksame name
    6. coder/coder★ 17ksame name
    7. browseros-ai/BrowserOS★ 14ksame name
    8. Agenta-AI/agenta★ 4.9ksame name
    9. liveblocks/liveblocks★ 4.8ksame name
    10. dzhng/jevgrep★ 3.2ksame name

    33 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.

  • In this repository5 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 42 edited versions we read keep these.

  • 4

    Distinctive

    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:

    No table of contents, whatever the heading count.

    line 50
  2. Distinctive:

    No runbooks: state the rule, do not demonstrate it.

    line 51
  3. Very specific:

    Read the repository's own conventions - CLAUDE.md, GEMINI.md, CONTRIBUTING.md, docs/README.md - before drafting.

    line 86
  4. Distinctive:

    Add or refresh the table of contents when the type allows one and the document has more than three H2 headings.

    line 93
  5. Distinctive:

    Commit through the repository's commit flow.

    line 96

“Common” is measured: kept by at least 6 in 10 of the 42 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

Write Docs

Pick the document type first, obey the general rules, and lint the result before reporting it as done. One document may hold several types as sections - a service description followed by an SOP and its known issues is one document, not three. Where a repository states its own convention, that convention wins over the defaults here.

General rules

  • Format - Markdown. Every fenced block carries a language tag (bash, text, yaml, ...).
  • Charset - ASCII only. No smart quotes, em dashes, non-breaking spaces or box drawing.
  • Graphics - ASCII art only.
  • Lint - the document passes markdownlint without edits: blank line around every heading, list and fenced block, one H1, no duplicate heading text, no trailing punctuation in headings, no trailing whitespace, no hard tabs, file ends with a single newline.
  • Language - English, unless the user asks for another language.
  • Table of contents - required once a document has more than three H2 headings: a bullet list of links to the H2 headings, placed under the intro paragraph. Service utilities are the exception - see below.
  • Size - one item is at most one paragraph, three to four sentences. Prose that overflows becomes its own section. Lists, tables and code blocks do not count against it.
  • Style - the simplest language that is still accurate: short sentences, active voice, second person in procedures. Link every external product on first mention.
  • Runbooks - examples, tests and procedures are copy-pasteable: one command per line, no $ prompt inside the block, expected output shown separately.

Document types

Pick the type before writing. If the request fits none of them, ask the user instead of guessing.

Service utilities

Skills, agent instructions, memory and plans - documents an agent reads, not a person.

  • No table of contents, whatever the heading count.
  • No runbooks: state the rule, do not demonstrate it.

Project description

  • Why the project exists, which tasks and goals it serves.
  • How it implements those goals.

Code description

  • What the code does.
  • Its main classes and methods.
  • Two or three usage examples.

Service description

  • Why the service is needed.
  • How it is implemented.
  • How to install it.
  • How to integrate it.
  • Examples.

SOP

  • What the procedure covers.
  • The procedure itself, as a copy-paste runbook.
  • How to test that it worked.

Known issues

  • The problem: symptom, trigger, blast radius.
  • A runbook that fixes it.

Workflow

  1. Identify the type, asking the user when it is ambiguous.
  2. Read the repository's own conventions - CLAUDE.md, GEMINI.md, CONTRIBUTING.md, docs/README.md - before drafting. A repository-specific template is a contract: keep its headers, field lines and numbering.
  3. Extend a document that already covers the topic rather than adding a second one.
  4. Draft against the general rules and the type's required content.
  5. Add or refresh the table of contents when the type allows one and the document has more than three H2 headings.
  6. Validate, fix, revalidate.
  7. Commit through the repository's commit flow.

Validation

Markdown linters are rarely on PATH: they live in a project virtualenv, in node_modules, or behind pre-commit. Find the one this repository uses, then run it on the file. These two checks close the gap the linter leaves - the first must print nothing, the second must show no stale link to a document you renamed.

grep -nP '[^\x00-\x7F]' "docs/my-note.md"
grep -rn "old-basename" --include='*.md' .

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.