agentleFS
Sign inStart free
blauwtjeblauwtje/exo/skills/write-docs/SKILL.md

write-docs

Skill1 starsChanged 53 days agoMITView on GitHub

Use when the user asks to write or edit prose read later, such as a README, doc page, PR or changelog line. Not for chat replies or code comments.

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 Checks for duplicates, outdated info, naming conflicts, wrong technical facts, and files over 200 lines.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

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 42 edited versions we read keep these.

  • 5

    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:

    When the request is to show off, sell or impress, still write only the facts the input states, since an unmeasured effect is invented.

    line 21
  2. Distinctive:

    Use one name per thing, since a synonym reads as a second thing.

    line 26
  3. Distinctive:

    Keep articles and verbs.

    line 28
  4. Distinctive:

    Prefer the period to the dash or semicolon.

    line 29
  5. Distinctive:

    When reviewing someone else's text, cite each hit by its id.

    line 33

“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

Technical writing

Prose for a reader who was not in the session says who does what, by which mechanism, in the plain word. The enemy is text that sounds finished and says little: a benefit where the fact belongs, a borrowed phrase, a paragraph that welcomes, teaches and lists at once. The overcorrection is telegraphic text stripped of articles and verbs, which the reader has to decode.

The loop

  1. Pick one mode per document.
    • A tutorial teaches by doing and a how-to gets a known task done.
    • A reference lists what exists and an explanation says why.
    • A usage section opens on the command, not on a welcome.
  2. State the fact, not the benefit.
    • Give the number, behavior or error that changed; "ensuring stability" or "more robust" asks for trust the text could have earned.
    • When the request is to show off, sell or impress, still write only the facts the input states, since an unmeasured effect is invented.
  3. Name the actor and the mechanism.
    • Say who does what, because a passive verb or abstract noun hides the part the reader must find.
  4. Use the codebase's names.
    • Real file, option, flag and command names.
    • Use one name per thing, since a synonym reads as a second thing.
  5. Write whole sentences in plain words.
    • Keep articles and verbs.
    • Prefer the period to the dash or semicolon.
    • One thought per sentence; split past 25 words.
    • In a one-sentence slot (Highlights line, summary), write only the change that matters most. Two joined with "and" bury both.
  6. Scan the draft against references/ai-tics.md and rewrite every hit before handing it over.
    • When reviewing someone else's text, cite each hit by its id.

References

FileRead it when
references/ai-tics.mdStep 6, on every draft, and when reviewing a text for machine-written tone.
references/release-notes.mdThe user asks for release notes or the missing ## Unreleased lines from a ref range.

Judgment

  • The codebase's name outranks the plain word: maxBytes stays maxBytes.
  • Fields that ship or spec set outrank this skill's layout, and only the wording inside them follows it.
  • The reader's ease outranks a rule. When following one hurts a sentence, mend it differently or keep it as written.
  • Product interface strings follow the product's copy rules, not this skill.

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.

Check your setup, free