create-doc
Skill119 starsChanged 6 months agoMITView on GitHub
Use when the user wants to save knowledge as a file so others don't have to rediscover it — \"turn this into a doc\", \"write this up\", \"document how X works\", \"we figured this out and want to capture it\", \"nobody should have to figure this out again\". Covers any request to create or update durable written artifacts: onboarding guides, runbooks, ADRs, API docs, architecture notes, postmortems, changelogs, setup guides. The trigger: user wants knowledge captured in a file for future reference, not just a conversation. Do NOT use when still making decisions (→ give-plan), just asking for explanation without a file (→ ask), or writing code (→ cook).
2 other projects use a version of this.
Adopted by
Most recently taken up by
- skeletonlabs/skeletontheir own version, first seen Oct 8, 2026
- DGouron/review-flowtheir own version, first seen May 14, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- skeletonlabs/skeleton★ 6.1ksame name
- DGouron/review-flow★ 42same name
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 repository22 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agent-browserSkill
- askSkill
- cookSkill
- diagnoseSkill
- discussSkill
- docs-seekerSkill
- fixSkill
- frontend-designSkill
- give-planSkill
- media-processorSkill
- optimus-primeSkill
- prime-syncSkill
- review-codeSkill
- self-evolveSkill
- skill-creatorSkill
- testSkill
- backend-fastapi-pythonSkill
- dockerSkill
- frontend-developmentSkill
- humanizerSkill
- monorepoSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
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
- Distinctive: line 11
Check conversation context and skip completed steps.
- Distinctive: line 16
If the request is still evaluating options, stop and discuss — drafting docs before a decision is made locks in the wrong answer.
- Very specific: line 18
If the doc type is a recognized structured format (runbook, ADR, postmortem, onboarding guide, API/architecture doc), read …
- Distinctive: line 21
Before writing factual claims, read relevant sources — existing docs, code, config, tickets, PRs, prior discussion.
- Distinctive: line 24
Prefer updating the canonical existing doc when one exists.
- Very specific: line 31
When you need a fresh timestamp, use date +%Y%m%d%H%M%S.
- Distinctive: line 37
Write the file at the path from Step 3 — don't paste in chat without creating the file.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
ultrathink
Process
Check conversation context and skip completed steps.
1. Identify the doc job
Figure out the document type, audience, purpose, whether to update an existing doc or create new, and what source material it draws from. If any of these would materially change the output and are unclear, ask.
If the request is still evaluating options, stop and discuss — drafting docs before a decision is made locks in the wrong answer.
If the doc type is a recognized structured format (runbook, ADR, postmortem, onboarding guide, API/architecture doc), read references/doc-types.md now — it has the required sections for each type.
2. Ground in evidence
Before writing factual claims, read relevant sources — existing docs, code, config, tickets, PRs, prior discussion. Don't present guesses as fact. Label uncertain details explicitly, or collect them in an "Open questions" section rather than hedging every sentence.
3. Choose destination
Prefer updating the canonical existing doc when one exists.
For new documents, MUST default to docs/ at the repo root (create it if missing). Only deviate when:
- A more specific existing doc home clearly fits (ADR directory, changelog, README section, established project docs tree) — use it
- The repo already follows a convention of keeping docs next to the code they explain — match that
- The doc is event-like (postmortem, incident note) — use a timestamped filename
When you need a fresh timestamp, use date +%Y%m%d%H%M%S.
4. Outline first when substantial
For large or structurally ambiguous docs, propose a title and section outline before drafting. For small or routine docs, write directly.
5. Write the artifact
Write the file at the path from Step 3 — don't paste in chat without creating the file. Adapt structure to the document type (ADRs, runbooks, postmortems, API docs, etc.) and include only sections that earn their keep.
A strong document is accurate, concise, audience-aware, scannable, explicit about why something matters, and clear about what is current behavior vs. decision vs. open question. Write for the intended reader, not for completeness theater. Prefer concrete repo-specific details over generic filler. When sources conflict, name the conflict instead of quietly picking one.
6. Report and stop
Report the path, whether you updated or created, what was captured, and any assumptions or gaps. Do not drift into implementation unless explicitly asked.
Topic
<topic>$ARGUMENTS</topic>
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
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.

