openclaw-refactor-docs
Skill393k starsChanged 7 days agoMITView on GitHub
Refactor an existing OpenClaw docs page with source-audited preservation, restructuring, and verification.
We split this skill into the rules it gives an agent
30 rules. About 0 are common, 26 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈26
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Use this skill when the user gives a target OpenClaw docs page and asks to rewrite, refactor, reorganize, split, shorten, or improve it.
- Distinctive: line 31
If the target page is missing or ambiguous, ask one concise question before editing.
- Distinctive: line 39
Do not treat a rewrite as permission to discard behavior facts.
- Very specific: line 56
Read ../technical-documentation/SKILL.md first.
- Very specific: line 59
Run pnpm docs:list when available, then read only the target page and the likely entry points, references, or related pages needed for the …
- Very specific: line 64
Before editing, decide the intended page type from technical-documentation.
- Distinctive: line 66
If the current page mixes page types, choose the main page type and plan where the other material belongs:
- Distinctive: line 72
Keep concise routing, decision, and safety details in the main page when readers need them to complete the workflow.
- Distinctive: line 77
Create a working inventory from the old page before rewriting.
- Distinctive: line 92
Keep it in the refactored target page.
- Distinctive: line 95
Delete it because current source proves it is obsolete or out of scope.
- Distinctive: line 97
Do not infer defaults, permissions, policy, timeout behavior, or safety posture from names or intent.
- Distinctive: line 102
Use the nearest authoritative source for each behavior-sensitive claim:
- Distinctive: line 114
If a page promises a reference, compare its tables against the schema, manifest, CLI help, generated docs, or exported types.
- Distinctive: line 120
When moving detail out of the target page, record the destination before editing:
- Distinctive: line 129
Avoid duplicate truth. If the same contract appears in multiple places, choose one canonical page and link to it.
- Distinctive: line 137
Put the recommended path before alternatives.
- Distinctive: line 138
Keep only decision-making and common operational detail in the main flow.
- Distinctive: line 142
Add troubleshooting from observable symptoms, not internal guesses.
- Very specific: line 145
Add doc-schema-version: 1 to the YAML frontmatter of every docs page that the refactor migrates, creates, or materially rewrites.
- Distinctive: line 151
Do not leave placeholders such as "TODO", "TBD", or "see docs" unless the user explicitly asks for a draft.
- Distinctive: line 156
After editing, compare the old and new page:
- Distinctive: line 160
Check that the main page still covers the 80/20 scenario end to end.
- Distinctive: line 161
Check that reference pages remain exhaustive for the scope they claim.
- Distinctive: line 162
Check that links from the target page reach moved details.
- Distinctive: line 163
Check that headings are stable, searchable, and action-oriented.
- Distinctive: line 165
If the refactor deliberately removes relevant material, say where it went or why it was removed in the final report.
- Distinctive: line 170
Run the smallest reliable docs checks for the touched surface:
- Distinctive: line 182
Run commands and examples from the page whenever feasible.
- Distinctive: line 195
Do not include a long rewrite diary.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
OpenClaw Refactor Docs
Overview
Use this skill when the user gives a target OpenClaw docs page and asks to rewrite, refactor, reorganize, split, shorten, or improve it.
This skill builds on technical-documentation: use that skill for style, page types,
structure, examples, discoverability, and verification. This skill adds the
rewrite workflow needed to avoid losing accurate behavior during a major docs
refactor.
Inputs
Required:
- A target docs page path, such as
docs/plugins/codex-harness.md.
Optional:
- Desired page type, such as topic page, guide, reference, or troubleshooting.
- Specific goals, such as shorter main page, move details to reference pages, or align with current CLI behavior.
- Related source files, schemas, commands, tests, specs, or PRs.
If the target page is missing or ambiguous, ask one concise question before editing. Otherwise, proceed.
Working Contract
Refactor the target page to be more useful, concise, and comprehensive within its stated scope.
Do not treat a rewrite as permission to discard behavior facts. Preserve, verify, move, or explicitly retire existing material. Incorrect docs are worse than verbose docs.
Prefer this split:
- Topic or guide pages cover the 80/20 path, decisions readers must make, safe setup, smallest reliable verification, common failures, and links onward.
- Reference pages cover exhaustive fields, defaults, enums, limits, precedence rules, API contracts, narrow internals, and rare debugging details.
- Troubleshooting pages start from observable symptoms and map to checks, causes, and fixes.
Workflow
1. Load the doc standard
Read ../technical-documentation/SKILL.md first. Apply its page-type, style,
examples, navigation, and verification guidance throughout the refactor.
Run pnpm docs:list when available, then read only the target page and the
likely entry points, references, or related pages needed for the refactor.
2. Classify the page
Before editing, decide the intended page type from technical-documentation.
If the current page mixes page types, choose the main page type and plan where the other material belongs:
- Move exhaustive contracts to an existing or new reference page.
- Move symptom-driven material to an existing or new troubleshooting page.
- Move narrow setup workflows to a guide when they interrupt the main path.
- Keep concise routing, decision, and safety details in the main page when readers need them to complete the workflow.
3. Preserve and audit existing facts
Create a working inventory from the old page before rewriting. Include:
- Config fields, flags, commands, slash commands, env vars, defaults, enums, nullable values, and constraints.
- Precedence rules, fallback behavior, caps, limits, rate limits, timeouts, lifecycle states, queueing behavior, and compatibility rules.
- Auth, permission, approval, sandbox, safety, privacy, and destructive-action behavior.
- Setup requirements, supported versions, dependencies, operating systems, credentials, and account requirements.
- Error messages, troubleshooting symptoms, diagnostics, and recovery steps.
- Examples, expected output, command routing tables, and cross-links.
For each fact, choose one outcome:
- Keep it in the refactored target page.
- Move it to a specific existing page.
- Move it to a specific new page.
- Delete it because current source proves it is obsolete or out of scope.
Do not infer defaults, permissions, policy, timeout behavior, or safety posture from names or intent. Verify them.
4. Find source of truth
Use the nearest authoritative source for each behavior-sensitive claim:
- Public schema, plugin manifest, generated config docs, or exported types for config fields.
- CLI implementation, slash-command handlers, help text, and command tests for commands and flags.
- Runtime source and tests for lifecycle, queueing, permission, fallback, timeout, and provider behavior.
- Protocol docs, SDK facades, and contract tests for APIs and plugin surfaces.
- Existing docs only as secondary evidence unless the target is purely conceptual.
If a page promises a reference, compare its tables against the schema, manifest, CLI help, generated docs, or exported types. Missing public fields, defaults, precedence rules, caps, or side effects are correctness bugs.
5. Plan moved material
When moving detail out of the target page, record the destination before editing:
- Existing page: name the page and section.
- New page: choose the page type, slug, title, frontmatter summary,
doc-schema-version: 1, andread_whenhints. - Target page: keep a short summary and link from the point where readers need the deeper detail.
Avoid duplicate truth. If the same contract appears in multiple places, choose one canonical page and link to it.
6. Rewrite
Rewrite in this order:
- Make the first screen answer what the reader can do and why this page exists.
- Put the recommended path before alternatives.
- Keep only decision-making and common operational detail in the main flow.
- Move exhaustive tables and rare details to the planned reference pages.
- Preserve concise routing tables when they help readers choose commands, config paths, harnesses, plugins, providers, or references.
- Add troubleshooting from observable symptoms, not internal guesses.
- Link related concepts, guides, references, diagnostics, and adjacent tools.
Add doc-schema-version: 1 to the YAML frontmatter of every docs page that the
refactor migrates, creates, or materially rewrites. Apply it only to docs page
files, not docs.json, glossary JSON, or other non-page metadata. If a
migrated page is generated, update the generator so regeneration preserves the
marker instead of hand-editing generated output.
Do not leave placeholders such as "TODO", "TBD", or "see docs" unless the user explicitly asks for a draft.
7. Compare old and new
After editing, compare the old and new page:
- Confirm all behavior-sensitive facts were kept, moved, or intentionally deleted with source-backed reason.
- Check that the main page still covers the 80/20 scenario end to end.
- Check that reference pages remain exhaustive for the scope they claim.
- Check that links from the target page reach moved details.
- Check that headings are stable, searchable, and action-oriented.
If the refactor deliberately removes relevant material, say where it went or why it was removed in the final report.
8. Verify
Run the smallest reliable docs checks for the touched surface:
pnpm docs:listgit diff --check -- <touched-files>- Targeted
pnpm exec oxfmt --check --threads=1 <touched-files> pnpm docs:check-mdxpnpm docs:check-linkspnpm docs:check-i18n-glossarywhen link text, navigation, labels, or glossary surfaces changed- Generated-doc checks when schemas, generated config docs, API docs, or generated baselines are touched
Run commands and examples from the page whenever feasible. If you cannot verify a behavior-sensitive claim, either remove the claim, mark the uncertainty in the work-in-progress report, or ask for the missing source.
Final Report
Report:
- What changed in the target page.
- What details moved and their destination pages.
- What source-of-truth checks backed behavior-sensitive claims.
- What validation ran and what failed for unrelated reasons.
Do not include a long rewrite diary. Lead with remaining risks only if there are any.
Trending
Quiet since March.about the whole repository
Who's talking about moltbot/moltbot
- A Hacker News story“Clawdbot Renames to Moltbot”Hacker News · Jan 27, 2026 · 249 points
- openclaw/openclaw“Fixes cron jobs”GitHub · Jan 28, 2026 · 17 reactions
- openclaw/openclaw“[Feature]: Add Email (AgentMail) as a channel”GitHub · Jan 30, 2026 · 8 reactions
- @aellalabrys.bsky.social“Hier liegen die Sourcen. Moltbot verwendet vorwiegend TypeScript, nur einige Anpassungen sind in Swift (für …”Bluesky · Jan 28, 2026 · 6 likes
- openclaw/openclaw“feat(providers): add ANTHROPIC_BASE_URL environment variable support”GitHub · Jan 27, 2026 · 6 reactions
The biggest 5 of 54 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 54
Talked about on GitHub, the web, Bluesky and Hacker News (54 times).
On GitHub · 32
- Jan 28, 2026Fixes cron jobs — openclaw/openclaw17 reactions · 6 comments
- Jan 30, 2026[Feature]: Add Email (AgentMail) as a channel — openclaw/openclaw8 reactions · 2 comments
- Jan 27, 2026feat(providers): add ANTHROPIC_BASE_URL environment variable support — openclaw/openclaw6 reactions · 1 comment
- Jan 28, 2026[Feature]: x402 payment protocol extension — openclaw/openclaw5 reactions · 5 comments
- Jan 28, 2026feat(models): Add Kimi K2.5 support for the kimi coding plan — openclaw/openclaw3 reactions
27 more on GitHub
- Jan 31, 2026fix(docs): update MiniMax plugin URL from legacy moltbot org — openclaw/openclaw2 reactions · 1 comment
- Jan 30, 2026feat: add Dokploy deployment guide — openclaw/openclaw2 reactions · 2 comments
- Jan 30, 2026fix(slack): Convert Unicode emojis to Slack shortcodes for ack reactions — openclaw/openclaw2 reactions · 1 comment
- Jan 29, 2026首个打通了企业微信,稳定好用。 — openclaw/openclaw2 reactions
- Jan 29, 2026Fix/3038 cli name moltbot — openclaw/openclaw1 reaction · 4 comments
- Jan 29, 2026fix(subagent): fix subagent thinking override — openclaw/openclaw1 reaction · 1 comment
- Jan 29, 2026Fix: File ID Format Mismatch When Switching from Gemini to OpenAI #3702 — openclaw/openclaw1 reaction · 1 comment
- Jan 28, 2026Merge branch 'main' of https://github.com/moltbot/moltbot — openclaw/openclaw1 reaction · 1 comment
- Jan 28, 2026feat(fireworks): integrate Fireworks AI support into onboarding and a… — openclaw/openclaw1 reaction · 1 comment
- Jan 28, 2026[macOS] Telegram long-polling causes 'fetch failed' crash (Node 23) — openclaw/openclaw1 reaction · 4 comments
- Jan 28, 2026fix(slack): forward threadId in extension read action — openclaw/openclaw1 reaction · 1 comment
- Jan 27, 2026[Bug]: Wrong dependency or possible rogue package — openclaw/openclaw1 reaction · 2 comments
- Jan 27, 2026feat: add Moltbot template — Dokploy/templates1 reaction · 2 comments
- Mar 17, 2026feat(pipeline): orchestrator, parallel backfill, and URL redirect dedup fix — yya007/SkillFinder0 reactions
- Feb 4, 2026sessions_spawn ignores target agent's model config, uses caller's model instead — openclaw/openclaw0 reactions · 1 comment
- Feb 3, 2026[Security] Multiple Credential Inputs Vulnerable to Type Coercion Leading to Predictable 'undefined' Values — openclaw/openclaw0 reactions
- Jan 31, 2026refactor: rename moltbot to openclaw branding — marcusquinn/aidevops0 reactions · 9 comments
- Jan 30, 2026feat: enhance OpenAI compatibility for tool calling — openclaw/openclaw0 reactions · 17 comments
- Jan 29, 2026[Feature]: Add Cognee as optional memory provider — openclaw/openclaw0 reactions · 3 comments
- Jan 29, 2026Fix npm binary: use moltbot@beta tag to get working bin field (#3787) — Joe-Heffer/deploy-openclaw0 reactions
- Jan 29, 2026fix(telegram): preserve reasoning tags inside code blocks (#3952) — openclaw/openclaw0 reactions · 1 comment
- Jan 29, 2026Feature[https://github.com/moltbot/moltbot/issues/3694] Public WebChat route /public/chat (UI shell) — openclaw/openclaw0 reactions · 8 comments
- Jan 28, 2026Giving Access to MacOS — openclaw/openclaw0 reactions · 1 comment
- Jan 28, 2026--json option does not exist in `browser set headers` — openclaw/openclaw0 reactions · 3 comments
- Jan 27, 2026refactor: rename Clawdbot to Moltbot across repo — marcusquinn/aidevops0 reactions · 5 comments
- Jan 27, 2026feat: add Moltbot template — Dokploy/templates0 reactions · 2 comments
- Jan 26, 2026feat: adding support for Together ai provider — openclaw/openclaw0 reactions · 2 comments
On the web · 14
- Feb 20, 2026Moltbot Review: Local-First AI Agent Architecture — linkedin.com
- Feb 3, 2026Moltbot: 83 сценария использования open-source AI-агента / Хабр — habr.com
- Feb 1, 2026ClawBot(Moltbot)安装与上手:用一条命令在本地跑起个人 AI 助手(含 Dashboard/Chat)_人工智能_JavaEdge.-2048 AI社区 — devpress.csdn.net
- Jan 31, 2026In-Depth Moltbot Analysis for AI Developers — blog.promptlayer.com
- Jan 30, 2026Docker方式安装你的私人AI电脑助手Moltbot_moltbot docker-CSDN博客 — blog.csdn.net
9 more on the web
- Jan 29, 2026Moltbot (Clawdbot) : Setup Guide+ API hosting Tutorial — dev.to
- Jan 29, 2026Running Moltbot (Clawdbot) with Bifrost: Observability, Cost Control, and Multi-Model Routing — dev.to
- Jan 29, 2026Falling in and out of love with Moltbot — platformer.news
- Jan 28, 2026Self-Hosted AI Assistant: Complete Moltbot Installation Guide for Docker — dev.to
- Jan 28, 2026How Clawdbot gave me back 40 hours in minutes. — linkedin.com
- Jan 27, 2026Moltbot (Clawdbot) What it is and isn't - by Matt Taylor — mjtdev.substack.com
- Jan 27, 2026Clawdbot → Moltbot: How the Viral Self-Hosted AI Agent Actually Works (2026 Deep Dive) - A Streak of Communication — telestreak.com
- Jan 27, 2026Moltbot Review 2026: Everything You Need to Know About the… | NxCode — nxcode.io
- Jan 26, 2026Clawdbot [Moltbot/OpenClaw], или почему нужно срочно дать языковой модели контроль над вашим Mac mini / Хабр — habr.com
On Bluesky · 5
- Jan 28, 2026Hier liegen die Sourcen. Moltbot verwendet vorwiegend TypeScript, nur einige Anpassungen sind in Swift (für Apple) und Kotlin (für Android)… — @aellalabrys.bsky.social6 likes and reposts · 1 reply
- Jan 29, 2026💎 Hidden Gem! 💎 (1000+ new stars) 📦 moltbot / moltbot ⭐ 89,672 (+17,830) 🗒 TypeScript Your own personal AI assistant. Any OS. Any… — @github-trending.bsky.social5 likes and reposts · 1 reply
- Jan 29, 2026💎 Hidden Gem! 💎 (1000+ new stars) 📦 moltbot / moltbot ⭐ 89,672 (+17,830) 🗒 TypeScript Your own personal AI assistant. Any OS. Any… — @github-trending-js.bsky.social2 likes and reposts · 1 reply
- Jan 29, 2026今日のGitHubトレンド moltbot/moltbot Moltbotは、個人のデバイスで動作するAIアシスタントです。 WhatsApp、Telegram、Slackなど様々なチャネルで応答し、音声入力やCanvasの操作も可能です。… — @dailygithubtrends.bsky.social1 likes and repost
- Jan 27, 2026Clawdbot is a personal AI assistant you run on your own devices. It answers you on the channels you already use (WhatsApp, Telegram, Slack,… — @ytroncal.bsky.social1 likes and repost
On Hacker News · 3
- Jan 27, 2026Clawdbot Renames to Moltbot249 points · 227 comments
- Jan 27, 2026Clawdbot Renamed to Moltbot2 points · 1 comment
- Jan 29, 2026Moltbot: Own Personal AI Assistant1 point · 1 comment
Other versions11 projects use a version of this.
Word for word · 9
- clawdbot/clawdbot★ 393k100% same
- steipete/warelay★ 392k100% same
- moltbot/clawdbot★ 392k100% same
- steipete/clawdis★ 392k100% same
- molt-bot/clawdbot★ 391k100% same
- openclaw/openclaw★ 391k100% same
- friuns2/openclaw-android-assistant★ 556100% same
- OpenClawAndroid/openclaw-android-assistant★ 556100% same
- bighamx/openclaw-android-node-apk★ 59100% same
Edited · 2
- clawsouls/soulclaw★ 998% same
- supermansuper563-ops/openclaw-workbench★ 098% same
Wrote their own version · 0
None found.
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 repository109 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- extensions/AGENTS.mdAGENTS.md
- scripts/AGENTS.mdAGENTS.md
- test/AGENTS.mdAGENTS.md
- ui/AGENTS.mdAGENTS.md
- agent-transcriptSkill
- auto-qaSkill
- autoreviewSkill
- channel-message-flowsSkill
- clawdtributorSkill
- claw-scoreSkill
- clawsweeperSkill
- control-ui-e2eSkill
- crabboxSkill
- discord-clawdSkill
- discord-e2eSkill
- discord-user-postSkill
- discrawlSkill
- gitcrawlSkill
- graincrawlSkill
- notcrawlSkill
- openclaw-changelog-updateSkill
- openclaw-ci-limitsSkill
- openclaw-debuggingSkill
- openclaw-docker-e2e-authoringSkill
- openclaw-ghsa-maintainerSkill
- openclaw-live-updaterSkill
- openclaw-parallels-smokeSkill
- openclaw-performanceSkill
- openclaw-pr-maintainerSkill
- openclaw-qa-testingSkill
- openclaw-release-validationSkill
- openclaw-repair-sweepSkill
- openclaw-secret-scanning-maintainerSkill
- openclaw-test-heap-leaksSkill
- openclaw-testingSkill
- openclaw-test-performanceSkill
- openclaw-updateSkill
- parallels-discord-roundtripSkill
- plugin-sdk-impactSkill
- proof-videoSkill
- prototype-openclaw-tuiSkill
- pr-simplifySkill
- release-openclaw-announcementSkill
- release-openclaw-ciSkill
- release-openclaw-macSkill
- release-openclaw-maintainerSkill
- release-openclaw-plugin-testingSkill
- security-triageSkill
- slack-e2eSkill
- slacrawlSkill
- solidSkill
- tag-duplicate-prs-issuesSkill
- technical-documentationSkill
- telegram-e2e-userbotSkill
- test-auditSkill
- update-team-serverSkill
- verify-releaseSkill
- 1passwordSkill
- The first 60 shown.
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.

