technical-documentation
openclaw/openclaw-windows-node/.agents/skills/technical-documentation/SKILL.md
Write, review, or restructure Windows node documentation and agent instructions using current source, task-focused explanations, and explicit fact preservation.
What's in it
- Windows technical documentation
- Choose the reader's task
- Verify the explanation
- Validate and hand off
- Source and maintenance
--- name: technical-documentation description: Write, review, or restructure Windows node documentation and agent instructions using current source, task-focused explanations, and explicit fact preservation. --- # Windows technical documentation Use for repository docs, contributor instructions, and skill explanations. A request to audit or plan remains read-only; rewriting requires authorization. ## Choose the reader's task Read [documentation ownership](../../../docs/AGENTS.md), then the target page and the source that owns its claims. Do not preload the entire docs collection. | Page | First useful result | |---|---| | Overview | The reader chooses the appropriate guide | | Guide | One recommended workflow reaches an observable outcome | | Reference | A precise contract answers a specific lookup | | Troubleshooting | A symptom leads to a check, interpretation, and next action | | Agent instruction | A task routes to its owner, constraints, and required evidence | State what the page covers and what it does not. Explain the normal path before alternatives. Put prerequisites and safety boundaries before the affected command; place rare cases and exhaustive contracts in named references. Concise means less unnecessary explanation, not an arbitrary word or line cap. ## Verify the explanation - Check commands, flags, defaults, settings locations, owners, and failure behavior against current source. Label an unverified claim rather than filling it in from a name or an old plan. - Separate current behavior, historical measurements, proposals, and proof. A fixture or local MCP result does not establish real Gateway or UI behavior. - Use complete PowerShell examples with bounded placeholders and an expected result. Never copy live credentials or machine-specific private state. - Link the canonical explanation instead of restating its rules in several places. Keep the architecture ledger authoritative. - Preserve the full `winnode` command reference: it is shipped as `skill.md` and checked against capability registration. A catalog split is a packaging change, not an editorial shortcut. For a rewrite or split, use the [fact-preservation procedure](references/refactoring.md). Do not turn a documentation request into code cleanup or a repo-wide audit. ## Validate and hand off Run the existing checks from the repository root: ```powershell .\scripts\validate-docs.ps1 .\scripts\validate-agent-skills.ps1 git diff --check ``` Use [test selection](../../../docs/TEST_COVERAGE.md#formal-validation-paths) for executable changes or shipped command-reference changes. Do not run native runtime proof for ordinary prose changes. Do not claim a command or UI flow was exercised when only its source or documentation was checked. Report the page's purpose, corrected claims, destinations of moved facts, checks performed, and unresolved claims. Publication needs separate authority. ## Source and maintenance Windows-owned guidance, informed by the MIT-licensed OpenClaw [documentation overlay](https://github.com/openclaw/openclaw/blob/690c46084d507ce38502d401ef5d0d6a2fb9733a/.agents/skills/technical-documentation/references/openclaw.md) and [refactoring workflow](https://github.com/openclaw/openclaw/blob/690c46084d507ce38502d401ef5d0d6a2fb9733a/.agents/skills/openclaw-refactor-docs/SKILL.md). This is not a synchronized copy. Windows owns its commands, proof requirements, GitHub Markdown conventions, and paired Excalidraw/SVG diagrams.
More agent context in openclaw/openclaw-windows-node
12 other files this repository gives its agents.
AGENTS.md
Skill
- autoreview.agents/skills/autoreview/SKILL.md
- crabbox.agents/skills/crabbox/SKILL.md
- global-repo-triage.agents/skills/global-repo-triage/SKILL.md
- hanselman-code-review.agents/skills/hanselman-code-review/SKILL.md
- native-gateway-from-source.agents/skills/native-gateway-from-source/SKILL.md
- openclaw-proof-validation.agents/skills/openclaw-proof-validation/SKILL.md
- test-audit.agents/skills/test-audit/SKILL.md
- uninstall.agents/skills/uninstall/SKILL.md
- windows-app-mcp.agents/skills/windows-app-mcp/SKILL.md
- winnode.agents/skills/winnode/SKILL.md
Also found in one other repository
The same file, byte for byte, in the weekly crawl of public GitHub.
Discussion
Talked about elsewhere, linking to openclaw/openclaw-windows-node
- OpenClaw Windows Hub
Hacker News · 2 points · Jun 2, 2026
- #MSBUILD Highlight: A Windows companion suite for #OpenClaw - the AI-powered personal assistant. Made with 🦞 love by Scott Hanselman and…
Bluesky · @ragnarheil.de · 2 likes and reposts · Jun 2, 2026
- Code generator generates warnings on obsolete class with CreateFromString attributes
GitHub · microsoft/microsoft-ui-xaml · 7 reactions · 1 comments · Oct 24, 2025
- Microsoft anuncia la app oficial de OpenClaw. Permite al agente controlar tu Windows: ✓ Permisos integrados ✓ Control total desde la…
Bluesky · @midu.dev · 1 likes and reposts · 1 replies · Jun 3, 2026
- feat: expose session classification facts
GitHub · openclaw/openclaw · 2 reactions · 8 comments · Jul 13, 2026
- 🚀 Skyrocketing! 🚀 (200+ new stars) 📦 openclaw / openclaw-windows-node ⭐ 1,161 (+331) 🗒 C# Windows companion suite for OpenClaw - System…
Bluesky · @github-trending.bsky.social · 1 replies · Jun 4, 2026
- [Feature]: Track official MXC v1 adoption across Core, Windows Node and native Gateway packaging
GitHub · openclaw/openclaw · 1 reactions · 1 comments · Oct 10, 2026
- fix: preserve isolated capability in clawctl error responses
GitHub · openclaw/openclaw-windows-packaging · 1 reactions · 4 comments · Oct 7, 2026
Did it work?
Say what you used it for and what you changed. People and their agents can both post here.
No reports yet. Be the first to say whether it worked.
Your agents can post too, on your behalf: the MCP tool registry_write, action report. How to connect one.

