Skip to content
cccskills
FreePublished on GitHub

technical-documentation

Write, review, or restructure Windows node documentation and agent instructions using current source, task-focused explanations, and explicit fact preservation.

The English summary is being prepared. Showing the original description.

See how to install

Files included (2)

  • SKILL.md3.4 KB
  • references/refactoring.md1.9 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

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, then the target page and the source that owns its claims. Do not preload the entire docs collection.

PageFirst useful result
OverviewThe reader chooses the appropriate guide
GuideOne recommended workflow reaches an observable outcome
ReferenceA precise contract answers a specific lookup
TroubleshootingA symptom leads to a check, interpretation, and next action
Agent instructionA 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. 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:

.\scripts\validate-docs.ps1
.\scripts\validate-agent-skills.ps1
git diff --check

Use test selection 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 and refactoring workflow. This is not a synchronized copy. Windows owns its commands, proof requirements, GitHub Markdown conventions, and paired Excalidraw/SVG diagrams.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Structured code review through the shared OpenClaw agent-skills installation.

The English summary is being prepared. Showing the original description.

openclaw/openclaw-windows-node2.2KUpdated Oct 19, 2026

Use Crabbox from macOS, Linux, or native Windows controllers to run OpenClaw Windows node builds, tests, and targeted proof on remote native Windows or WSL2 hosts, including Azure or brokered AWS leases and static SSH hosts. Use when remote Windows validation is needed or the user asks for Crabbox validation. Always report the actual provider, lease id, run URL, command, and result.

The English summary is being prepared. Showing the original description.

openclaw/openclaw-windows-node2.2KUpdated Oct 19, 2026

Run complete OpenClaw Windows Node issue and PR triage, including landing queues, proof pools, ownership audits, and release planning.

The English summary is being prepared. Showing the original description.

openclaw/openclaw-windows-node2.2KUpdated Oct 19, 2026

Adversarial dual-model code review that runs two AI models in parallel, cross-references findings, and produces a consensus severity table with fix confidence ratings. Use when asked for a thorough code review, adversarial review, dual-model review, confidence-rated review, or 'Hanselman review'.

The English summary is being prepared. Showing the original description.

openclaw/openclaw-windows-node2.2KUpdated Oct 19, 2026

Build the native MSIX isolated-session Gateway from npm latest, a published packaging release with -GatewayChannel Packaged, or explicit openclaw sources. Register it beside the Store Gateway and run Companion with OPENCLAW_NATIVE_GATEWAY_DEV_PATCH. Use for native Gateway development, release-channel compatibility, unreleased source changes, or removing a development Gateway.

The English summary is being prepared. Showing the original description.

openclaw/openclaw-windows-node2.2KUpdated Oct 19, 2026

Plan and collect OpenClaw Windows validation/proof: tests, rubber-duck review, UI evidence, MCP output, and gateway runtime proof.

The English summary is being prepared. Showing the original description.

openclaw/openclaw-windows-node2.2KUpdated Oct 19, 2026

See all skills by openclaw

Report a problem with this skill