$ loading_
Create and review technical docs and agent instruction files in repositories.
This appears to be a prompt-only documentation skill with no required secrets, no declared remote endpoints, and no indicated local execution or standalone data exfiltration capability. Combined with its open-source GitHub origin and extremely high community adoption, the overall risk is low; the repo-audit/document-review workflow described is guidance rather than a request for extra system privileges.
The material explicitly states that no keys or environment variables are required. No API tokens, OAuth flows, cloud credentials, or other sensitive authentication requirements are described, so credential exposure and abuse risk appears low.
The material explicitly lists no remote host endpoints. As a prompt-only skill, it does not describe sending user content to third-party services, telemetry collection, or connections to unknown external destinations.
There is no description of spawning local processes, running scripts, installing dependencies, invoking a shell, or using system tools. The content is primarily a documentation build/review workflow and does not indicate code execution privileges.
The material mentions inventorying and reviewing repository docs such as README, docs, AGENTS.md, and CONTRIBUTING.md, but it does not claim direct read/write access to local files, databases, or other resources. Based on the available facts, this is documentation guidance rather than excessive access.
The source is an open-source GitHub repository with extremely high community adoption (about 377k stars), both strong risk-reducing signals. While the license is unspecified and maintenance status is unknown, that creates some governance uncertainty but not a high-risk red flag by itself.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "technical-documentation" skill from askskill: 1. Download https://raw.githubusercontent.com/openclaw/openclaw/main/.agents/skills/technical-documentation/SKILL.md 2. Save it as ~/.claude/skills/technical-documentation/SKILL.md 3. Reload skills and tell me it's ready
Based on the backend code structure in this repository, create API documentation including endpoint paths, HTTP methods, parameter descriptions, response examples, and common error codes, then output it in Markdown.
A well-structured Markdown API document for development and collaboration.
Review the README and docs directory in the repository, identify outdated content, inconsistent terminology, missing steps, or unclear wording, and provide replacement-ready revision suggestions.
A documentation review checklist with issue notes and actionable revisions.
Using the repository tech stack, folder structure, and development conventions, draft an instruction file for an AI coding assistant that defines code style, testing requirements, commit conventions, and prohibited actions.
A repository-ready draft agent instruction file that can be adopted directly.
Produce and review technical documentation that is clear, actionable, and maintainable for both humans and agents, including contributor-governance files and agent instruction files.
docs/, README*, .md/.mdx/.mdc, Fern/Sphinx/Mintlify-style sources).CLAUDE.md, AGENT.md, .cursorrules, .cursor/rules/*, .agent/, .agents/, .pi/) where AGENTS.md is treated as canonical when present and aliases should be kept as compatibility surfaces.build or review; context: brownfield or evergreen.references/agent-and-contributing.md for agent instruction and CONTRIBUTING.md workflow rules (inventory, canonical/alias mapping, dual-mode balance, deliverable standards, and precedence/conflict handling).references/principles.md for the governing ruleset (Matt Palmer & OpenAI).references/openclaw.md before the build/review playbook.references/build.md.references/review.md and proactively detect issues without waiting for repeated prompts.references/tooling.md when platform/tooling choices affect recommendations.Prefer sub-agents when the repo is large or the requested change set is broad; use them by default for repo-wide, multi-framework, or high-conflict work.
inventory-agent -> agents/inventory-agent.md (fast / Claude haiku): file/config discovery, coverage map, and missing-path checks.governance-agent -> agents/governance-agent.md (thinking / Claude sonnet): AGENTS/CONTRIBUTING/alias precedence, conflicts, and policy drift.docs-framework-agent -> agents/docs-framework-agent.md (thinking / Claude sonnet): framework config, relative path base, and file-path vs URL-path mapping checks.…
Generate concept, architecture, flow, and whiteboard diagrams in multiple formats.
Helps maintainers triage, clean up, and resolve OpenClaw secret scanning alerts.
Investigate test memory growth, heap leaks, and OOM root causes.
Discover and control Sonos speakers for playback, volume, status, and grouping.
Summarize CodexBar local cost logs by model for Codex or Claude.
Automate web page workflows, login checks, tab handling, and recovery steps.
Write and maintain technical docs, from READMEs to API and runbook guides.
Guide users to co-author docs, proposals, and specs through iterative refinement.
Keep repository docs, progress logs, and handoff context continuously updated.
Generate, search, and maintain codebase documentation for faster team development.
Access and understand Agent Skills specifications and documentation quickly.
Search project docs semantically to find relevant files before coding changes.