Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
skill-claw
OpenClaw instance administration — manage hosts across macOS, Ubuntu/Debian, Docker, OCI, and Proxmox. Use when: AUTOMATICALLY ACTIVATE when user asks about:. "manage openclaw" or "openclaw status" or "openclaw health". "update openclaw" or "upgrade openclaw" or "openclaw doctor"
nyldn/claude-octopus 2,561
-
skill-coverage-audit
Trace codepaths in diffs, map against tests, auto-generate missing coverage. Use when: AUTOMATICALLY ACTIVATE when user requests coverage analysis:. "check test coverage" or "coverage audit". "what's not tested" or "find untested code"
nyldn/claude-octopus 2,561
-
skill-tdd
Build features with tests-before-code rigor — use for new features needing test coverage. Use when: Use when implementing any feature, bugfix, or behavior change.. Auto-invoke when user says "implement X", "add feature Y", "fix bug Z".
nyldn/claude-octopus 2,561
-
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX office documents. Use when: AUTOMATICALLY ACTIVATE when user requests:. Export knowledge work to office formats (e.g., "export to Word", "create PowerPoint", "convert to DOCX"). Generate professional documents from research (e.g., "create presentation from this synthesis")
nyldn/claude-octopus 2,561
-
skill-prd
AI-optimized PRD creation with 100-point scoring framework
nyldn/claude-octopus 2,561
-
skill-finish-branch
Wrap up a branch — run tests, create PR, merge or discard — use when implementation is done. Use when: AUTOMATICALLY ACTIVATE when user requests task completion with git operations:. "commit and push" or "git commit and push". "complete all tasks and commit and push"
nyldn/claude-octopus 2,561
-
octopus-architecture
System architecture and API design with multi-AI consensus
nyldn/claude-octopus 2,561
-
sys-configure
Configure Claude Octopus providers and preferences. Use when: Use this skill when the user wants to "configure Claude Octopus", "setup octopus",. "configure providers", "set up API keys for octopus", or mentions octopus configuration.
nyldn/claude-octopus 2,561
-
skill-scope-drift
Scope drift detection — compares actual diff against stated intent to catch scope creep and missing requirements. Informational only, never blocks.
nyldn/claude-octopus 2,561
-
skill-knowledge-work
Switch to Knowledge Work mode for research and writing — use when task is non-code focused
nyldn/claude-octopus 2,561
-
skill-rollback
Roll back to a previous checkpoint via git — use when a change went wrong and you need to revert. Use when: AUTOMATICALLY ACTIVATE when user mentions:. "rollback" or "revert" or "undo". "go back to" or "restore checkpoint"
nyldn/claude-octopus 2,561
-
skill-debug
Debug issues methodically — use when stuck on errors, test failures, or unexpected behavior. Use when: AUTOMATICALLY ACTIVATE when encountering bugs or failures:. "fix this bug" or "debug Y" or "troubleshoot X". "why is X failing" or "why isn't X working" or "why doesn't X work"
nyldn/claude-octopus 2,561
-
skill-content-pipeline
Extract patterns and anatomy from URLs — use to reverse-engineer content strategies from live pages. Use when: Use PROACTIVELY when user wants to:. "analyze this article", "analyze this content". "deconstruct this content", "break down this post"
nyldn/claude-octopus 2,561
-
skill-cost-projections
Project remaining workflow cost from per-phase averages — warns on budget ceiling overruns. Use when: AUTOMATICALLY ACTIVATE when user asks about workflow costs:. "cost projection", "estimate remaining cost". "budget forecast", "how much will this cost"
nyldn/claude-octopus 2,561
-
skill-security-framing
URL validation and content wrapping for untrusted sources. Use when: This skill provides SECURITY UTILITIES - it should be referenced by other skills,. not invoked directly by users. Auto-integrate when:. Fetching content from URLs
nyldn/claude-octopus 2,561
-
flow-discover
Multi-AI research using Codex and Gemini CLIs (Double Diamond Discover phase). Use when: AUTOMATICALLY ACTIVATE when user requests research or exploration:. "research X" or "explore Y" or "investigate Z". "what are the options for X" or "what are my choices for Y"
nyldn/claude-octopus 2,561
-
skill-task-management
Manage tasks with Claude Code native tools — use to track TODOs, delegate work, and monitor progress. Use when: AUTOMATICALLY ACTIVATE when user requests task management:. "add to the todo's" or "add this to todos". "resume tasks" or "continue tasks" or "pick up where we left off"
nyldn/claude-octopus 2,561
-
skill-resume
Pick up where you left off from a previous session — use after context resets, compaction, or new conversations. Use when: AUTOMATICALLY ACTIVATE when user mentions:. "resume" or "continue" or "pick up where I left off". "what was I doing" or "restore session"
nyldn/claude-octopus 2,561
-
flow-develop
Multi-AI implementation using Codex and Gemini CLIs (Double Diamond Develop phase). Use when: AUTOMATICALLY ACTIVATE when user requests building or implementation:. "build X" or "implement Y" or "create Z". "develop a feature for X"
nyldn/claude-octopus 2,561
-
skill-writing-plans
Zero-context implementation plans with bite-sized tasks. Use when: Use when you have a spec or requirements for a multi-step task.. Auto-invoke when user says "plan how to implement X", "create implementation plan", . "break down this feature into tasks".
nyldn/claude-octopus 2,561
-
skill-intent-contract
Lock in user goals upfront and validate outputs against them — use to prevent scope drift
nyldn/claude-octopus 2,561
-
flow-deliver
Multi-AI validation, scoring, and review using Codex and Gemini CLIs (Double Diamond Deliver phase). Use when: AUTOMATICALLY ACTIVATE when user requests validation, scoring, or review:. "review X" or "validate Y" or "test Z". "score this", "quality check", "validate before shipping"
nyldn/claude-octopus 2,561
-
skill-verify
Verify claims with actual evidence before declaring success — use to prevent false completion. Use when: Use when about to claim work is complete, fixed, or passing.. Auto-invoke before: commits, PRs, task completion, moving to next task.. ALWAYS use before expressing satisfaction ("Done!", "Fixed!", "All passing!").
nyldn/claude-octopus 2,561
-
skill-debate
Structured four-way AI debates between Claude, Sonnet, Gemini, and Codex. Use when: AUTOMATICALLY ACTIVATE when user says:. "/debate <question>". "run a debate about X"
nyldn/claude-octopus 2,561