Skills your agents can run

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".

Delegate coding tasks to Codex, Claude Code, or Pi agents via a background process. Use when: (1) building or creating new features or apps, (2) reviewing PRs (spawn in a temp dir), (3) refactoring large codebases, (4) iterative coding that requires file exploration. NOT for: simple one-liner fixes (just edit), passive code reading (use the read tool), thread-bound ACP harness requests in chat (for example, spawning/running Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work inside the ~/clawd workspace (never spawn agents there). Claude Code: invoke with --print --permission-mode bypassPermissions (avoid PTY). Codex/Pi/OpenCode: pty:true required.

Code review practices with technical rigor and verification gates. Use for receiving feedback, requesting code-reviewer subagent reviews, or preventing false completion claims in pull requests.

Master Python 3.12+ with modern features, async programming, performance optimization, and production-ready practices. Expert in the latest Python ecosystem including uv, ruff, pydantic, and FastAPI.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Use OpenAI Codex from inside Claude Code for code reviews and delegated background tasks.

Troubleshoot Claude Code extensions and behavior. Triggers on: debug, troubleshoot, not working, skill not loading, hook not running, agent not found.

Two Codex MCP servers must be configured in the global `settings.json`:

Propose backend, frontend, and data design for a feature, aligned with existing patterns.

Every meaningful directory in a project should have a `.context.md` that orients whoever arrives next — human or agent.

Debugging Rust programs with GDB/LLDB, panic triage, tokio-console, tracing, and IDE integration. Use when diagnosing crashes, analyzing panics, setting up debug tooling, or introspecting async runtime behavior.

Turn raw diffs or PRs into structured summaries: modules changed, behavior, APIs, risks, and test impact.

Given a feature/task, assemble a concise, structured context: relevant code, docs, prior work, risks, and open questions.

Group and explain lint/TypeScript errors, suggesting minimal, safe fixes without masking issues.

Create, validate, and publish Claude Code plugins from forge modules. Use when creating or validating plugins, publishing to a marketplace, working with plugin.json, or managing Cowork plugins.

Perform a structured PR review with blocking issues, non-blocking suggestions, test gaps, and open questions.

Save your working state before a context window reset so you (or any agent) can resume cleanly with full understanding and zero wasted tokens.

Convert requirements and architecture into a concrete test plan that includes unit, integration, and end-to-end (E2E) test cases.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.