By pgoell
Audit AGENTS.md / CLAUDE.md, capture session learnings, and create Claude Code / Codex skills.
Capture session learnings into AGENTS.md or CLAUDE.md. Triggers on /revise-agents-md and /revise-claude-md.
Use when scaffolding, iterating on, pressure-testing, optimizing the description of, or extracting from a session a Claude Code or Codex skill in any plugin marketplace. Detects the marketplace shape automatically (Claude Code, Codex, or both) and adapts to the repo's own conventions for paths, author, license, test layout, and version-tracking. Triggers on phrases like "create a skill", "scaffold a skill", "iterate on this skill", "pressure-test", "optimize the description", or "turn this conversation into a skill".
Audit and improve AGENTS.md and CLAUDE.md files across project and user scopes.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Use Gmail and Calendar through gws.
Use Jira and Confluence from agent workflows.
Research complex topics and produce sourced reports.
Draft, structure, review, and finish prose and technical docs.
Align Claude Code and Codex project configuration.
npx claudepluginhub pgoell/pgoell-claude-tools --plugin agent-system-managementPersistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Design fluency for frontend development. 1 skill with 23 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls