By peterpme
Manage codebase quality through pattern enforcement, guided React/React Native refactors, multi-agent task coordination, PR review summaries, and interactive codebase exploration.
Component and data architecture workflow for focused React and React Native refactors. Use when the user asks to refactor a specific screen, component, feature, or PR and wants the agent to review first, ask architecture questions, sketch data flow and component tree separately, reason about render triggers, and wait for approval before editing code.
Learn, record, audit, and apply codebase patterns consistently across a repository by comparing current code to canonical local examples and a repo-local pattern registry. Use when asked to preserve continuity, learn a pattern, check drift, fix inconsistent implementations, migrate code to a local convention, or produce a CI-friendly continuity report.
reusable engineering manager workflow for complex agentic or human-led engineering tasks that require coordinating specialists, auditing repositories, implementing changes, validating with project-native commands, opening pull requests, resolving review comments, and running an independent final audit. Use when the user asks an agent or engineering lead to coordinate multi-agent or multi-reviewer implementation, create a PR, install project rules or skills, perform large refactors, enforce validation gates, or manage a complex engineering issue from intake through merge readiness.
Summarize PRs merged in a GitHub repo over the last N hours (default 12), excluding ones you authored or have already touched, and rank what's worth reviewing. Use when user says "morning recap", "what did I miss", "what shipped overnight", or "what went on while I was sleeping".
Clone a GitHub repo and set up an interactive study session for reading and analyzing the codebase. Use when user says "study repo", "learn this repo", "analyze this codebase", or provides a GitHub URL they want to explore.
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.
My collection of agent skills (slash commands and behaviors) for Claude Code.
Install from this repo via the Claude Code plugin marketplace.
git clone [email protected]:peterpme/skills.git ~/projects/skills
bash ~/projects/skills/scripts/link-skills.sh
This symlinks every SKILL.md-bearing directory under skills/ (excluding deprecated/) into ~/.claude/skills/.
Skills for daily code work.
General workflow tools, not code-specific.
Tools kept around but rarely used.
(none yet)
skills/
├── engineering/ # daily code work (shippable)
├── productivity/ # daily non-code (shippable)
├── misc/ # rare-use tools (shippable)
├── personal/ # tied to my own setup (not promoted)
├── in-progress/ # drafts (not promoted)
└── deprecated/ # no longer used (not linked)
Skills in engineering/, productivity/, and misc/ are listed in this README and in .claude-plugin/plugin.json. The other buckets are not.
npx claudepluginhub peterpme/skillsPersonal development best practices skills for React, Effect-TS, and other frameworks. Enforces patterns, anti-patterns, and code quality guidelines.
General purpose Claude Code toolkit with research agents, skills, and introspection commands
Utharn Buranasaksee's agent skills for real engineering — grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.
Refactor and simplify code for clarity and maintainability. Helps AI agents reduce code complexity, improve readability, and optimize code structure.
Git and PR workflows with code review, onboarding, and PR enhancement
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.