Personal Claude Code skills: code review, debugging, project management, design tools
Review changed code for reuse, quality, and efficiency, then fix any issues found. Use when the user wants to clean up, simplify, or review recently changed code. Launches three parallel review agents (code reuse, code quality, efficiency) and aggregates findings.
Use when the user explicitly invokes /clear-issues or says "clear the backlog". Orchestrates the full issue lifecycle from investigation through close. Explicitly invoked only — not triggered by general conversation about issues.
Reviews code changes using CodeRabbit AI. Use when user asks for code review, PR feedback, code quality checks, security issues, or wants autonomous fix-review cycles.
Use when the user wants their idea, plan, or decision rigorously challenged — not just explained. Trigger on "grill me", "challenge me on this", "push back on my idea", "stress test my thinking", or any engineering plan presented with overconfident framing that the user wants questioned. This skill asks one focused question at a time with a recommended answer, working through a decision tree of assumptions. Use it whenever someone wants to be challenged, not just informed.
Use when delivering a single PR-scoped feature end-to-end with multi-critic review loops. Triggers on "/shipit", "ship this feature", or any request for full-cycle feature delivery from design through ship-ready PR with structured critique.
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.
Personal skills collection for AI coding agents. Built for Claude Code, also compatible with OpenCode, Codex, and others.
All agents (recommended):
npx skills add AmosChenZixuan/Agentic-working-contract -g -y
Bare skill names (/shipit), works cross-platform, tracks updates via npx skills update.
Claude Code only (marketplace):
claude plugin marketplace add AmosChenZixuan/Agentic-working-contract
claude plugin install awc
Note: marketplace adds a /awc: prefix to skill names.
Manual (any agent):
git clone https://github.com/AmosChenZixuan/Agentic-working-contract /tmp/awc
cp -r /tmp/awc/skills/* ~/.agent/skills/
After install, tell your agent:
read https://github.com/AmosChenZixuan/Agentic-working-contract/blob/main/README.md and install the third-party skills
You just installed a set of slash-command skills. Now do the following:
Confirm local skills are available. Run /shipit --help or equivalent.
Check what's already installed. Run npx skills ls and npx skills ls -g, scan both .agent/skills/ and ~/.agent/skills/. Remove any already-installed skills from the checklist below — don't ask the human about things they already have.
Present an interactive checklist (max 4 options per question — split into more questions if needed).
Use your platform's Q&A tool: Claude Code → AskUserQuestion (multiSelect: true), OpenCode → question, Hermes → clarify.
If no Q&A tool, post as markdown and ask the human to reply.
For each skill the human picks, determine install scope:
claude plugin install for Claude Code, npx skills add -a cursor for Cursor).
If native path unavailable, ask: "install globally (all projects) or per-project (this directory only)?"npx skills add or file copy.
Ask the human: "install globally (-g, all projects) or per-project (current directory only)?"Question 1 — Workflow & output:
Question 2 — Cleanup & style:
Install only the skills the human picked, using the scope they chose.
Tell the human how to update:
npx skills ls (per-project) / npx skills ls -g (global) to check; npx skills update to update allclaude plugin install): use that agent's native update mechanism — run claude plugin update, check the upstream guide, or re-run the install commandAll invoked as slash commands. Skills are auto-discovered from the skills/ directory.
| Skill | What it does |
|---|---|
/shipit | Full-cycle PR delivery — main agent owns design + AC + planning + arbitration; spawns Smith (white-box implementer), Scout (black-box AC verifier), and Hawk (white-box reviewer) in a bounded critique loop on a worktree or feature branch; output is a ship-ready PR (never auto-merged) |
/grill-me | Challenge your idea with design-decision questions |
/to-issues | Convert specs or findings into agent-ready GitHub issues |
/clear-issues | Autonomous issue lifecycle: investigate → implement → review → merge |
/c-simplify | Review changed code for reuse, quality, efficiency; fix issues |
/coderabbit-review | Run CodeRabbit AI review from the terminal |
Two orthogonal axes: how the work is partitioned (context-boundary vs task-boundary) and where intermediate state lives (local files vs issue tracker).
npx claudepluginhub amoschenzixuan/agentic-working-contract --plugin awcCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,561 supported skills.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer