By mizzy
Orchestrate a disciplined, AI-assisted development workflow from design to deployment: automate planning, TDD implementation, systematic debugging, self-review, verification, and PR merging using GitHub and integrated AI (Codex, Opus).
Use when starting new feature work, adding functionality, or modifying behavior - explores design before implementation, creates plan, PR, and GitHub Issues
Use to delegate all hands-on work to Codex - plan-writing, implementation, and refactoring. Opus reads, thinks, reviews, and writes docs only.
Use when encountering test failures, bugs, or unexpected behavior - requires root cause investigation before any fix attempt
Use when you want to be exhaustively questioned about a plan or design until shared understanding is reached - asks one question at a time, traverses the design tree, and proposes a recommended answer for each question
Use after a PR is opened and you want it merged - waits for CI to pass, marks draft PRs ready, removes the worktree, then merges and cleans up
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 Claude Code skills for a design-first, TDD-driven development workflow: brainstorming, planning, TDD, debugging, verification, review, merge, and Codex integration.
| Skill | Description |
|---|---|
brainstorming | Explore design before implementation; produces a design doc, plan, Draft PR, and GitHub Issues. |
grill-me | Exhaustively question a plan or design one question at a time, traversing the design tree with a recommended answer for each. |
plan | Decompose specs/design docs into bite-sized TDD tasks with file paths and examples. |
pick-issue | Pick a GitHub Issue, create a worktree, implement with TDD, verify, review 5x, and open a PR. |
tdd | Enforce Red-Green-Refactor — no production code without a failing test first. |
debugging | Systematic root-cause investigation before any fix attempt. |
verify | Require evidence (commands + output) before claiming work is complete. |
review | Run 5 rounds of self-review against the plan/spec, fixing issues each round. |
merge-when-ready | Wait for CI to pass, mark draft PRs ready, remove the worktree, then merge and clean up. |
codex | Delegate all hands-on work (plan-writing, implementation, refactoring) to Codex. |
These skills are distributed as a Claude Code plugin via a marketplace.
Add this repository as a marketplace:
/plugin marketplace add mizzy/my-skills
Install the plugin:
/plugin install my-skills
Once installed, the skills become available in Claude Code. Invoke a skill with
its slash command (e.g. /brainstorming, /pick-issue), or let Claude pick one
automatically based on the task.
After changing any skill's content:
Bump version in .claude-plugin/plugin.json.
Commit and push.
Refresh the marketplace cache:
/plugin marketplace update my-skills
Update the plugin:
/plugin update
/plugin update detects the version change and updates the plugin. If the
marketplace cache is stale, the version bump won't be picked up — always run
marketplace update before plugin update.
npx claudepluginhub mizzy/my-skills --plugin my-skillsReliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Core 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
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