By drdanmaggs
General-purpose Claude Code skills and agents — TDD, code review, shipping, testing, docs, and project hygiene
Hunts for bugs and security vulnerabilities in code diffs. Used by the code-reviewer skill.
Reviews code diffs for semantic issues using full file context. Used by the code-reviewer skill.
Reviews code diffs for real performance problems. Used by the code-reviewer skill.
Reviews code diffs for code quality, maintainability, and clean code violations. Used by the code-reviewer skill.
Checks code diffs against CLAUDE.md project standards. Used by the code-reviewer skill.
Use this skill to review code. It supports both local changes (staged or working tree) and remote Pull Requests (by ID or URL). It focuses on correctness, maintainability, and adherence to project standards. Uses parallel review agents with a validation pass to deliver high-signal findings only.
Creates GitHub pull requests with properly formatted titles that pass the check-pr-title CI validation. Use when creating PRs, submitting changes for review, or when the user says /pr or asks to create a pull request.
Risk-driven testing — identify and test critical user paths first, coverage is an output not the goal
Use when building email features, emails going to spam, high bounce rates, setting up SPF/DKIM/DMARC authentication, implementing email capture, ensuring compliance (CAN-SPAM, GDPR, CASL), handling webhooks, retry logic, or deciding transactional vs marketing.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
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.
A Claude Code plugin: 22 general-purpose skills and 15 supporting agents for test-driven development, code review, shipping, and project hygiene.
These previously lived inside rocket-fuel, a
multi-agent orchestrator. They don't belong there — none of them know the orchestrator
exists, and bundling them meant a one-line fix to /ship required a version bump on an
unrelated Go project. See ADR-009 in that repo for the reasoning.
claude plugin marketplace add drdanmaggs/claude-skills
claude plugin install claude-skills
Invoke as /claude-skills:<name> — e.g. /claude-skills:tdd. Most skills also
auto-trigger on relevant phrasing.
| Skill | What it does |
|---|---|
tdd | RED/GREEN/REFACTOR with context-isolated subagents per phase |
ship | End-to-end pre-PR: commit, lint, review, fix, draft PR |
create-pr | PRs with titles that pass conventional-commit CI validation |
pr-quality | Autonomous loop — processes review feedback and CI until clean |
resolve-conflict | Rebases and resolves conflicts, stopping only when genuinely ambiguous |
git-workflow | Commit, branch and PR conventions |
| Skill | What it does |
|---|---|
code-reviewer | Parallel review agents plus a validation pass; high-signal findings only |
Backed by seven agents: code-reviewer-bug-hunter, -context-reviewer,
-performance-reviewer, -quality-reviewer, -standards-checker,
-test-coverage-reviewer, and -validator, which tries to disprove findings before they
are reported.
| Skill | What it does |
|---|---|
test-fixer | Diagnoses and fixes failures across Playwright, Vitest, Jest, RTL |
skip-failed-test | Decides whether a failure is yours or flaky; skips with a tracked issue |
critical-path-testing | Risk-driven — test critical paths first, coverage is an output |
test-coverage-retrofit | Coverage-driven parallel test writing for legacy code |
supabase-rls-testing | Vitest integration tests for Row Level Security policies |
| Skill | What it does |
|---|---|
issue-scope | Turns vague features into scoped plans with test decomposition |
issue-triage | Evaluates a backlog against the real codebase; drops what's stale |
github-issue-relationships | Blocked-by/blocking links and epic hierarchies |
write-concise-docs | Rewrites verbose docs into scannable, token-efficient form |
skill-creator | Guide for writing and updating skills |
| Skill | What it does |
|---|---|
frontend-design | Distinctive production-grade UI that avoids generic AI aesthetics |
vercel-react-best-practices | React/Next.js performance patterns from Vercel Engineering |
react-email | HTML email templates as React components |
resend | Sending, receiving, audiences, broadcasts |
email-best-practices | Deliverability, SPF/DKIM/DMARC, compliance |
Some skills are better taken from their vendor than vendored here. Install these with the Skills CLI instead — they are first-party and stay current on their own:
npx skills add vercel-labs/skills@find-skills # discovers and installs skills
npx skills add langfuse/skills@langfuse # LLM observability
npx skills add stripe/ai@stripe-best-practices # Stripe integration guidance
This plugin shipped its own find-skills and langfuse until they were removed in favour
of the upstream versions, which are maintained by the tools' own authors. A second copy
here would shadow whichever one you installed and then rot.
hooks/tdd-gate.sh is a PreToolUse gate that enforces TDD phase discipline. It reads a
.tdd-phase file at the repo root and blocks edits that violate the current phase:
| Phase | Tests | Source |
|---|---|---|
| RED | allow | deny |
| GREEN | deny | allow |
| REFACTOR | deny | allow |
It is completely invisible when no .tdd-phase file exists, so it never affects non-TDD
work. Run its 13-case offline test matrix with:
bash hooks/tdd-gate.test.sh
rules/ is not a plugin primitive. A rules/ directory in a plugin is copied into the
install cache and never loaded — nothing reads it. Rocket Fuel shipped eight rule files
that way for four months with no effect whatsoever.
Rules that actually load live in ~/.claude/rules/, referenced from ~/.claude/CLAUDE.md.
Put them there.
The failure mode is quiet: of the five files that existed in both places, four were
byte-identical and testing.md had drifted, with the better version — a section on tests
owning their own data rather than querying for pre-existing records — sitting in the copy
nothing read. It was ported across before the plugin copy was deleted.
npx claudepluginhub drdanmaggs/claude-skillsMulti-agent orchestrator for Claude Code — Integrator/Worker agents, board setup, and worktree management
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
v9.54.1 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development