mirror of
https://github.com/duthaho/claudekit.git
synced 2026-06-11 20:54:56 +03:00
feat: 6-phase workflow spine + plan-review pipeline (v3.1.0)
This commit is contained in:
duthaho
@@ -1,114 +1,138 @@
|
||||
---
|
||||
title: Skills Reference
|
||||
description: All 44 skills in Claude Kit, organized by category.
|
||||
description: All 35 skills in Claude Kit, organized around the 6-phase development workflow.
|
||||
---
|
||||
|
||||
# Skills Reference
|
||||
|
||||
Skills are knowledge modules that auto-trigger based on keywords in your conversation. No commands needed — Claude activates the right skills based on what you're doing.
|
||||
Claude Kit is organized around a **6-phase development workflow**. 13 spine skills are user-invocable — typed directly as `/claudekit:<name>` — and 22 supporting skills auto-trigger by context behind the scenes.
|
||||
|
||||
## How Skills Work
|
||||
|
||||
Each skill has a trigger description with keywords. When you say something that matches, the skill loads automatically:
|
||||
Skills have trigger descriptions with keywords. When your conversation matches, the skill loads automatically:
|
||||
|
||||
```
|
||||
"fix this bug" → systematic-debugging, root-cause-tracing
|
||||
"plan the feature" → brainstorming, writing-plans
|
||||
"review the code" → requesting-code-review
|
||||
"review my plan" → plan-ceo-review, plan-eng-review
|
||||
"switch to brainstorm" → mode-switching, brainstorming
|
||||
```
|
||||
|
||||
Skills are bundled with the plugin and auto-trigger when installed. You can also create project-level skills in `.claude/skills/`.
|
||||
You can also invoke spine skills directly by typing `/claudekit:<name>`. Project-level skills go in `.claude/skills/`.
|
||||
|
||||
---
|
||||
|
||||
## Development
|
||||
## 🧠 Think
|
||||
|
||||
Skills for languages, frameworks, and application patterns.
|
||||
Explore ideas, refine requirements, produce a spec.
|
||||
|
||||
| Skill | Description | Triggers On |
|
||||
|-------|-------------|-------------|
|
||||
| **languages** | Python, TypeScript, JavaScript idioms — type hints, generics, async/await, Pydantic, Zod | Language-specific code patterns |
|
||||
| **frontend** | React components, Next.js App Router, SSR/SSG, shadcn/ui, hooks | React, Next.js, component work |
|
||||
| **frontend-styling** | Tailwind CSS, WCAG accessibility, ARIA, dark mode, responsive | Styling, accessibility |
|
||||
| **backend-frameworks** | FastAPI, Django, NestJS, Express — routing, middleware, DI | API endpoints, server code |
|
||||
| **databases** | PostgreSQL, MongoDB, Redis — schema, queries, indexing, migrations | Database operations |
|
||||
| **state-management** | useState, Zustand, Jotai, TanStack Query, server/form/URL state | State architecture |
|
||||
| **api-client** | axios, fetch, httpx — interceptors, retry logic, type-safe clients | HTTP requests, API integration |
|
||||
| **openapi** | OpenAPI 3.1 design, error contracts, pagination, code-gen | API specification |
|
||||
| **brainstorming** | Interactive design — one question at a time. Includes Startup Mode (6 forcing questions) for new product ideas | "brainstorm", "design", "explore", "is this worth building" |
|
||||
| **writing-plans** | Break a spec into bite-sized tasks with exact code, file paths, and verification commands | "plan", "break down", "task list", "implementation steps" |
|
||||
|
||||
## Infrastructure
|
||||
## 🔍 Review
|
||||
|
||||
Skills for deployment, caching, logging, and operational concerns.
|
||||
Pressure-test a written plan before coding. Each dimension scores 0-10 with a one-sentence rationale and concrete fixes. Selected fixes are written directly into the plan file.
|
||||
|
||||
| Skill | Dimensions scored | When to invoke |
|
||||
|-------|------------------|----------------|
|
||||
| **autoplan** | All 4 below, parallel fan-out, single consolidated fix gate | Full gauntlet before handoff — "autoplan", "auto review", "run all reviews" |
|
||||
| **plan-ceo-review** | Ambition, problem clarity, wedge focus, demand reality, future-fit | Scope / strategy pressure-test — "think bigger", "scope review" |
|
||||
| **plan-eng-review** | Data flow, failure modes, edge cases, test matrix, rollback | Architecture audit — "does this design make sense", "lock in the plan" |
|
||||
| **plan-design-review** | Hierarchy, visual consistency, state coverage, accessibility, AI-slop avoidance | Plans with UI surfaces — "design critique", "avoid AI slop" |
|
||||
| **plan-devex-review** | Time to Hello World, ergonomics, error copy, docs structure, magical moments | Plans shipping APIs / CLIs / SDKs — "DX review", "is this SDK ergonomic" |
|
||||
|
||||
## 🔨 Build
|
||||
|
||||
Implement with discipline — TDD, systematic debugging, and verification gates.
|
||||
|
||||
| Skill | Description | Triggers On |
|
||||
|-------|-------------|-------------|
|
||||
| **devops** | Docker, GitHub Actions, Cloudflare Workers, multi-stage builds | Containers, CI/CD, deployment |
|
||||
| **caching** | Redis, memoization, HTTP cache headers, CDN, TTL policies | Cache strategy |
|
||||
| **logging** | Logger setup, log levels, correlation IDs, sensitive data redaction | Logging, observability |
|
||||
| **error-handling** | Try/catch, custom errors, retry logic, React error boundaries | Exception handling |
|
||||
| **background-jobs** | Celery, BullMQ, task queues, cron jobs, async processing | Background tasks, workers |
|
||||
| **authentication** | JWT, OAuth2, sessions, RBAC, password hashing, MFA | Login, auth, permissions |
|
||||
| **performance-optimization** | Profiling, N+1 queries, bundle size, memory leaks, benchmarks | "slow", "optimize", "profiling" |
|
||||
| **feature-workflow** | End-to-end orchestrator: requirements → plan → review → implement → test → review | "feature", "implement end-to-end" |
|
||||
| **test-driven-development** | Strict red-green-refactor — no production code without a failing test first | "implement", "add feature", "fix bug", "build" |
|
||||
| **systematic-debugging** | 4-phase investigation: observe, hypothesize, test, prove | "bug", "error", "broken", stack traces |
|
||||
| **verification-before-completion** | Mandatory evidence before any completion claim | "done", "fixed", "tests pass" |
|
||||
|
||||
## Quality
|
||||
|
||||
Skills for testing, security, and code verification.
|
||||
## 🎛️ Session
|
||||
|
||||
| Skill | Description | Triggers On |
|
||||
|-------|-------------|-------------|
|
||||
| **testing** | pytest, Vitest, Jest — fixtures, mocking, coverage, config | Writing/debugging tests |
|
||||
| **test-driven-development** | Strict red-green-refactor — no production code without failing test | "implement", "add feature", "build" |
|
||||
| **testing-anti-patterns** | Detecting unreliable tests, heavy mocking, false positives | "flaky test", "mock", test review |
|
||||
| **playwright** | E2E tests, page objects, visual regression, cross-browser | End-to-end testing |
|
||||
| **owasp** | OWASP Top 10, XSS, SQL injection, CSRF, dependency scanning | Security review, user input |
|
||||
| **defense-in-depth** | Multi-layer validation, preventing single-point bypass | Data integrity bugs |
|
||||
| **verification-before-completion** | Mandatory evidence before completion claims | "done", "fixed", "tests pass" |
|
||||
| **mode-switching** | Switch behavioral modes (brainstorm, token-efficient, deep-research, implementation, review) | "mode", "switch to brainstorm" |
|
||||
|
||||
## Debugging
|
||||
|
||||
Skills for investigating and resolving issues.
|
||||
## ⚙️ Setup
|
||||
|
||||
| Skill | Description | Triggers On |
|
||||
|-------|-------------|-------------|
|
||||
| **systematic-debugging** | Four-phase investigation: observe, hypothesize, test, fix | "bug", "error", "broken", stack traces |
|
||||
| **root-cause-tracing** | Tracing bugs that manifest far from their origin | Deep bugs, data corruption |
|
||||
| **sequential-thinking** | Step-by-step reasoning with confidence tracking | Complex decisions, analysis |
|
||||
| **condition-based-waiting** | Polling CI pipelines, deployments, long-running processes | "wait for", "check status" |
|
||||
| **init** | Interactive setup wizard — scaffolds rules, modes, hooks, MCP configs into your project | `/claudekit:init` (user-invocable) |
|
||||
|
||||
## Workflow
|
||||
---
|
||||
|
||||
Skills for development process and session management.
|
||||
## Supporting Skills (auto-trigger, non-user-invocable)
|
||||
|
||||
| Skill | Description | Triggers On |
|
||||
|-------|-------------|-------------|
|
||||
| **feature-workflow** | End-to-end: requirements → planning → implementation → review | "feature", "implement end-to-end" |
|
||||
| **brainstorming** | Interactive design with one question at a time | "brainstorm", "design", "explore" |
|
||||
| **writing-plans** | Detailed task breakdown with exact code and file paths | "plan", "break down", "task list" |
|
||||
| **executing-plans** | Subagent-driven execution with review gates | "execute the plan", "run the plan" |
|
||||
| **git-workflows** | Conventional commits, PRs, changelogs, release notes | "commit", "PR", "ship", "changelog" |
|
||||
| **documentation** | Docstrings, JSDoc, README, API docs, tech specs | "document", "docstring", "README" |
|
||||
| **refactoring** | Improving code structure without behavior change | "refactor", "clean up", "simplify" |
|
||||
| **mode-switching** | Switching behavioral modes for the session | "mode", "switch to brainstorm" |
|
||||
| **session-management** | Checkpoints, project indexing, context loading | "checkpoint", "index", "status" |
|
||||
| **writing-concisely** | Token optimization, compressed output, 30-70% savings | "be concise", "code only" |
|
||||
These 22 skills activate silently when Claude detects a matching context. You don't invoke them directly — they shape how Claude works within the spine phases above.
|
||||
|
||||
## Collaboration
|
||||
### Execution & Parallelism
|
||||
|
||||
Skills for multi-agent workflows and team processes.
|
||||
| Skill | Triggers On |
|
||||
|-------|-------------|
|
||||
| **executing-plans** | "execute the plan", "run the plan" |
|
||||
| **subagent-driven-development** | "use subagents", "dispatch agents", parallel task execution |
|
||||
| **using-git-worktrees** | "worktree", "isolated branch", parallel development |
|
||||
| **finishing-a-development-branch** | "ship it", "ready to merge", "branch is done" |
|
||||
| **dispatching-parallel-agents** | 3+ independent failures or tasks |
|
||||
| **condition-based-waiting** | "wait for", "check status", polling CI pipelines |
|
||||
|
||||
| Skill | Description | Triggers On |
|
||||
|-------|-------------|-------------|
|
||||
| **dispatching-parallel-agents** | Launching parallel agents for independent tasks | 3+ independent failures/tasks |
|
||||
| **subagent-driven-development** | Parallel task execution via Agent tool | "use subagents", "dispatch agents" |
|
||||
| **using-git-worktrees** | Isolated branch work, parallel development | "worktree", "isolated branch" |
|
||||
| **requesting-code-review** | Preparing code for review with clear context | Before PRs, before merging |
|
||||
| **receiving-code-review** | Processing review feedback systematically | Review comments, PR feedback |
|
||||
| **finishing-a-development-branch** | Branch completion: verify, review, merge/PR options | "ship it", "ready to merge" |
|
||||
| **writing-skills** | Creating and editing skills for this kit | "create a skill", "new skill" |
|
||||
### Testing Discipline
|
||||
|
||||
## Setup
|
||||
| Skill | Triggers On |
|
||||
|-------|-------------|
|
||||
| **testing** | pytest, Vitest, Jest — fixtures, mocking, coverage config |
|
||||
| **playwright** | E2E tests, page objects, visual regression |
|
||||
| **testing-anti-patterns** | "flaky test", "mock", test review — catches unreliable tests |
|
||||
|
||||
| Skill | Description | Triggers On |
|
||||
|-------|-------------|-------------|
|
||||
| **init** | Interactive setup wizard — scaffolds rules, modes, hooks, MCP configs | `/claudekit:init` (user-invocable) |
|
||||
### Debug Techniques
|
||||
|
||||
| Skill | Triggers On |
|
||||
|-------|-------------|
|
||||
| **root-cause-tracing** | Deep bugs where error location differs from bug origin |
|
||||
| **defense-in-depth** | Data integrity bugs, single-point bypass scenarios |
|
||||
|
||||
### Review Etiquette
|
||||
|
||||
| Skill | Triggers On |
|
||||
|-------|-------------|
|
||||
| **requesting-code-review** | Before PRs, before merging |
|
||||
| **receiving-code-review** | Review comments, PR feedback |
|
||||
|
||||
### Reasoning & Meta
|
||||
|
||||
| Skill | Triggers On |
|
||||
|-------|-------------|
|
||||
| **sequential-thinking** | Complex decisions needing step-by-step reasoning |
|
||||
| **writing-concisely** | "be concise", "code only" — 30-70% token savings |
|
||||
| **writing-skills** | "create a skill", "new skill" |
|
||||
| **refactoring** | "refactor", "clean up", "simplify" |
|
||||
|
||||
### Operations
|
||||
|
||||
| Skill | Triggers On |
|
||||
|-------|-------------|
|
||||
| **devops** | Docker, GitHub Actions, Cloudflare Workers — CI/CD, deployment |
|
||||
| **git-workflows** | "commit", "PR", "ship", "changelog" |
|
||||
| **performance-optimization** | "slow", "optimize", "profiling", N+1 queries, bundle size |
|
||||
| **session-management** | "checkpoint", "index", "status", context loading |
|
||||
|
||||
### Security
|
||||
|
||||
| Skill | Triggers On |
|
||||
|-------|-------------|
|
||||
| **owasp** | Security review, user input, authentication, CORS, CSP |
|
||||
|
||||
---
|
||||
|
||||
## Counts
|
||||
|
||||
- **Total:** 35 skills
|
||||
- **Spine (user-invocable):** 13 — brainstorming, writing-plans, autoplan, plan-ceo-review, plan-eng-review, plan-design-review, plan-devex-review, feature-workflow, test-driven-development, systematic-debugging, verification-before-completion, mode-switching, init
|
||||
- **Supporting (auto-trigger only):** 22
|
||||
|
||||
Reference in New Issue
Block a user