@spardutti/claude-skills 1.19.0 → 1.19.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +130 -44
  2. package/package.json +5 -1
package/README.md CHANGED
@@ -1,67 +1,153 @@
1
- # @spardutti/claude-skills
1
+ # Claude Skills
2
2
 
3
- Interactive CLI to install reusable [Claude Code](https://docs.anthropic.com/en/docs/claude-code) skills into any project.
3
+ Personal collection of reusable Claude Code skills.
4
4
 
5
- ## Usage
5
+ ## Skills
6
6
 
7
- ```bash
8
- npx @spardutti/claude-skills
9
- ```
7
+ ### Frontend
10
8
 
11
- Run this from your project's root directory. The CLI will:
12
-
13
- 1. Fetch the latest skills from [GitHub](https://github.com/Spardutti/claude-skills)
14
- 2. Let you interactively select which skills to install
15
- 3. Copy them into your project's `.claude/skills/` directory
16
- 4. Ask to set up **automatic skill evaluation** (hook + CLAUDE.md rule)
9
+ | Skill | Description |
10
+ |-------|-------------|
11
+ | `react-best-practices` | React 19 component design, state management, performance, React 19 features, TypeScript integration |
12
+ | `react-use-effect` | React 19 useEffect best practices and anti-patterns |
13
+ | `react-query` | TanStack React Query with @lukemorales/query-key-factory patterns |
14
+ | `react-single-responsibility` | React single responsibility component splitting, hook isolation, file size limits, complexity rules |
15
+ | `tanstack-router-best-practices` | TanStack Router — file-based routing, type-safe navigation, loaders, search params, auth guards |
16
+ | `trpc-react-query` | tRPC v11 — queryOptions/mutationOptions patterns, router organization, middleware, cache invalidation, optimistic updates |
17
+ | `tailwind-tokens` | Enforce Tailwind CSS design tokens — no arbitrary values when a token exists |
18
+ | `zustand` | Zustand — store design, selectors, persist/immer middleware, slices pattern, devtools, transient updates |
19
+ | `dnd-kit` | @dnd-kit — sortable lists, sensors, collision detection, drag overlays, multi-container (kanban), accessibility |
20
+ | `framer-motion` | Motion (Framer Motion) — AnimatePresence, layout animations, variants, gestures, useAnimate, performance |
17
21
 
18
- ## Automatic Skill Evaluation
22
+ ### Desktop
19
23
 
20
- Skills alone don't guarantee Claude will use them. The CLI can optionally set up enforcement:
24
+ | Skill | Description |
25
+ |-------|-------------|
26
+ | `tauri-v2` | Tauri v2 — IPC commands, plugins, window management, system tray, global shortcuts, capabilities/permissions, events |
21
27
 
22
- - **Hook** (`.claude/hooks/skill-forced-eval-hook.sh`) — Runs on every prompt, injects a mandatory skill evaluation sequence into Claude's context
23
- - **CLAUDE.md rule** (`skill_evaluation` block) — Instructs Claude to list every skill as ACTIVATE/SKIP before writing any code
28
+ ### TypeScript
24
29
 
25
- Together, these force Claude to explicitly evaluate and activate relevant skills instead of silently ignoring them.
30
+ | Skill | Description |
31
+ |-------|-------------|
32
+ | `typescript-best-practices` | TypeScript 5.x — type design, type safety, generics, error handling, tsconfig |
26
33
 
27
- ## Available Skills
34
+ ### Backend
28
35
 
29
36
  | Skill | Description |
30
37
  |-------|-------------|
31
- | `react-best-practices` | React 19 — component design, state management, performance, React 19 features, TypeScript integration |
32
- | `react-use-effect` | React 19 useEffect best practices and anti-patterns |
33
- | `react-query` | TanStack React Query with query-key-factory patterns |
34
- | `tanstack-router-best-practices` | TanStack Router — file-based routing, type-safe navigation, loaders, search params, auth guards |
35
- | `typescript-best-practices` | TypeScript 5.x — type design, type safety, generics, error handling, tsconfig |
36
- | `react-single-responsibility` | React single responsibility — component splitting, hook isolation, file size limits, complexity rules |
37
- | `tailwind-tokens` | Enforce Tailwind CSS design tokens — no arbitrary values when a token exists |
38
- | `drf-best-practices` | Django REST Framework — thin serializers, service layer, queryset optimization, object-level permissions |
39
- | `fastapi-best-practices` | FastAPI — async correctness, Pydantic validation, dependency injection, service layer, structured error handling |
40
- | `security-practices` | Web security — OWASP Top 10 prevention, input validation, auth, SQL injection, XSS, CSRF, secure defaults |
41
- | `alembic-migrations` | Alembic — naming conventions, autogenerate review, data migration safety, downgrades, production deployment |
42
- | `testing-best-practices` | Testing — Arrange-Act-Assert, factory-based test data, test isolation, mocking boundaries, pyramid-balanced coverage |
43
- | `docker-best-practices` | Docker — multi-stage builds, layer caching, security hardening, Compose Watch for local dev, health checks |
44
- | `trpc-react-query` | tRPC v11 — queryOptions/mutationOptions patterns, router organization, middleware, cache invalidation, optimistic updates |
45
38
  | `express-best-practices` | Express.js — feature-based structure, 3-layer architecture, Zod validation, centralized error handling, security middleware |
46
39
  | `fastify-best-practices` | Fastify — plugin architecture, encapsulation, TypeBox validation/serialization, services as decorators, reply helpers, hooks |
40
+ | `fastapi-best-practices` | FastAPI — async correctness, Pydantic validation, dependency injection, service layer, structured error handling |
41
+ | `drf-best-practices` | Django REST Framework — thin serializers, service layer, queryset optimization, object-level permissions |
47
42
  | `drizzle-orm` | Drizzle ORM — schema design, identity columns, relations, relational queries, migrations, drizzle-kit workflow, type inference |
48
- | `zustand` | Zustandstore design, selectors, persist/immer middleware, slices pattern, devtools, transient updates |
49
- | `tauri-v2` | Tauri v2 IPC commands, plugins, window management, system tray, global shortcuts, capabilities/permissions, events |
50
- | `dnd-kit` | @dnd-kit — sortable lists, sensors, collision detection, drag overlays, multi-container (kanban), accessibility |
51
- | `framer-motion` | Motion (Framer Motion) — AnimatePresence, layout animations, variants, gestures, useAnimate, performance |
43
+ | `alembic-migrations` | Alembicnaming conventions, autogenerate review, data migration safety, downgrades, production deployment |
44
+ | `docker-best-practices` | Dockermulti-stage builds, layer caching, security hardening, Compose Watch for local dev, health checks |
45
+
46
+ ### Database
47
+
48
+ | Skill | Description |
49
+ |-------|-------------|
50
+ | `sql-joins` | SQL joins — LEFT JOIN traps, fan-out, NOT IN NULL bug, EXISTS vs IN, FK design, junction tables, CASCADE pitfalls |
51
+ | `sql-indexing` | SQL indexing — composite order, covering/partial/expression indexes, SARGability, EXPLAIN interpretation, keyset pagination |
52
+ | `sql-schema-design` | SQL schema — normalization, data types (TIMESTAMPTZ, NUMERIC), constraints, anti-patterns, safe migrations |
53
+ | `sql-orm-patterns` | SQL ORM — N+1 fixes for Prisma/Django/SQLAlchemy/ActiveRecord/TypeORM, transactions, isolation levels, locking |
54
+
55
+ ### Architecture
56
+
57
+ | Skill | Description |
58
+ |-------|-------------|
52
59
  | `single-responsibility` | Single Responsibility Principle — language-agnostic SRP, file size limits, CQS, separation of concerns, smell tests |
53
60
 
54
- ## GitHub Authentication
61
+ ### Quality
62
+
63
+ | Skill | Description |
64
+ |-------|-------------|
65
+ | `testing-best-practices` | Testing — Arrange-Act-Assert, factory-based test data, test isolation, mocking boundaries, pyramid-balanced coverage |
66
+ | `security-practices` | Web security — OWASP Top 10 prevention, input validation, auth, SQL injection, XSS, CSRF, secure defaults |
67
+
68
+ ## Commands
69
+
70
+ Portable slash commands for common git workflows. Installed to `.claude/commands/` in your project.
71
+
72
+ | Command | Description |
73
+ |---------|-------------|
74
+ | `/commit` | Smart commit — branch safety, atomic staging, conventional commits |
75
+ | `/pr` | Create PR — auto-detect base branch, structured summary and test plan |
76
+ | `/release` | Release flow — dev→main PR with semver, changelog, tag, and GitHub release |
77
+ | `/refactor` | Find code files over 200 lines and refactor them into smaller modules |
78
+ | `/deep-review` | Multi-agent deep code review — 5 parallel agents catch guard bypasses, lost async state, wrong-table queries, dead references, protocol violations |
79
+
80
+ ## Quick Start
55
81
 
56
- The CLI fetches skills via the GitHub API. Unauthenticated requests are limited to 60/hour. To avoid rate limits:
82
+ Run from any project directory:
57
83
 
58
- - Install the [GitHub CLI](https://cli.github.com) and run `gh auth login` — the token is detected automatically
59
- - Or set `GITHUB_TOKEN` / `GH_TOKEN` as an environment variable
84
+ ```bash
85
+ npx @spardutti/claude-skills
86
+ ```
87
+
88
+ The CLI will:
89
+
90
+ 1. Fetch the latest skills and commands from GitHub
91
+ 2. Let you pick which skills to install → `.claude/skills/`
92
+ 3. Let you pick which commands to install → `.claude/commands/`
93
+ 4. **Optionally set up automatic skill evaluation** (recommended — see below)
94
+
95
+ ## Automatic Skill Evaluation
96
+
97
+ After installing skills, the CLI asks if you want to set up automatic skill evaluation. If you say yes, it will:
98
+
99
+ - **Create a hook** at `.claude/hooks/skill-forced-eval-hook.sh` that runs on every prompt
100
+ - **Update your `CLAUDE.md`** with a `skill_evaluation` rule
101
+
102
+ This forces Claude to explicitly evaluate every installed skill before writing code — listing each skill as ACTIVATE or SKIP with a reason, then calling the relevant ones. Without this, Claude may silently ignore your skills.
60
103
 
61
- ## What are Claude Code Skills?
104
+ ### What gets created
62
105
 
63
- Skills are markdown files placed in `.claude/skills/` that give Claude Code domain-specific knowledge and guidelines. They help Claude follow your team's patterns and best practices automatically.
106
+ **`.claude/settings.json`** Registers the hook:
64
107
 
65
- ## License
108
+ ```json
109
+ {
110
+ "hooks": {
111
+ "UserPromptSubmit": [
112
+ {
113
+ "hooks": [
114
+ {
115
+ "type": "command",
116
+ "command": ".claude/hooks/skill-forced-eval-hook.sh"
117
+ }
118
+ ]
119
+ }
120
+ ]
121
+ }
122
+ }
123
+ ```
124
+
125
+ **`CLAUDE.md`** — Appends the evaluation rule:
126
+
127
+ ```yaml
128
+ skill_evaluation:
129
+ mandatory: true
130
+ rule: |
131
+ BEFORE writing ANY code, you MUST:
132
+ 1. List EVERY skill from the system-reminder's available skills section
133
+ 2. For each skill, write: [skill-name] → ACTIVATE / SKIP — [one-line reason]
134
+ 3. Call Skill(name) for every skill marked ACTIVATE
135
+ 4. Only THEN proceed to implementation
136
+ If you skip this evaluation, your response is INCOMPLETE and WRONG.
137
+ ```
138
+
139
+ ### GitHub Authentication
140
+
141
+ The CLI uses the GitHub API to fetch skills. To avoid rate limits:
66
142
 
67
- MIT
143
+ - If you have the [GitHub CLI](https://cli.github.com) installed and authenticated (`gh auth login`), the token is picked up automatically
144
+ - Or set `GITHUB_TOKEN` / `GH_TOKEN` environment variable
145
+ - Without auth, GitHub allows 60 requests/hour (the CLI uses ~6 per run)
146
+
147
+ ## Manual Install
148
+
149
+ Copy a skill directory into your project's `.claude/skills/` folder:
150
+
151
+ ```bash
152
+ cp -r skills/<skill-name> /path/to/project/.claude/skills/
153
+ ```
package/package.json CHANGED
@@ -1,11 +1,15 @@
1
1
  {
2
2
  "name": "@spardutti/claude-skills",
3
- "version": "1.19.0",
3
+ "version": "1.19.2",
4
4
  "description": "CLI to install Claude Code skills from the claude-skills collection",
5
5
  "type": "module",
6
6
  "bin": {
7
7
  "claude-skills": "bin/cli.mjs"
8
8
  },
9
+ "scripts": {
10
+ "prepack": "cp ../README.md README.md",
11
+ "postpack": "git checkout -- README.md"
12
+ },
9
13
  "engines": {
10
14
  "node": ">=18"
11
15
  },