Skip to content
Back to search

claude-skillz

SkillWorks with Claude CodeGitHub

Random Claude skills for common, simple programming tasks

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/ntcoding--claude-skillz/badge.svg)](/listings/ntcoding--claude-skillz)

HTML

<a href="/listings/ntcoding--claude-skillz"><img src="/api/listings/ntcoding--claude-skillz/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Per-project

Add the plugin to your `settings.json`. See [Claude Plugin Settings](https://code.claude.com/docs/en/settings#plugin-configuration).

Globally Setup Marketplace

**Local:**

/plugin marketplace add file:///absolute/path/to/claude-skillz

**GitHub:**

/plugin marketplace add ntcoding/claude-skillz

Install Plugins

**Interactive:** 1. Run `/plugin` 2. Select `Browse and install plugins` 3. Select `claude-skillz` marketplace 4. Select desired plugin 5. Select `Install now`

**Direct:**

/plugin install <plugin-name>@claude-skillz

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 138 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "claude-skillz",
  3. "owner": {
  4. "name": "Nick Tune",
  5. "email": "nick@ntcoding.co.uk"
  6. },
  7. "metadata": {
  8. "description": "Nick Tune's claude code skills",
  9. "version": "1.3.0",
  10. "homepage": "https://github.com/ntcoding/claude-skillz"
  11. },
  12. "plugins": [
  13. {
  14. "name": "task-check",
  15. "source": "./task-check",
  16. "description": "Verify task completion before finishing work. Catches incomplete work, bugs, and quality issues.",
  17. "version": "1.0.5",
  18. "category": "productivity",
  19. "keywords": ["task", "qa", "verification", "completion", "quality"]
  20. },
  21. {
  22. "name": "automatic-code-review",
  23. "source": "./automatic-code-review",
  24. "description": "Automatic code review on session stop with configurable rules",
  25. "version": "1.0.4",
  26. "category": "development",
  27. "keywords": ["code-review", "quality", "hooks", "semantic-review"]
  28. },
  29. {
  30. "name": "full-codebase-review",
  31. "source": "./full-codebase-review",
  32. "description": "Periodic full codebase review using automatic-code-review rules. Reviews entire codebase, not just modified files.",
  33. "version": "1.0.1",
  34. "category": "development",
  35. "keywords": ["code-review", "tech-debt", "codebase-analysis", "periodic-review", "quality"]
  36. },
  37. {
  38. "name": "track-and-improve",
  39. "source": "./track-and-improve",
  40. "description": "Capture mistakes and improvement opportunities with automatic 5 whys analysis",
  41. "version": "1.0.0",
  42. "category": "productivity",
  43. "keywords": ["improvement", "tracking", "feedback", "learning"]
  44. },
  45. {
  46. "name": "collaboration-modes",
  47. "source": "./collaboration-modes",
  48. "description": "Define collaboration style between Claude Code and user: step-by-step, deep-think, or pair programming",
  49. "version": "1.0.1",
  50. "category": "productivity",
  51. "keywords": ["collaboration", "workflow", "pair-programming", "modes"]
  52. },
  53. {
  54. "name": "learn-from-prs",
  55. "source": "./learn-from-prs",
  56. "description": "Analyze PR feedback patterns from CodeRabbit, SonarQube, and reviewers to suggest config updates that catch issues locally",
  57. "version": "1.0.0",
  58. "category": "development",
  59. "keywords": ["pr-review", "feedback", "learning", "code-quality", "conventions"]
  60. },
  61. {
  62. "name": "challenge-that",
  63. "source": "./challenge-that",
  64. "description": "Force critical evaluation of proposals from 5 adversarial perspectives (Skeptic, Pragmatist, Edge Case Hunter, Structural Critic, Root Cause Analyst)",
  65. "version": "1.0.0",
  66. "category": "productivity",
  67. "keywords": ["critical-thinking", "evaluation", "review", "proposals", "decisions"]
  68. },
  69. {
  70. "name": "architect-refine-critique",
  71. "source": "./architect-refine-critique",
  72. "description": "Three-phase design review producing an ADR: Architect → Refiner → Critique → Interactive Review. Run /arc-review after to produce the ADR. Run /arc-prd to add architecture section to a PRD.",
  73. "version": "1.6.1",
  74. "category": "development",
  75. "keywords": ["architecture", "design-review", "refactoring", "ddd", "separation-of-concerns"]
  76. },
  77. {
  78. "name": "session-optimizer",
  79. "source": "./session-optimizer",
  80. "description": "Analyze session transcripts for optimization opportunities using 4 parallel subagents",
  81. "version": "1.0.0",
  82. "category": "productivity",
  83. "keywords": ["session", "optimization", "analysis", "workflow"]
  84. },
  85. {
  86. "name": "optimization-team",
  87. "source": "./optimization-team",
  88. "description": "Two-agent optimization team: researcher proposes, critic challenges, lead presents synthesized result",
  89. "version": "1.0.0",
  90. "category": "productivity",
  91. "keywords": ["optimization", "agent-teams", "research", "critique", "claude-code"]
  92. },
  93. {
  94. "name": "claude-code-updates",
  95. "source": "./claude-code-updates",
  96. "description": "Detects Claude Code version updates and surfaces relevant new features. SessionStart hook nudges on updates, /whats-new command analyzes changelog and blog for applicable changes.",
  97. "version": "1.0.0",
  98. "category": "productivity",
  99. "keywords": ["updates", "changelog", "features", "version-tracking", "release-notes"]
  100. },
  101. {
  102. "name": "development-skills",
  103. "source": "./",
  104. "description": "Random skills for various software development tasks",
  105. "version": "5.7.0",
  106. "category": "development",
  107. "keywords": ["tdd", "design", "workflow", "personality", "project-setup"],
  108. "skills": [
  109. "./tdd-process",
  110. "./writing-tests",
  111. "./switch-persona",
  112. "./lightweight-implementation-analysis-protocol",
  113. "./lightweight-design-analysis",
  114. "./software-design-principles",
  115. "./critical-peer-personality",
  116. "./independent-research",
  117. "./concise-output",
  118. "./observability-first-debugging",
  119. "./data-visualization",
  120. "./confidence-honesty",
  121. "./questions-are-not-instructions",
  122. "./create-tasks",
  123. "./typescript-backend-project-setup",
  124. "./separation-of-concerns",
  125. "./tactical-ddd",
  126. "./fix-it-never-work-around-it"
  127. ]
  128. },
  129. {
  130. "name": "fetching-circleci-logs",
  131. "source": "./fetching-circleci-logs",
  132. "description": "Fetch CircleCI job logs via v1.1 API with step-level output and failure analysis",
  133. "version": "1.0.0",
  134. "category": "development",
  135. "keywords": ["circleci", "ci", "build-logs", "debugging", "pr-checks"]
  136. }
  137. ]
  138. }
README.md · README · 163 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Claude Skills & Composable Personas
  2. Reusable skills and composable system prompts for Claude Code.
  3. ---
  4. ## Claude Launcher
  5. **Interactive system prompt and model selector for Claude Code.**
  6. Start Claude with your chosen persona and model in seconds:
  7. ```bash
  8. # Interactive 2-step selection (persona → model)
  9. $ cl
  10. # Direct shortcuts (order-independent)
  11. $ cl tdd opus # Super TDD Developer + Opus
  12. $ cl opt sonn # Claude Code Optimizer + Sonnet
  13. $ cl haik # Generalist Robot + Haiku (default persona + model)
  14. # Model-only (uses generalist-robot)
  15. $ cl sonn
  16. $ cl opus
  17. ```
  18. **Features:**
  19. - Order-independent shortcuts: `cl tdd sonn` = `cl sonn tdd`
  20. - Frontmatter-based shortcuts (add your own personas instantly)
  21. - Automatic skill loading via @ references
  22. - Conflict detection with prominent warnings
  23. - Exports CLAUDE_PERSONA for status line display
  24. **Setup:**
  25. ```bash
  26. alias cl='python3 /path/to/claude-skillz/claude-launcher/claude-launcher.py'
  27. # Optional: Install fzf for interactive fuzzy search
  28. brew install fzf # macOS
  29. ```
  30. See [available personas](#system-prompts) below. You can [add your own](claude-launcher/README.md#adding-your-own-personas).
  31. ---
  32. ## OpenCode Launcher
  33. **Generates OpenCode agents from the same personas used by Claude Launcher.**
  34. This repo contains system prompts that work with both Claude Code and OpenCode:
  35. - **Claude Launcher** (`cl`) - for Claude Code
  36. - **OpenCode Launcher** - generates agents for OpenCode
  37. ```bash
  38. # Generate OpenCode agents (run once or after changing personas)
  39. python3 opencode-launcher/generate-opencode-agents.py
  40. # Then use OpenCode - agents appear in agent selector
  41. opencode
  42. ```
  43. See [opencode-launcher/README.md](opencode-launcher/README.md) for details.
  44. ---
  45. ## Installation
  46. ### Per-project
  47. Add the plugin to your `settings.json`. See [Claude Plugin Settings](https://code.claude.com/docs/en/settings#plugin-configuration).
  48. ### Globally Setup Marketplace
  49. **Local:**
  50. ```bash
  51. /plugin marketplace add file:///absolute/path/to/claude-skillz
  52. ```
  53. **GitHub:**
  54. ```bash
  55. /plugin marketplace add ntcoding/claude-skillz
  56. ```
  57. ### Install Plugins
  58. **Interactive:**
  59. 1. Run `/plugin`
  60. 2. Select `Browse and install plugins`
  61. 3. Select `claude-skillz` marketplace
  62. 4. Select desired plugin
  63. 5. Select `Install now`
  64. **Direct:**
  65. ```bash
  66. /plugin install <plugin-name>@claude-skillz
  67. ```
  68. ## Available Skills
  69. Skills are reusable behavioral instructions loaded into personas. Load them with `@` references in your system prompts.
  70. ### Research & Evidence
  71. - **independent-research** - Research-driven investigation. Never guess—validate solutions before presenting. Use WebFetch, WebSearch, testing.
  72. - **confidence-honesty** - Force honest confidence assessment. Express confidence as percentage, explain gaps, validate assumptions before presenting.
  73. ### Communication & Output
  74. - **concise-output** - Signal-over-noise. Eliminate verbose phrases, prioritize density. Every word must carry information.
  75. - **critical-peer-personality** - Professional, skeptical communication. Challenge constructively, propose instead of asking, coach rather than serve.
  76. - **questions-are-not-instructions** - Answer questions literally. Don't interpret as hidden instructions. STOP after answering, let user decide.
  77. ### Code & Design
  78. - **software-design-principles** - Object calisthenics, dependency inversion, fail-fast error handling, feature envy detection, intention-revealing naming.
  79. - **lightweight-implementation-analysis-protocol** - Trace execution paths before implementing. Create lightweight diagrams. Prevent wasted effort from assumptions.
  80. - **lightweight-design-analysis** - Systematic design review across 8 dimensions: Naming, Object Calisthenics, Coupling & Cohesion, Immutability, Domain Integrity, Type System, Simplicity, Performance.
  81. ### Development Processes
  82. - **tdd-process** - Strict TDD state machine: red-green-refactor with 11 enforced rules. Meaningful failures, minimum implementations, full verification.
  83. - **writing-tests** - Principles for effective tests. Naming conventions, assertion best practices, comprehensive edge case checklists (based on BugMagnet).
  84. - **observability-first-debugging** - Systematic debugging. Add instrumentation to gather specific data. Evidence before hypothesis.
  85. ### Workflows & Tools
  86. - **switch-persona** - Mid-conversation persona switching without restart. Lists personas, reads file, switches immediately.
  87. - **lightweight-task-workflow** - Task list state machine for multi-session work. Tracks status, prevents auto-advancement, enforces state transitions.
  88. - **create-tasks** - Convert requirements into actionable tasks following a structured template. Engineering-ready work items.
  89. ### Specialized
  90. - **data-visualization** - Build charts, graphs, dashboards. Visual execution, technical implementation, perceptual foundations, chart selection, layout algorithms, library guidance.
  91. - **typescript-backend-project-setup** - NX monorepo setup for TypeScript backend projects optimized for AI-assisted development.
  92. ## System Prompts
  93. 12 pre-built personas ready to use via `cl` shortcuts:
  94. | Shortcut | Persona |
  95. |----------|---------|
  96. | `tdd` | [Super TDD Developer](system-prompts/super-tdd-developer.md) |
  97. | `opt` | [Claude Code Optimizer](system-prompts/claude-code-optimizer.md) |
  98. | `prd` | [PRD Expert](system-prompts/prd-expert.md) |
  99. | `arc` | [Strategic Architect](system-prompts/strategic-architect.md) |
  100. | `doc` | [Documentation Expert](system-prompts/documentation-expert.md) |
  101. | `rct` | [Super React Developer](system-prompts/super-react-developer.md) |
  102. | `inv` | [Technical Investigator](system-prompts/technical-investigator.md) |
  103. | `wrt` | [Writing Tool](system-prompts/writing-tool.md) |
  104. | `tsc` | [Super TypeScript Developer](system-prompts/super-typescript-developer.md) |
  105. | `viz` | [Frontend Visualization Expert](system-prompts/frontend-visualization-expert.md) |
  106. | `uix` | [UI/UX Design Leader](system-prompts/ui-design-expert.md) |
  107. | `gen` | [Generalist Robot](system-prompts/generalist-robot.md) |
  108. ### Composability
  109. System prompts use @ references to load skills. See [CLAUDE.md](CLAUDE.md) for composability guidelines and [launcher docs](claude-launcher/README.md#adding-your-own-personas) for creating custom personas.a
  110. ## Plugins
  111. - **track-and-improve** - Capture mistakes and improvement opportunities with automatic 5 whys root cause analysis
  112. - **automatic-code-review** - Automatic semantic code review on session stop with configurable project-specific rules. Auto-initializes with default rules, supports any language.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.