@skills · Owner
Agent skills by neolabhq
231 skills indexed from github.com/neolabhq. Reference any of them in AdaL, Claude Code, Cursor or any coding agent — nothing to install.
- actualize · Skill · 1,306 stars
Reconcile the project's FPF state with recent repository changes
- add-task · Skill · 1,306 stars
creates draft task file in .specs/tasks/draft/ with original user intent
- agent-evaluation · Skill · 1,306 stars
Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring
- analyse · Skill · 1,306 stars
Auto-selects best Kaizen method (Gemba Walk, Value Stream, or Muda) for target
- analyse-problem · Skill · 1,306 stars
Comprehensive A3 one-page problem analysis with root cause and action plan
- analyze-issue · Skill · 1,306 stars
Analyze a GitHub issue and create a detailed technical specification
- apply-anthropic-skill-best-practices · Skill · 1,306 stars
Comprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure
- attach-review-to-pr · Skill · 1,306 stars
Add line-specific review comments to pull requests using GitHub CLI API
- brainstorm · Skill · 1,306 stars
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative question
- build-mcp · Skill · 1,306 stars
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use w
- cause-and-effect · Skill · 1,306 stars
Systematic Fishbone analysis exploring problem causes across six categories
- commit · Skill · 1,306 stars
Create well-formatted commits with conventional commit messages and emoji
- context-engineering · Skill · 1,306 stars
Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents
- context-engineering-kit · Collection · 1,306 stars
- create-agent · Skill · 1,306 stars
Comprehensive guide for creating Claude Code agents with proper structure, triggering conditions, system prompts, and validation - combines official Anthro
- create-command · Skill · 1,306 stars
Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration
- create-hook · Skill · 1,306 stars
Create and configure git hooks with intelligent project analysis, suggestions, and automated testing
- create-ideas · Skill · 1,306 stars
Generate ideas in one shot using creative sampling
- create-pr · Skill · 1,306 stars
Create pull requests using GitHub CLI with proper templates and formatting
- create-rule · Skill · 1,306 stars
Use when found gap or repetative issue, that produced by you or implemenataion agent. Esentially use it each time when you say "You absolutly right, I shou
- create-skill · Skill · 1,306 stars
Guide for creating effective skills. This command should be used when users want to create a new skill (or update an existing skill) that extends Claude's
- create-workflow-command · Skill · 1,306 stars
Create a workflow command that orchestrates multi-step execution through sub-agents with file-based task prompts
- critique · Skill · 1,306 stars
Comprehensive multi-perspective review using specialized judges with debate and consensus building
- customaize-agent · Collection · 1,306 stars
- decay · Skill · 1,306 stars
Manage evidence freshness by identifying stale decisions and providing governance actions
- design-testing-strategy · Skill · 1,306 stars
Use before writing any type of tests. Distills 14 industry sources into deterministic decision gates, schemas, and worked test examples.
- do-and-judge · Skill · 1,306 stars
Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop
- do-competitively · Skill · 1,306 stars
Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis
- do-in-parallel · Skill · 1,306 stars
Run independent tasks concurrently across multiple files or targets using parallel sub-agents, with per-task model selection and LLM-as-a-judge verificatio
- do-in-steps · Skill · 1,306 stars
Execute one complex task as ordered, dependent steps run sequentially, passing context from each step to the next, with per-step LLM-as-a-judge verificatio
- docs · Collection · 1,306 stars
- fix-tests · Skill · 1,306 stars
Systematically fix all failing tests after business logic changes or refactoring
- fpf · Collection · 1,306 stars
- git · Collection · 1,306 stars
- git-notes · Skill · 1,306 stars
Use when adding metadata to commits without changing history, tracking review status, test results, code quality annotations, or supplementing commit messa
- git-worktrees · Skill · 1,306 stars
Use when working on multiple branches simultaneously, context switching without stashing, reviewing PRs while developing, testing in isolation, or comparin
- implement-task · Skill · 1,306 stars
Implement a task step by step with automated LLM-as-Judge verification at the end of each phase
- judge · Skill · 1,306 stars
Launch a meta-judge then a judge sub-agent to evaluate results produced in the current conversation
- judge-with-debate · Skill · 1,306 stars
Evaluate solutions through multi-round debate between independent judges until consensus
- kaizen · Skill · 1,306 stars
Use when Code implementation and refactoring, architecturing or designing systems, process and workflow improvements, error handling and validation. Provid
- kaizen · Collection · 1,306 stars
- launch-sub-agent · Skill · 1,306 stars
Launch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and mandatory
- load-issues · Skill · 1,306 stars
Load all open issues from GitHub and save them as markdown files
- load-pr-comments · Skill · 1,306 stars
Use to load open/unresolved PR review comments then aggregate them as tasks in .specs/comments/*.md for parallel agents to fix.
- mcp · Collection · 1,306 stars
- memorize · Skill · 1,306 stars
Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering
- multi-agent-patterns · Skill · 1,306 stars
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or whe
- plan-do-check-act · Skill · 1,306 stars
Iterative PDCA cycle for systematic experimentation and continuous improvement
- plan-task · Skill · 1,306 stars
Refine a draft task specification into a fully planned, implementation-ready task with acceptance criteria, architecture, per-step sub-task files and verif
- plugins · Collection · 1,306 stars
- prompt-engineering · Skill · 1,306 stars
Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, im
- propose-hypotheses · Skill · 1,306 stars
Execute complete FPF cycle from hypothesis generation to decision
- query · Skill · 1,306 stars
Search the FPF knowledge base and display hypothesis details with assurance information
- reflect · Skill · 1,306 stars
Reflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity triage and verification
- reflexion · Collection · 1,306 stars
- reset · Skill · 1,306 stars
Reset the FPF reasoning cycle to start fresh
- resolve-fixed-pr-comments · Skill · 1,306 stars
Verify what PR review comments have been addressed (committed/pushed OR uncommitted local changes) and resolve the threads that are genuinely fixed or no l
- review · Collection · 1,306 stars
- review-local-changes · Skill · 1,306 stars
Review your local uncommitted working-tree changes (git diff plus untracked files) and return actionable improvement suggestions. Use before committing, wh
- review-pr · Skill · 1,306 stars
Review an existing GitHub pull request and post inline review comments on its diff. Use when the changes are on an opened PR rather than your local working
- root-cause-tracing · Skill · 1,306 stars
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, a
- sadd · Collection · 1,306 stars
- sdd · Collection · 1,306 stars
- setup-arxiv-mcp · Skill · 1,306 stars
Guide for setup arXiv paper search MCP server using Docker MCP
- setup-codemap-cli · Skill · 1,306 stars
Guide for setup Codemap CLI for intelligent codebase visualization and navigation
- setup-context7-mcp · Skill · 1,306 stars
Guide for setup Context7 MCP server to load documentation for specific technologies.
- setup-serena-mcp · Skill · 1,306 stars
Guide for setup Serena MCP server for semantic code retrieval and editing capabilities
- skills · Collection · 1,306 stars
- skills · Collection · 1,306 stars
- skills · Collection · 1,306 stars
- skills · Collection · 1,306 stars
- skills · Collection · 1,306 stars
- skills · Collection · 1,306 stars
- skills · Collection · 1,306 stars
- skills · Collection · 1,306 stars
- skills · Collection · 1,306 stars
- skills · Collection · 1,306 stars
- skills · Collection · 1,306 stars
- status · Skill · 1,306 stars
Display the current state of the FPF knowledge base
- subagent-driven-development · Skill · 1,306 stars
Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shar
- tdd · Collection · 1,306 stars
- test-coverage · Skill · 1,306 stars
Use after writing tests to assess coverage quality across structural, mutation, requirements, and API/integration dimensions; organized knowledge for choos
- test-driven-development · Skill · 1,306 stars
Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures
- test-prompt · Skill · 1,306 stars
Use when creating or editing any prompt (commands, hooks, skills, subagent instructions) to verify it produces desired behavior - applies RED-GREEN-REFACTO
- test-skill · Skill · 1,306 stars
Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to
- thought-based-reasoning · Skill · 1,306 stars
Use when tackling complex reasoning tasks requiring step-by-step logic, multi-step arithmetic, commonsense reasoning, symbolic manipulation, or problems wh
- traiage-review · Skill · 1,306 stars
This skill should be used when need prioritize what changed code in repository human must review.
- tree-of-thoughts · Skill · 1,306 stars
Execute tasks through systematic exploration, pruning, and expansion using Tree of Thoughts methodology with meta-judge evaluation specifications and multi
- update-docs · Skill · 1,306 stars
Update and maintain project documentation for local code changes using multi-agent workflow with tech-writer agents. Covers docs/, READMEs, JSDoc, and API
- why · Skill · 1,306 stars
Iterative Five Whys root cause analysis drilling from symptoms to fundamentals
- write-concisely · Skill · 1,306 stars
Apply writing rules to any documentation that humans will read. Makes your writing clearer, stronger, and more professional.
- write-tests · Skill · 1,306 stars
Add missing test coverage for your local code changes by generating new test files (covers uncommitted and untracked changes, or the latest commit if every
- actualize · Skill
Reconcile the project's FPF state with recent repository changes
- actualize · Skill
Reconcile the project's FPF state with recent repository changes
- add-task · Skill
creates draft task file in .specs/tasks/draft/ with original user intent
- add-task · Skill
creates draft task file in .specs/tasks/draft/ with original user intent
- agent-evaluation · Skill
Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring
- agent-evaluation · Skill
Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring
- analyse · Skill
Auto-selects best Kaizen method (Gemba Walk, Value Stream, or Muda) for target
- analyse · Skill
Auto-selects best Kaizen method (Gemba Walk, Value Stream, or Muda) for target
- analyse-problem · Skill
Comprehensive A3 one-page problem analysis with root cause and action plan
- analyse-problem · Skill
Comprehensive A3 one-page problem analysis with root cause and action plan
- analyze-issue · Skill
Analyze a GitHub issue and create a detailed technical specification
- analyze-issue · Skill
Analyze a GitHub issue and create a detailed technical specification
- antigravity · Collection
- apply-anthropic-skill-best-practices · Skill
Comprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure
- apply-anthropic-skill-best-practices · Skill
Comprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure
- attach-review-to-pr · Skill
Add line-specific review comments to pull requests using GitHub CLI API
- attach-review-to-pr · Skill
Add line-specific review comments to pull requests using GitHub CLI API
- brainstorm · Skill
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative question
- brainstorm · Skill
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative question
- build-mcp · Skill
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use w
- build-mcp · Skill
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use w
- cause-and-effect · Skill
Systematic Fishbone analysis exploring problem causes across six categories
- cause-and-effect · Skill
Systematic Fishbone analysis exploring problem causes across six categories
- commit · Skill
Create well-formatted commits with conventional commit messages and emoji
- commit · Skill
Create well-formatted commits with conventional commit messages and emoji
- context-engineering · Skill
Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents
- context-engineering · Skill
Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents
- create-agent · Skill
Comprehensive guide for creating Claude Code agents with proper structure, triggering conditions, system prompts, and validation - combines official Anthro
- create-agent · Skill
Comprehensive guide for creating Claude Code agents with proper structure, triggering conditions, system prompts, and validation - combines official Anthro
- create-command · Skill
Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration
- create-command · Skill
Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration
- create-hook · Skill
Create and configure git hooks with intelligent project analysis, suggestions, and automated testing
- create-hook · Skill
Create and configure git hooks with intelligent project analysis, suggestions, and automated testing
- create-ideas · Skill
Generate ideas in one shot using creative sampling
- create-ideas · Skill
Generate ideas in one shot using creative sampling
- create-pr · Skill
Create pull requests using GitHub CLI with proper templates and formatting
- create-pr · Skill
Create pull requests using GitHub CLI with proper templates and formatting
- create-rule · Skill
Use when found gap or repetative issue, that produced by you or implemenataion agent. Esentially use it each time when you say "You absolutly right, I shou
- create-rule · Skill
Use when found gap or repetative issue, that produced by you or implemenataion agent. Esentially use it each time when you say "You absolutly right, I shou
- create-skill · Skill
Guide for creating effective skills. This command should be used when users want to create a new skill (or update an existing skill) that extends Claude's
- create-skill · Skill
Guide for creating effective skills. This command should be used when users want to create a new skill (or update an existing skill) that extends Claude's
- create-workflow-command · Skill
Create a workflow command that orchestrates multi-step execution through sub-agents with file-based task prompts
- create-workflow-command · Skill
Create a workflow command that orchestrates multi-step execution through sub-agents with file-based task prompts
- critique · Skill
Comprehensive multi-perspective review using specialized judges with debate and consensus building
- critique · Skill
Comprehensive multi-perspective review using specialized judges with debate and consensus building
- decay · Skill
Manage evidence freshness by identifying stale decisions and providing governance actions
- decay · Skill
Manage evidence freshness by identifying stale decisions and providing governance actions
- design-testing-strategy · Skill
Use before writing any type of tests. Distills 14 industry sources into deterministic decision gates, schemas, and worked test examples.
- design-testing-strategy · Skill
Use before writing any type of tests. Distills 14 industry sources into deterministic decision gates, schemas, and worked test examples.
- do-and-judge · Skill
Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop
- do-and-judge · Skill
Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop
- do-competitively · Skill
Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis
- do-competitively · Skill
Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis
- do-in-parallel · Skill
Run independent tasks concurrently across multiple files or targets using parallel sub-agents, with per-task model selection and LLM-as-a-judge verificatio
- do-in-parallel · Skill
Run independent tasks concurrently across multiple files or targets using parallel sub-agents, with per-task model selection and LLM-as-a-judge verificatio
- do-in-steps · Skill
Execute one complex task as ordered, dependent steps run sequentially, passing context from each step to the next, with per-step LLM-as-a-judge verificatio
- do-in-steps · Skill
Execute one complex task as ordered, dependent steps run sequentially, passing context from each step to the next, with per-step LLM-as-a-judge verificatio
- fix-tests · Skill
Systematically fix all failing tests after business logic changes or refactoring
- fix-tests · Skill
Systematically fix all failing tests after business logic changes or refactoring
- git-notes · Skill
Use when adding metadata to commits without changing history, tracking review status, test results, code quality annotations, or supplementing commit messa
- git-notes · Skill
Use when adding metadata to commits without changing history, tracking review status, test results, code quality annotations, or supplementing commit messa
- git-worktrees · Skill
Use when working on multiple branches simultaneously, context switching without stashing, reviewing PRs while developing, testing in isolation, or comparin
- git-worktrees · Skill
Use when working on multiple branches simultaneously, context switching without stashing, reviewing PRs while developing, testing in isolation, or comparin
- implement-task · Skill
Implement a task step by step with automated LLM-as-Judge verification at the end of each phase
- implement-task · Skill
Implement a task step by step with automated LLM-as-Judge verification at the end of each phase
- judge · Skill
Launch a meta-judge then a judge sub-agent to evaluate results produced in the current conversation
- judge · Skill
Launch a meta-judge then a judge sub-agent to evaluate results produced in the current conversation
- judge-with-debate · Skill
Evaluate solutions through multi-round debate between independent judges until consensus
- judge-with-debate · Skill
Evaluate solutions through multi-round debate between independent judges until consensus
- kaizen · Skill
Use when Code implementation and refactoring, architecturing or designing systems, process and workflow improvements, error handling and validation. Provid
- kaizen · Skill
Use when Code implementation and refactoring, architecturing or designing systems, process and workflow improvements, error handling and validation. Provid
- launch-sub-agent · Skill
Launch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and mandatory
- launch-sub-agent · Skill
Launch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and mandatory
- load-issues · Skill
Load all open issues from GitHub and save them as markdown files
- load-issues · Skill
Load all open issues from GitHub and save them as markdown files
- load-pr-comments · Skill
Use to load open/unresolved PR review comments then aggregate them as tasks in .specs/comments/*.md for parallel agents to fix.
- load-pr-comments · Skill
Use to load open/unresolved PR review comments then aggregate them as tasks in .specs/comments/*.md for parallel agents to fix.
- memorize · Skill
Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering
- memorize · Skill
Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering
- multi-agent-patterns · Skill
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or whe
- multi-agent-patterns · Skill
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or whe
- plan-do-check-act · Skill
Iterative PDCA cycle for systematic experimentation and continuous improvement
- plan-do-check-act · Skill
Iterative PDCA cycle for systematic experimentation and continuous improvement
- plan-task · Skill
Refine a draft task specification into a fully planned, implementation-ready task with acceptance criteria, architecture, per-step sub-task files and verif
- plan-task · Skill
Refine a draft task specification into a fully planned, implementation-ready task with acceptance criteria, architecture, per-step sub-task files and verif
- prompt-engineering · Skill
Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, im
- prompt-engineering · Skill
Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, im
- propose-hypotheses · Skill
Execute complete FPF cycle from hypothesis generation to decision
- propose-hypotheses · Skill
Execute complete FPF cycle from hypothesis generation to decision
- query · Skill
Search the FPF knowledge base and display hypothesis details with assurance information
- query · Skill
Search the FPF knowledge base and display hypothesis details with assurance information
- reflect · Skill
Reflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity triage and verification
- reflect · Skill
Reflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity triage and verification
- reset · Skill
Reset the FPF reasoning cycle to start fresh
- reset · Skill
Reset the FPF reasoning cycle to start fresh
- resolve-fixed-pr-comments · Skill
Verify what PR review comments have been addressed (committed/pushed OR uncommitted local changes) and resolve the threads that are genuinely fixed or no l
- resolve-fixed-pr-comments · Skill
Verify what PR review comments have been addressed (committed/pushed OR uncommitted local changes) and resolve the threads that are genuinely fixed or no l
- review-local-changes · Skill
Review your local uncommitted working-tree changes (git diff plus untracked files) and return actionable improvement suggestions. Use before committing, wh
- review-local-changes · Skill
Review your local uncommitted working-tree changes (git diff plus untracked files) and return actionable improvement suggestions. Use before committing, wh
- review-pr · Skill
Review an existing GitHub pull request and post inline review comments on its diff. Use when the changes are on an opened PR rather than your local working
- review-pr · Skill
Review an existing GitHub pull request and post inline review comments on its diff. Use when the changes are on an opened PR rather than your local working
- root-cause-tracing · Skill
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, a
- root-cause-tracing · Skill
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, a
- setup-arxiv-mcp · Skill
Guide for setup arXiv paper search MCP server using Docker MCP
- setup-arxiv-mcp · Skill
Guide for setup arXiv paper search MCP server using Docker MCP
- setup-codemap-cli · Skill
Guide for setup Codemap CLI for intelligent codebase visualization and navigation
- setup-codemap-cli · Skill
Guide for setup Codemap CLI for intelligent codebase visualization and navigation
- setup-context7-mcp · Skill
Guide for setup Context7 MCP server to load documentation for specific technologies.
- setup-context7-mcp · Skill
Guide for setup Context7 MCP server to load documentation for specific technologies.
- setup-serena-mcp · Skill
Guide for setup Serena MCP server for semantic code retrieval and editing capabilities
- setup-serena-mcp · Skill
Guide for setup Serena MCP server for semantic code retrieval and editing capabilities
- skills · Collection
- skills · Collection
- status · Skill
Display the current state of the FPF knowledge base
- status · Skill
Display the current state of the FPF knowledge base
- subagent-driven-development · Skill
Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shar
- subagent-driven-development · Skill
Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shar
- test-coverage · Skill
Use after writing tests to assess coverage quality across structural, mutation, requirements, and API/integration dimensions; organized knowledge for choos
- test-coverage · Skill
Use after writing tests to assess coverage quality across structural, mutation, requirements, and API/integration dimensions; organized knowledge for choos
- test-driven-development · Skill
Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures
- test-driven-development · Skill
Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures
- test-prompt · Skill
Use when creating or editing any prompt (commands, hooks, skills, subagent instructions) to verify it produces desired behavior - applies RED-GREEN-REFACTO
- test-prompt · Skill
Use when creating or editing any prompt (commands, hooks, skills, subagent instructions) to verify it produces desired behavior - applies RED-GREEN-REFACTO
- test-skill · Skill
Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to
- test-skill · Skill
Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to
- thought-based-reasoning · Skill
Use when tackling complex reasoning tasks requiring step-by-step logic, multi-step arithmetic, commonsense reasoning, symbolic manipulation, or problems wh
- thought-based-reasoning · Skill
Use when tackling complex reasoning tasks requiring step-by-step logic, multi-step arithmetic, commonsense reasoning, symbolic manipulation, or problems wh
- traiage-review · Skill
This skill should be used when need prioritize what changed code in repository human must review.
- traiage-review · Skill
This skill should be used when need prioritize what changed code in repository human must review.
- tree-of-thoughts · Skill
Execute tasks through systematic exploration, pruning, and expansion using Tree of Thoughts methodology with meta-judge evaluation specifications and multi
- tree-of-thoughts · Skill
Execute tasks through systematic exploration, pruning, and expansion using Tree of Thoughts methodology with meta-judge evaluation specifications and multi
- update-docs · Skill
Update and maintain project documentation for local code changes using multi-agent workflow with tech-writer agents. Covers docs/, READMEs, JSDoc, and API
- update-docs · Skill
Update and maintain project documentation for local code changes using multi-agent workflow with tech-writer agents. Covers docs/, READMEs, JSDoc, and API
- why · Skill
Iterative Five Whys root cause analysis drilling from symptoms to fundamentals
- why · Skill
Iterative Five Whys root cause analysis drilling from symptoms to fundamentals
- write-concisely · Skill
Apply writing rules to any documentation that humans will read. Makes your writing clearer, stronger, and more professional.
- write-concisely · Skill
Apply writing rules to any documentation that humans will read. Makes your writing clearer, stronger, and more professional.
- write-tests · Skill
Add missing test coverage for your local code changes by generating new test files (covers uncommitted and untracked changes, or the latest commit if every
- write-tests · Skill
Add missing test coverage for your local code changes by generating new test files (covers uncommitted and untracked changes, or the latest commit if every