Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
build-validator
Validates build, tests, and lint before push to ensure quality gates pass.
goffity/claude-km-skill
-
test-fixer
Fix failing tests based on failure reports, verify fixes, and iterate until all tests pass. This skill should be used after test-executor generates failure reports, providing systematic debugging and fixing strategies that work with any framework or language.
LaizyIO/WorkflowSkills
-
feature-research
Guide interactive research and POC creation to understand features deeply. This skill should be used when planning to implement a new feature and needing to research design patterns, understand integration points in the codebase, consult documentation via MCP Deep Wiki, or create minimal POCs to validate concepts. Can receive CDC.md from feature-specification as input for clear requirements.
LaizyIO/WorkflowSkills
-
feature-workflow
Orchestrate complete or partial feature implementation workflow with configurable phases. This skill should be used to run the full workflow (specification → research → plan → implement → test → fix) or specific phases, coordinating between all feature-implementation skills automatically.
LaizyIO/WorkflowSkills
-
test-executor
Execute tests adaptively, analyze failures, generate detailed failure reports, and iterate until tests pass. This skill should be used when running tests from a test plan, working with any language, framework, or test type (E2E, API, unit, integration, performance).
LaizyIO/WorkflowSkills
-
feature-implementer
Implement feature steps using git worktrees, build and test adaptively, update implementation plan, and generate test plans. This skill should be used when ready to implement one or more steps from an implementation plan, automatically adapting to any framework, language, or project structure.
LaizyIO/WorkflowSkills
-
test-plan-generator
Generate intelligent, non-redundant test plans based on implementation changes. This skill should be used after implementing features to create comprehensive yet efficient test plans with proper coverage across unit, integration, API, and E2E tests without duplication.
LaizyIO/WorkflowSkills
-
feature-specification
Guide iterative specification and CDC (Cahier Des Charges) creation through deep questioning, context analysis, and proactive proposals. Use this skill BEFORE feature-research to clarify requirements, identify prerequisites, define scope, and document complete specifications. Triggers when starting a new feature, task, bug fix, or refactoring and requirements need clarification.
LaizyIO/WorkflowSkills
-
implementation-planner
Generate comprehensive implementation plans with checkboxes, dependencies, and parallelization details. This skill should be used after feature research is complete to create structured, step-by-step implementation plans that track progress, identify dependencies between tasks, and enable multiple developers to work in parallel.
LaizyIO/WorkflowSkills
-
workflow-challenger
Critical review and gap analysis skill that can be invoked at any workflow stage. Use to challenge decisions, identify missing specifications, verify coherence, and surface unaddressed questions in CDC, findings, plans, or any deliverable. Acts as a devil's advocate by deeply analyzing codebase, project documentation ([DOC]-* folders), and context.
LaizyIO/WorkflowSkills
-
git-workflow-manager
Manage git worktrees with GitFlow conventions for parallel development. This skill should be used when creating, managing, or cleaning up git worktrees, following standard GitFlow branch naming (feature/, fix/, hotfix/). 100% generic and reusable across all projects.
LaizyIO/WorkflowSkills
-
skill-name
Describe what this skill does and when to use it.
eirenik0/skills
-
sharpening-the-knife
Use when discovering a useful technique, pattern, or insight during work - pause to capture it as a skill before the knowledge evaporates, preventing the "I'll remember this" trap that causes expertise loss
zgagnon/skills
-
incremental-tdd
Use when implementing features or refactoring with TDD - enforces writing ONE test at a time, implementing minimal code to pass, then repeating, preventing batch test writing that defeats incremental design discovery
zgagnon/skills
-
discovery-tree-workflow
Use when planning and tracking work - creates visible, emergent work breakdown using TypeScript API with just-in-time planning and hierarchical task trees
zgagnon/skills
-
dispatching-systematic-debugging
Use when encountering bugs, test failures, unexpected behavior, errors, or performance problems - dispatches systematic-debugging-agent that enforces 4-phase process (root cause investigation, pattern analysis, hypothesis testing, implementation) to prevent quick-fix attempts and ensure proper debugging
zgagnon/skills
-
using-jj
Use when working with Jujutsu (jj) version control for task management and change tracking - provides workflows for examine-commit-work-squash cycle, checkpointing progress, and managing working copies
zgagnon/skills
-
test-watch-focused-patterns
Use when developing tests or refactoring test suites - run tests in watch mode with focused file patterns to get instant feedback on specific test files without running the entire suite
zgagnon/skills
-
wishful-thinking-programming
Use when building features with unknowns or uncertainties - start from well-understood parts (business logic, UX, pure functions), write code as if ideal collaborators exist, use mocks to define APIs through usage, preventing analysis paralysis from trying to understand everything upfront
zgagnon/skills
-
writing-commit-messages
Use when reviewing commit messages for compliance with the seven rules from cbea.ms/git-commit - checks subject line length, imperative mood, line wrapping, and that the message explains what and why
zgagnon/skills
-
dispatching-incremental-tdd
Use when implementing features or adding functionality - dispatches incremental-tdd-agent that enforces ONE test at a time, preventing batch test writing that defeats incremental design discovery. Maintains discipline through entire feature implementation (10+ test cycles)
zgagnon/skills
-
adr-review
Use when reviewing code for Architecture Decision Record (ADR) compliance during refactoring or code review - checks code against all project ADRs and reports violations with specific fixes
zgagnon/skills
-
k8s-troubleshooter
Use this skill when users report Kubernetes cluster issues, pod failures, or need incident response.
Comprehensive troubleshooting for diagnosing cluster, workload, networking, storage, and Helm issues.
Invoke for: pods not starting (Pending, CrashLoopBackOff, ImagePull), service connectivity problems,
DNS resolution failures, storage/PVC issues, node health problems, CNI/Calico networking, Helm release
failures, or cluster-wide performance degradation. Provides systematic diagnostic workflows, standardized
investigation reports with severity-based depth (Executive Triage Cards for rapid decision-making),
and incident response playbooks with phased triage (baseline → inspect → correlate → deep dive).
All commands are read-only by default for production safety.
randybias/k8s4agents 1
-
android-release-validation
Validate Android release builds before publishing to ensure quality and catch ProGuard issues
hitoshura25/claude-devtools 3