Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
cost-estimator
Infrastructure and development cost estimation for technical projects. Use when planning budgets, evaluating build vs buy decisions, or projecting TCO for architecture choices.
majiayu000/claude-skill-registry 163
-
CLI Testing Patterns
This skill should be used when performing exploratory testing of command-line tools and scripts, including help text validation, option testing, error handling verification, and output validation. Triggers when testing CLI commands, scripts, build tools, or command-line interfaces.
majiayu000/claude-skill-registry 163
-
plan
Draft a repo-local plan using the plan skill template and optionally save it.
majiayu000/claude-skill-registry 163
-
simulation-validator
Validate simulations before, during, and after execution. Use for pre-flight checks, runtime monitoring, post-run validation, diagnosing failed simulations, checking convergence, detecting NaN/Inf, or verifying mass/energy conservation.
majiayu000/claude-skill-registry 163
-
workflow-postmortem
Dual-mode workflow issue logger. Use with mode=log to append mistakes during waves. Use with mode=summary at workflow end to review accumulated issues. Use when completing /build, /audit, or /ms workflows.
majiayu000/claude-skill-registry 163
-
plugin-authoring
Use when creating, modifying, or debugging Claude Code plugins. Triggers on .claude-plugin/, plugin.json, marketplace.json, commands/, agents/, skills/, hooks/ directories. Provides schemas, templates, validation workflows, and troubleshooting.
majiayu000/claude-skill-registry 163
-
stata
Execute Stata do-files via Bash using absolute paths and automatically retrieve logs.
majiayu000/claude-skill-registry 163
-
grpc-patterns
gRPC service implementation patterns. Use when building gRPC services.
majiayu000/claude-skill-registry 163
-
performance-benchmark-specialist
Performance benchmarking expertise for shell tools, covering benchmark design, statistical analysis (min/max/mean/median/stddev), performance targets (<100ms, >90% hit rate), workspace generation, and comprehensive reporting
majiayu000/claude-skill-registry 163
-
creating-pull-request
majiayu000/claude-skill-registry 163
-
kuznetsov
Создание стратегических аналитических документов в стиле Кузнецова — профессиональное оформление для корпоративных стратегий, правовых меморандумов, финансовых планов и аналитических записок. Документы отличаются строгой структурой, точными формулировками и элегантным минималистичным дизайном. Использовать для создания документов высшего уровня качества для руководства компании, советов директоров, арбитражных трибуналов.
majiayu000/claude-skill-registry 163
-
form-validation
Validates forms using React Hook Form and Zod. Use when creating forms with validation, handling form state, showing error messages, or implementing multi-step forms. Includes schema patterns and Controller usage.
majiayu000/claude-skill-registry 163
-
backlog-update
Reminder to update backlog.org before commits or when finishing significant work. Use before committing changes, after completing implementation from plan mode, or when wrapping up a work session. This skill ensures the project's task tracking in backlog.org stays current with actual progress. Trigger when about to commit, exiting plan mode, or when user says "done", "let's commit", "wrap up", or similar.
majiayu000/claude-skill-registry 163
-
phoenix-thinking
This skill should be used when the user asks to "add a LiveView page", "create a form", "handle real-time updates", "broadcast changes to users", "add a new route", "create an API endpoint", "fix this LiveView bug", "why is mount called twice?", or mentions handle_event, handle_info, handle_params, mount, channels, controllers, components, assigns, sockets, or PubSub. Essential for avoiding duplicate queries in mount.
majiayu000/claude-skill-registry 163
-
budget-advisor
Analyze spending patterns and create personalized budget plans
majiayu000/claude-skill-registry 163
-
Git Investigation
This skill should be used when the user asks to "use git blame", "check git history", "find git commits", "use git log", "use git diff", "use git bisect", "trace code changes", "find who changed this code", or mentions using git commands for investigating code history and changes during root cause analysis.
majiayu000/claude-skill-registry 163
-
gemini-imagegen
This skill should be used when generating and editing images using the Gemini API (Nano Banana Pro). It applies when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.
majiayu000/claude-skill-registry 163
-
implement-plan
Execute approved technical implementation plans with verification checkpoints. This skill should be used when implementing pre-approved development plans, feature implementations, or technical specifications that have defined phases, success criteria, and verification steps. Triggers on requests like "implement the plan", "execute the implementation plan", or when given a path to a plan file.
majiayu000/claude-skill-registry 163
-
voice-interface-builder
Expert in building voice interfaces, speech recognition, and text-to-speech systems
majiayu000/claude-skill-registry 163
-
reactive-programming
Implement reactive programming patterns using RxJS, streams, observables, and backpressure handling. Use when building event-driven UIs, handling async data streams, or managing complex data flows.
majiayu000/claude-skill-registry 163
-
generate-tasks
Convert PRD to structured task list with automatic linking
majiayu000/claude-skill-registry 163
-
flaky-test-detective
Diagnoses and fixes flaky tests by identifying root causes (timing issues, shared state, randomness, network dependencies) and provides stabilization strategies. Use for "flaky tests", "test stability", "intermittent failures", or "test debugging".
majiayu000/claude-skill-registry 163
-
checkpointing-an-iteration
Use when saving current iteration progress mid-conversation, before context compaction, or at interim pause points
majiayu000/claude-skill-registry 163
-
bug-triage-prioritizer
Triage bug reports by severity, recommend fix order, generate client communication templates, determine whether to charge for fixes, and provide Claude Code prompts to resolve issues quickly.
majiayu000/claude-skill-registry 163