Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
view-results
View and analyze Hawk evaluation results. Use when the user wants to see eval-set results, check evaluation status, list samples, view transcripts, or analyze agent behavior from a completed evaluation run.
majiayu000/claude-skill-registry 163
-
agentv-bench
Optimize agents through evaluation-driven iteration. Use when asked to evaluate an agent, optimize prompts against evals, run EVAL.yaml or evals.json evaluations, benchmark agent performance, compare agent outputs across providers, analyze eval results, or improve agent performance. Supports workspace evaluation with real repos, multi-provider targets, multi-turn conversations, code judges, tool trajectory scoring, and workspace file change tracking. Use this skill whenever the user mentions evaluating, benchmarking, testing, or optimizing any agent, prompt, or skill — even if they don't explicitly say "agentv".
majiayu000/claude-skill-registry 163
-
package-upgrade
Use when the user asks to analyze package upgrades, check for outdated dependencies, plan npm/NuGet updates, or assess breaking changes in package updates. Triggers on keywords like "upgrade packages", "outdated", "npm update", "breaking changes", "dependency upgrade", "package update", "version upgrade".
majiayu000/claude-skill-registry 163
-
responsive-system
Use when implementing responsive layouts, mobile-first design, or adaptive components. Covers breakpoints, container queries, fluid typography.
majiayu000/claude-skill-registry 163
-
ralph-init
Initialize a PRD (Product Requirements Document) for structured ralph-loop execution
majiayu000/claude-skill-registry 163
-
spark
Distributed processing framework for large-scale data sets using in-memory computing.
majiayu000/claude-skill-registry 163
-
pix
Launches an autonomous, pixel-perfect UI implementation loop using Figma MCP and Chrome.
majiayu000/claude-skill-registry 163
-
Bytecode VM
Expert skill for bytecode virtual machine design including instruction set design, dispatch mechanisms, and stack/register architectures
majiayu000/claude-skill-registry 163
-
vue-skill
Vue/TypeScriptの実装に関するAgent
majiayu000/claude-skill-registry 163
-
style-standards
Enforces LLM-optimized style compliance for documentation and code. Use when creating/modifying markdown (headers, lists, Dictums, separators), code organization (comments, dividers, naming), or validating voice (grammar, tone, imperative phrasing) and formatting against taxonomy/whitespace standards.
majiayu000/claude-skill-registry 163
-
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates
majiayu000/claude-skill-registry 163
-
merge-main
Use when all feature work is merged to `develop` and the batch is ready to ship to `main`. Handles the full release workflow: NEWS.md update, version bump, develop → main PR, CI monitoring, merge, tagging, and post-release dev version bump. Trigger when the user says "merge to main", "release time", "prepare release", "ship this", "release vX.Y.Z", or "merge develop to main". CRITICAL: This skill only edits NEWS.md and DESCRIPTION. It does NOT write or edit R source files, test files, or any other source code.
majiayu000/claude-skill-registry 163
-
git-protocol
Git protocol implementation patterns using gitoxide for Guts repository operations
majiayu000/claude-skill-registry 163
-
analyzing-nft-rarity
Calculate NFT rarity scores and rank tokens by trait uniqueness.
Use when analyzing NFT collections, checking token rarity, or comparing NFTs.
Trigger with phrases like "check NFT rarity", "analyze collection", "rank tokens", "compare NFTs".
majiayu000/claude-skill-registry 163
-
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
majiayu000/claude-skill-registry 163
-
devops-engineer
Use when setting up CI/CD pipelines, containerizing applications, or managing infrastructure as code. Invoke for pipelines, Docker, Kubernetes, cloud platforms, GitOps.
majiayu000/claude-skill-registry 163
-
react-expert
React development expertise and best practices.
majiayu000/claude-skill-registry 163
-
sys-activating-goals
Creates execution threads for goals using the 6-stage causal flow pattern. Links threads to goals, initializes 1-input.md with goal context, and routes to appropriate agent for execution. Transforms defined goals into actionable work.
majiayu000/claude-skill-registry 163
-
mermaid-chart
Creates Mermaid diagrams (.mmd) and generates PNG images from them. Use when the user wants to create flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts, or any other Mermaid-supported diagram.
majiayu000/claude-skill-registry 163
-
database-testing
Database schema validation, data integrity testing, migration testing, transaction isolation, and query performance. Use when testing data persistence, ensuring referential integrity, or validating database migrations.
majiayu000/claude-skill-registry 163
-
helm-release-troubleshooting
Troubleshoot and fix Helm release issues managed by Terraform. Use when:
(1) Terraform applies successfully but K8s resources don't reflect new Helm values,
(2) New ports/volumes/containers from Helm chart values don't appear in deployed resources,
(3) helm upgrade --reuse-values doesn't re-render templates for structural changes,
(4) Terraform thinks Helm release is up-to-date but actual K8s resources are stale,
(5) terraform apply fails with "another operation (install/upgrade/rollback) is in progress",
(6) helm history shows status "pending-upgrade" or "pending-rollback",
(7) a Helm upgrade was interrupted by network timeout, etcd timeout, or VPN drop,
(8) helm upgrade fails with "an error occurred while finding last successful release".
Covers force re-rendering via state removal/reimport and stuck release recovery via
secret cleanup.
majiayu000/claude-skill-registry 163
-
mermaid-design
majiayu000/claude-skill-registry 163
-
test-catalog-updater
Automates TEST_CATALOG updates after test execution. Records test metrics, pass/fail status, coverage data, and execution time. Maintains single source of truth for all test files and their health status.
majiayu000/claude-skill-registry 163
-
design-system-patterns
Build scalable design systems with design tokens, theming infrastructure, and component architecture patterns. Use when creating design tokens, implementing theme switching, building component libraries, or establishing design system foundations.
majiayu000/claude-skill-registry 163