Discover skills
Discover and install skills to enhance your AI agent's capabilities.
| Name | Contains | Score |
|---|---|---|
docker-sandbox joelhooks/joelclaw Create, manage, and execute agent tools (claude, codex) inside Docker sandboxes for isolated code execution. Use when running agent loops, spawning tool subprocesses, or any task requiring process isolation. Triggers on "sandbox", "isolated execution", "docker sandbox", "safe agent execution", or when working on agent loop infrastructure. | Skills | 92 3.22x Agent success vs baseline Impact 100% 3.22xAverage score across 3 eval scenarios Securityby  Risky Do not use without reviewing Reviewed: Version: 0.0.1 |
rei openclaw/skills Set up Rei Qwen3 Coder as a model provider. Use when configuring coder.reilabs.org, adding Rei to Clawdbot, or troubleshooting 403 errors from Rei endpoints. | Skills | 92 1.66x Agent success vs baseline Impact 100% 1.66xAverage score across 3 eval scenarios Securityby Risky Do not use without reviewing Reviewed: Version: 0.0.1 |
model-usage qsimeon/openclaw-engaging Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON. | Skills | 92 3.70x Agent success vs baseline Impact 100% 3.70xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
model-usage attilaczudor/Test Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON. | Skills | 92 3.70x Agent success vs baseline Impact 100% 3.70xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
model-usage Hung-Reo/hungreo-openclaw Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON. | Skills | 92 3.70x Agent success vs baseline Impact 100% 3.70xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
caching-strategies fernandezbaptiste/rails_ai_agents Implements Rails caching patterns for performance optimization. Use when adding fragment caching, Russian doll caching, low-level caching, cache invalidation, or when user mentions caching, performance, cache keys, or memoization. | Skills | 92 1.09x Agent success vs baseline Impact 100% 1.09xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
clang-format Jamie-BitFlight/claude_skills Configure clang-format code formatting. Use when: user mentions clang-format or .clang-format, analyzing code style/patterns, creating/modifying formatting config, troubleshooting formatting, brace styles/indentation/spacing/alignment/pointer alignment, or codifying conventions. | Skills | 92 1.13x Agent success vs baseline Impact 100% 1.13xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
agent-pr-creator ravnhq/ai-toolkit Analyzes git diffs and commit history to intelligently fill PR templates and create pull requests via gh CLI. Use when: creating a PR, needing PR description help, saying 'create a pull request', 'fill PR template', 'make a PR', 'open a pull request'. Triggers on: create PR, open pull request, make a PR, fill template. | Skills | — |
project-setup dwmkerr/claude-toolkit Create a new GitHub project with standard configuration. Use when user asks to "create a project", "set up a new repo", "initialize a repository", or wants to start a new GitHub project. | Skills | 92 1.75x Agent success vs baseline Impact 100% 1.75xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
rei Demerzels-lab/elsamultiskillagent Set up Rei Qwen3 Coder as a model provider. Use when configuring coder.reilabs.org, adding Rei to Clawdbot, or troubleshooting 403 errors from Rei endpoints. | Skills | 92 1.66x Agent success vs baseline Impact 100% 1.66xAverage score across 3 eval scenarios Securityby Risky Do not use without reviewing Reviewed: Version: 0.0.1 |
ddd-quarkus jeremyrdavis/claude-skill-quarkus-ddd Scaffold and generate Domain-Driven Design components with Hexagonal Architecture in Quarkus projects. Use this skill whenever the user wants to create a new bounded context, add an aggregate, create value objects, scaffold a DDD module, add a new subdomain, or generate any DDD tactical pattern (aggregate, entity, value object, command, event, repository, service, endpoint) in a Quarkus/Java project. Also trigger when the user mentions 'hexagonal architecture', 'ports and adapters', or asks to add a new feature following DDD patterns. | Skills | 92 1.49x Agent success vs baseline Impact 100% 1.49xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
Break down goals into multiple tasks and coordinate execution with gates and recovery. Based on Claw Code's agentic harness. Contains: planning-execution-harness Use when you need to ask before executing, don't run without permission, review steps before proceeding, or confirm before executing. An LLM breaks down goals into tasks, presents the plan for approval, then executes only if approved. Enforces a mandatory approval gate that blocks all execution. Separates planning from execution so no action runs without prior sign-off. Classifies failures by type and applies type-specific recovery strategies. Produces a timestamped event log of every state change. Applies to: step-by-step workflows with approval, irreversible or risky operations, human-in-the-loop execution, agentic pipelines with intelligent failure recovery. | Skills | 92 1.09x Agent success vs baseline Impact 100% 1.09xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.7.6 |
agent-framework-azure-ai-py boisenoise/skills-collections Build persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK. | Skills | 92 100.00x Agent success vs baseline Impact 100% 100.00xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.0.1 |
action-cable-patterns fernandezbaptiste/rails_ai_agents Implements real-time features with Action Cable and WebSockets. Use when adding live updates, chat features, notifications, real-time dashboards, or when user mentions Action Cable, WebSockets, channels, or real-time. | Skills | 92 1.35x Agent success vs baseline Impact 100% 1.35xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.0.1 |
firstrun redongreen/uSpec First-time setup for uSpec. Prompts for MCP provider and environment (Cursor, Claude Code, Codex), syncs skills to the chosen platform, then configures your Figma template library. Use when the user mentions "firstrun", "first run", "setup", "setup library", "configure templates", or "link templates". | Skills | 92 1.88x Agent success vs baseline Impact 100% 1.88xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.0.1 |
firstrun redongreen/uSpec First-time setup for uSpec. Prompts for MCP provider and environment (Cursor, Claude Code, Codex), syncs skills to the chosen platform, then configures your Figma template library. Use when the user mentions "firstrun", "first run", "setup", "setup library", "configure templates", or "link templates". | Skills | 92 1.88x Agent success vs baseline Impact 100% 1.88xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.0.1 |
firstrun redongreen/uSpec First-time setup for uSpec. Prompts for MCP provider and environment (Cursor, Claude Code, Codex), syncs skills to the chosen platform, then configures your Figma template library. Use when the user mentions "firstrun", "first run", "setup", "setup library", "configure templates", or "link templates". | Skills | 92 1.88x Agent success vs baseline Impact 100% 1.88xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.0.1 |
java-test-updater ArabelaTso/Skills-4-SE Update Java test classes and methods to work with new code versions after refactoring or modifications. Use when code changes break existing tests due to signature changes, refactoring, or behavior modifications. Takes old and new code versions plus old tests as input, and outputs updated tests that compile and pass against the new code. Handles method signature changes, class refactoring, assertion updates, and mock modifications. | Skills | 92 1.00x No change in agent success vs baseline Impact 100% 1.00xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
error-explanation-generator ArabelaTso/Skills-4-SE Explains test failures and provides actionable debugging guidance. Use when tests fail (unit, integration, E2E), builds fail, or code throws errors. Analyzes error messages, stack traces, and test output to identify root causes and suggest concrete fixes. Handles pytest, jest, junit, mocha, vitest, selenium, cypress, playwright, and other testing frameworks across Python, JavaScript/TypeScript, Java, Go, and other languages. | Skills | 92 1.25x Agent success vs baseline Impact 88% 1.25xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
shopify-webhooks hookdeck/webhook-skills Receive and verify Shopify webhooks. Use when setting up Shopify webhook handlers, debugging signature verification, or handling store events like orders/create, products/update, or customers/create. | Skills | 92 1.35x Agent success vs baseline Impact 100% 1.35xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.0.1 |
Can't find what you're looking for? Evaluate a missing skill.