测试
单元测试、集成测试与测试自动化
codebase-migrate
ComposioHQ
Run large codebase migrations and multi-file refactors. Uses the Composio CLI to coordinate issue tracking, batched PRs, and CI verification while the agent executes the transforms locally across hundreds of files.
production-deployment
vanman2024
Production deployment patterns for ElevenLabs API including rate limiting, error handling, monitoring, and testing. Use when deploying to production, implementing rate limiting, setting up monitoring, handling errors, testing concurrency, or when user mentions production deployment, rate limits, error handling, monitoring, ElevenLabs production.
solana-sdk-zig
zigcc
This skill provides Solana SDK development guidance for Zig implementations. It ensures correct Rust source references, proper crate-to-module mapping, and test compatibility. Essential for writing Zig code that implements Solana SDK functionality, adding Rust source references, and creating integration tests.
crash-investigation
eltmon
Investigate system crashes, OOM kills, and unresponsive episodes. Analyzes previous boot logs, identifies memory hogs, tallies per-process-group consumption, checks agent and workspace state, and produces a recovery summary. Use after a hard reset, freeze, or reboot caused by resource exhaustion.
knowledge-capture
eltmon
AI self-monitoring skill. Triggers proactively when AI detects confusion or makes corrected mistakes (wrong DB schema, incorrect assumptions, user corrections on key insights). Prompts to capture learnings as project-specific skills. NOT user-invoked - AI should reference this when confused.
git-workflow
JetBrains
IdeaVim git workflow conventions covering commits, branches, PRs, and CI. Use when creating commits, managing branches, creating pull requests, reviewing git history, or any git-related activity in the IdeaVim project.
codebase-design
eltmon
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
pan-done
eltmon
"pan done <id> — mark work complete and signal the review pipeline"
pan-test-config
eltmon
Configure test suites for Overdeck projects in projects.yaml.
pan-new-project
eltmon
Complete setup for registering a new project with Overdeck. Handles project registration, issue prefix, workspace config, trust setup, xBRIEF task support init, tracker config, and validates against working projects. Three entry points: CLI (pan project clone/add/new), dashboard (/projects/new), and workspace-page chips for quick registration.
dependency-update
eltmon
Safe approach to updating dependencies
mutant
mbj
Run mutant, read mutation reports, fix alive mutations, and verify coverage. Use when running mutation testing or responding to alive mutations.
web3-protocol-gtm
tenequm
Go-to-market strategy for web3 builders - protocols, products, services, and solo founders. Use when planning growth for a crypto protocol, product, or service, building developer community, crafting CT narrative, planning ecosystem partnerships, preparing grant applications, measuring protocol traction, sequencing testnet to mainnet launch, launching tokens, pricing crypto-native products, optimizing landing page conversion, selling to AI agents, or growing as a solo founder in web3. Covers community-led growth, Crypto Twitter strategy, developer relations, hackathon playbooks, ecosystem composability, standards adoption, protocol metrics, solo founder GTM, token launch tactics, CT growth for small accounts, dual-rail payments, micropayment pricing, embedded wallet UX, and agent-as-customer models. Triggers on web3 GTM, protocol marketing, crypto growth, developer relations, community building, CT narrative, ecosystem partnerships, standards adoption, protocol launch, grant application, hackathon strategy, solo founder, token launch, pump.fun, building in public, CT growth, reply strategy, crypto SaaS, product launch, micropayment pricing, landing page conversion, x402 pricing, agent customers.
foundry-solidity
tenequm
Build and test Solidity smart contracts with Foundry toolkit. Use when developing Ethereum contracts, writing Forge tests, deploying with scripts, or debugging with Cast/Anvil. Triggers on Foundry commands (forge, cast, anvil), Solidity testing, smart contract development, or files like foundry.toml, .t.sol, .s.sol.
discover
AsiaOstrich
"[UDS] Assess project health, architecture, and risks before adding features"
skill-factory
tenequm
Autonomous skill creation agent that analyzes requests, automatically selects the best creation method (documentation scraping via Skill_Seekers, manual TDD construction, or hybrid), ensures quality compliance with Anthropic best practices, and delivers production-ready skills without requiring user decision-making or navigation
notion-spec-to-implementation
ComposioHQ
Turn Notion specs into implementation plans, tasks, and progress tracking; use when implementing PRDs/feature specs and creating Notion plans + tasks from them.
monorepo-ci-optimizer
patricio0312rev
Optimizes CI pipelines for monorepos by detecting affected packages/apps and running only necessary builds and tests. Includes Turborepo/Nx strategies, caching, and parallel execution. Use for "monorepo CI", "affected detection", "incremental builds", or "workspace optimization".
kubernetes-manifest-generator
patricio0312rev
Generates Kubernetes manifests including Deployments, Services, ConfigMaps, Secrets, Ingress, and HPA with best practices. Use when users request "Kubernetes setup", "K8s manifests", "deploy to Kubernetes", "container orchestration", or "K8s configuration".
prompt-regression-tester
patricio0312rev
Compares old vs new prompts across test cases with diff summaries, stability metrics, breakage analysis, and fix suggestions. Use for "prompt testing", "A/B testing prompts", "prompt versioning", or "quality regression".
create-plan
ComposioHQ
Create a concise plan. Use when a user explicitly asks for a plan related to a coding task.
repo-source-code-review
open-circle
Review pull requests and source code changes in /library/src/. Use when reviewing PRs, validating implementation patterns, or checking code quality before merging. Covers code quality checks, type safety, documentation review, test coverage, and common issues to watch for.
testing-laravel
iliaal
Writes and reviews Laravel tests using PHPUnit. Use when "write tests", "add tests", "review tests", "check tests", "phpunit", "laravel test", "feature test", "unit test", "mock", "factory", or testing/reviewing controllers, models, services, actions, jobs, artisan commands, or API endpoints.
terraform
iliaal
Terraform and OpenTofu configuration, modules, testing, state management, and HCL review. Use for "terraform module", "terraform test", "infrastructure as code", "IaC", "HCL", "tfvars", "terraform plan", "terraform apply", "OpenTofu", "tftest", or multi-environment patterns.