reduce-optional-params
Use when designing or refactoring functions with many optional params, configurable components, or when the user mentions optional params, function signatures,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-13 00:15
Coding & development
40,799 results
crit-story
Author a crit story and continue the interactive review loop only when the user explicitly invokes /crit-story or directly asks you to generate a crit story.…
staff-engineering-skills-cache-invalidation
Prevent stale data bugs caused by missing or incomplete cache invalidation. Use when adding caching layers (Redis, in-memory Map, CDN, HTTP cache headers),…
principles
Core engineering principles. Use as a guiding reference for designing, planning and reviewing.
openspec-brownfield-baseline
Introduce OpenSpec into an existing codebase by deriving baseline specs from current behavior, then switch future work to change-driven development. Use when a…
allocator-migration
Use when migrating Turso core code to crate::alloc, allocator-api2, cfg(nightly) allocator aliases, fallible collection APIs, try_vec!, try_collect, or…
dig
Look up documentation and source code for libraries and packages. Use when the user asks a question about a library, needs to understand a library's API, or…
maintainability-reviewer
Always-on code-review persona. Reviews code for premature abstraction, unnecessary indirection, dead code, coupling between unrelated modules, and naming that…
resolve-pr-parallel
Resolve all PR comments using parallel processing. Use when addressing PR review feedback, resolving review threads, or batch-fixing PR comments.
git-review
Interactive git diff annotation review. Generates a cleaned-up diff, opens in editor for user annotations, and addresses feedback in a loop. Activates on "git…
tilemap-ruletile-createfromsegment
Creates RuleTiles from existing terrain or edge sprites so tiles auto-tile while painting, and converts sprite-segment-3x3grid output patterns into…
plugin-dev
This skill should be used when creating extensions for Claude Code or OpenCode, including plugins, commands, agents, skills, and custom tools. Covers both…
fastapi-auth-patterns
Implement and validate FastAPI authentication strategies including JWT tokens, OAuth2 password flows, OAuth2 scopes for permissions, and Supabase integration.…
ai-coding-agents-release-distribution
Designs release and distribution systems for coding-agent CLIs. Use when modeling packaging, auto-update channels, plugin compatibility, cache migrations, or…
ai-coding-agents-remote-runtime
Designs remote execution and bridge runtimes for coding agents. Use when implementing remote sessions, local-UI remote-execution, reconnect logic, or…
ai-coding-agents-sessions
Designs session lifecycle for coding-agent runtimes. Use when implementing resume, transcript restoration, checkpoint rewind, cross-worktree recovery, or…
spike-skeleton
Construct and verify a minimal end-to-end walking skeleton across distributed modules or bounded contexts to prove architectural integration before detailed…
vgv-create-project
Scaffold a new Dart or Flutter project from a Very Good CLI template. Supports flutter_app, dart_package, flutter_package, flutter_plugin, dart_cli,…
audit-claude-settings
Use when auditing Claude Code settings and env vars against the latest docs to suggest tailored changes
refactor-claude-md
Use when about to refactor or refine a user-level or project-level CLAUDE.md
prisma_orm
Prisma ORM patterns including Prisma Client usage, queries, mutations, relations, transactions, and schema management. Use when working with Prisma database…
opencode-cli
Reference for using OpenCode CLI to handle complex coding tasks. Use when Research-Claw needs to delegate multi-file projects, code generation, or iterative…
wechat-miniprogram
Implement and verify WeChat Mini Program and Mini Game work: locate source and config, compile, preview and upload, automate pages and canvas, read…
wkc-implement
Take one ticket from ready to an open pull request with its acceptance checks run and the ticket at in-review, and after a person merges it, run the ticket's…