The library

unity-yaml-format · Diagnosing broken prefab references and resolving merge conflicts in serialized Unity scenes

assemblyai · Transcribing meetings or podcasts and extracting structured insights without round-tripping external LLMs

tailwind-config-generator · Setting up Tailwind in a new project with custom design system without manual config

rust-design-review · Comprehensive design review of library APIs or critical paths where idiomatic Rust matters

create-ai-project · Rapidly spinning up multi-agent TypeScript projects with context engineering baked in

sanitizing-inputs-zod · Server-side input hardening for form submissions before database mutation

aaaudit · Vicious pre-commit review of high-stakes specs to catch cross-vendor blind spots

orc · Shipping complex multi-file changes with parallel Sonnet workers and automated integration/deploy

cli · Upfront project planning to identify critical path and parallelize work

rev · Objective third-look validation of worker PRs before merge by separate grader

spec-handover · Discovering debt and dead code before a major refactor

think · Upfront API contract definition with integrated validation to prevent shape mismatches

verification-loop · Safely provisioning cloud resources with dry-run validation before apply

synckit · Quickly spinning up responsive layouts that work across desktop, tablet, mobile

Cartographer Reference Lookup · Tracking spending across parallel agentic runs to catch token leaks

pr-shepherd · Pre-commit linting to enforce team style without manual review friction

agentic-engineering · making skills more autonomous, concise, verifiable, long

agentuity-cli-profile-create · When you need specialized skill for agentuity-cli-profile-create instead of generic alternatives.

agentuity-cli-cloud-eval-list · Agentuity cloud platform operations

context-manager · approaching context limits or optimizing prompt costs

cli · When you need specialized skill for cli instead of generic alternatives.

fix · you have lint errors, formatting issues, or before committing code to ensure it passes CI

codex · operating Codex CLI itself (config, profiles, sandbox, approvals, and safe usage patterns)

harness-engineering · deploying agents to production or designing multi

dart-build · When you need specialized skill for dart-build instead of generic alternatives.

plugin-claude-code · When you need specialized skill for plugin-claude-code instead of generic alternatives.

verify-before-claim · When about to claim work is done and need fresh proof before saying so.

bedrock-sdk · When you need to use Claude API through AWS Bedrock infrastructure.

jomonsho-incident-triage · For structured jomonsho incident triage workflows.

react-native-share · For structured react native share workflows.

refactoring-08-experiment-tracking · For structured refactoring 08 experiment tracking workflows.

contract-driven-delivery · When non-engineers need AI implementation with spec authority and quality gates across brownfield systems.

opsx-workflow · When setting up a frontend project that needs AI-driven TDD, OpenSpec specs, and automated delivery gates.

docker-compose-dev · When you need a reproducible local dev environment with one command, no external DB.

validate · When you need a single pre-commit quality check across all CI lanes without stopping on first failure.

developer-mcp · See body for use case.

i18next-cli · See body for use case.

localization-manager · See body for use case.

type_checker · Researchers validating GNN model schemas and auto-generating comparison cards with FLOPS.

llm-context · Teams or operators requiring llm-context for skill-level automation.

implementing-code · Teams or operators requiring implementing-code for skill-level automation.

dev-workflow · Teams shipping code with strict quality gates, test-first discipline, and audit trails.

claude-code · Teams or operators requiring claude-code for skill-level automation.

building-project · Teams or operators requiring building-project for skill-level automation.

agent-workflow · Teams running collaborative AI agent sessions with persistent context and quality gates.

githits · Teams or operators requiring githits for skill-level automation.

doccraft-adr · Teams or operators requiring doccraft-adr for skill-level automation.

electronic · When Prepare CP2K electronic-analysis task inputs from prior converged context. Use when the user requests post-ground-state electronic analyses and needs prerequisite-aware setup

camera-shake · When Shake the camera when the player takes damage or on impacts for visual feedback

openspec-apply-change · When Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks