The library

optimizing-tauri-binary-size · Tauri already produces 3-6MB binaries vs Electron's 120MB—tuning shaves another 30-50% with standard LLVM flags.

reviewer · Distinguishes blocking issues from nits—allows teams to merge without blocking on style when logic is solid.

security · Severity classification separates critical auth issues from style nits—allows teams to merge without blocking on low-severity findings.

claude-skill · Single API handles database, auth, storage, and compute—saves hours of wiring up 4 separate cloud services.

DevOps Engineer · Designs for DORA metrics—deploy frequency, lead time, MTTR, change failure rate—instead of guessing what fast deployment looks like.

docker-development · Multi-stage builds separate build dependencies from runtime—shaves off 60-80% of image size vs single-stage.

parser · Semantic parsing extracts meaning from messy human text—outperforms regex on variants and typos.

nsauditor-ai-agent-skill · Security audits when you need multi-framework compliance evidence and vulnerability matching.

code · Code generation when you need to catch behavioral changes hidden by passing tests.

peekaboo · Headless macOS automation for interacting with native UI elements without public APIs.

email-template-builder · Email marketing when you need behavioral triggers and lifecycle automation across multiple providers.

perl-patterns · Perl projects when modernizing pre-5.36 code to idiomatic v5.36+ standards.

agent-workflow-cli · Multi-step agent coordination when you need session lifecycle and artifact tracking.

perl-testing · Perl testing when you need TDD discipline with Test2::V0 and coverage analysis.

env-secrets-manager · Secrets management when you need environment-specific configuration.

agentuity-cli-cloud-keyvalue-list-namespaces · Cloud infrastructure operations when you need to list available key-value storage namespaces.

php-laravel-core · Laravel applications when you need framework patterns and routing architecture.

agent-transcript · Meeting analytics when you need speaker diarization and structured extraction.

php-laravel-orchestrator · Laravel microservices when you need event-driven orchestration and service coordination.

deepagents-cli-claude-skill · Developers building custom agents with LangChain Deep Agents CLI integration across multiple Claude surfaces.

autoreview · Code review just before commit/ship when you need advisory findings verified against real dependencies.

docs-maintenance · Keeping project documentation fresh after feature completion to reduce AI context usage.

eval · Comparing multiple agent outputs for correctness, simplicity, and quality to pick a winner.

channel-message-flows · Iterating Telegram message UX by testing native draft → final workflows locally.

plan-orchestrate · Turning a PRD or implementation plan into runnable /orchestrate chains without manual agent selection.

clawdtributor · Prioritizing external contributor PRs/issues with maintainer-quality review and live GitHub freshness.

debugging-with-tools · Investigation-heavy debugging when tool-driven evidence (search/logs/diffs) beats guesswork.

plankton-code-quality · Projects needing automatic write-time quality enforcement with defense against agents gaming linter configs.

chrome-jig · Developers debugging JavaScript without DevTools UI or coordinating MCP browser tools with cjig via shared CDP port.

clawsweeper · OpenClaw maintainers automating issue/PR triaging, commit validation, and guarded fix PR creation.

control-ui-e2e · Control UI changes requiring browser routing, app boot, and Gateway handshake verification in one test.

refactor-pass · Cleaning up code after feature work by removing dead code and straightening logic.

postgres-patterns · Writing production PostgreSQL queries and schemas with Supabase best practices for performance and security.

extract · Capturing one-off debugging solutions as reusable skills to avoid re-discovering the same fix.

crabbox · When you need broad OS coverage, CI parity, or secrets validation without local resource constraints.

postgresql · When you need to model a relational schema with correct constraints, performance tuples, and MVCC semantics.

skillfish · When you want a unified skill distribution and versioning system across Claude Code, Cursor, Copilot, and 30+ other agents.

feature-flags-architect · When you need to ship behind a flag, ramp a launch, or clean up flag debt before a release freeze.

gitcrawl · When you need to find duplicate issues, triage PRs, or search GitHub history without live API overhead.

prepare-pr · When you need to draft a PR with proper context, verify CI readiness, and minimize review friction before opening.

prisma-patterns · When you need type-safe database design with Prisma, query optimization, or migration planning.

openclaw-changelog-update · When preparing a release, you need to synthesize commits into user-facing changelog entries.

openclaw-debugging · When OpenClaw behavior differs between local/live and you need to isolate which boundary (config, tool construction, provider payload, fetch, stream) is broken.

fix · When a Playwright test fails intermittently and you need a taxonomy to categorize it (timing/async, test isolation, environment, infrastructure) before applying the right fix pattern.

openclaw-docker-e2e-authoring · When you need to prove OpenClaw behavior crosses a boundary (deterministic for byte/payload routing, live for actual provider behavior).

production-audit · When CI is green but you need to assess actual production risk (auth, data integrity, payments, operations, UX) before launch.

flag-cleanup · When you want to clean up feature flags quarterly and identify which flags are safe to remove based on age and usage patterns.

openclaw-ghsa-maintainer · When you need to patch, validate, and publish a security advisory safely without accidentally publishing escaped newline literals or incomplete data.

focused-fix · When an entire feature or module is broken and you need to trace dependencies, diagnose all issues, and fix systematically rather than guessing at single symptoms.

openclaw-landable-bug-sweep · When you need to autonomously produce five high-confidence bugfix PRs with proof (CI green, autoreview clean, rebased on main).