The library

Everything we index — ranked by what works, never by stars.

untested
Build frontend with Vite and LeafletsubagentEngineeringL3
frontend-engineer · Building production Node.js backends with proper query optimization, transaction handling, authorization checks, and comprehensive error responses that match frontend API contracts.
untested
Develop ESP32 firmware with ZigbeesubagentEngineeringL3
firmware-engineer · Implementing resource-constrained embedded code with deterministic timing, memory safety, and robust error recovery for hardware control and sensor integration.
untested
Audit code for security vulnerabilitiessubagentEngineeringL2
security · Auditing code for authorization, RLS, and authentication vulnerabilities before launch.
untested
Detect accessibility patterns across pagessubagentEngineeringL2
cross-page-analyzer · Computing accessibility severity scores and cross-page patterns faster than manual auditing.
untested
Evaluate AI behavior with LLM evalssubagentEngineeringL2
ai-eval-engineer · Validating LLM behavior against strict criteria (structure, safety, cost) that string assertions cannot verify.
untested
Design system architecture and decisionssubagentEngineeringL2
architect · Auditing code for authorization, RLS, and authentication vulnerabilities before launch.
untested
Review code and flag violationssubagentEngineeringL1
code-inline-reviewer · Validating LLM behavior against strict criteria (structure, safety, cost) that string assertions cannot verify.
untested
Resolve build and type errorssubagentEngineeringL2
build-error-resolver · Auditing code for authorization, RLS, and authentication vulnerabilities before launch.
untested
Document technical architecture decisionssubagentEngineeringL2
adr-author · Auditing code for authorization, RLS, and authentication vulnerabilities before launch.
untested
Refactor code without changing behaviorsubagentEngineeringL2
refactorer · Improving code design while guaranteeing behavior preservation through automated validation.
untested
Validate high-risk planssubagentEngineeringL2
emma-frost · Flagging specific coding-standard violations with inline docs links at scale.
untested
Persist context across sessionspluginEngineeringL3
claude-mem · Handling specialized tasks that generic agents cannot perform.
untested
Automate Firefox testing and scrapingpluginEngineeringL2
firefox-devtools · Handling specialized tasks that generic agents cannot perform.
untested
Debug iOS Safari with WebKit InspectorpluginEngineeringL2
iwdp-mcp · Handling specialized tasks that generic agents cannot perform.
untested
Browse pages at 97% fewer tokenspluginEngineeringL2
pagemap · Browsing high-token pages (PDFs, documentation, dense paywalls) where 97% compression outweighs loss of formatting.
untested
Build and deploy full-stack apps to Tencent CloudBasepluginEngineeringL3
cloudbase-ai-toolkit · Tencent-native development where CloudBase platform provides cost-effective Alibaba-competitive serverless infrastructure for China-market apps.
untested
Deploy React/Vite web apps on Tencent CloudBasepluginEngineeringL2
cloudbase-sites · Two-stage save→deploy workflow for iterative React/Vite front-end development on CloudBase, inspired by Codex Sites pattern.
untested
Access Tencent CloudBase models, auth, and backend servicespluginEngineeringL2
cloudbase · Tencent stack full-stack apps needing unified auth, NoSQL+SQL, blob storage, serverless, and WeChat Mini Program integration.
untested
Run plan-execute-validate loops with parallel work and memorypluginOpsEngineeringL2
forge · Multi-file refactors, full-stack features, or spec-driven work where parallel validation and retry beat sequential manual oversight.
untested
Execute terminal commands and manage files across formatspluginEngineeringOpsL2
desktop-commander · Local-only automation across text, code, PDFs, spreadsheets where client-side execution avoids cloud egress and latency.
untested
Run interactive shell, SSH, and serial sessions for agentspluginEngineeringOpsL3
pty-mcp · Long-lived interactive debugging, DevOps orchestration, or system administration where persistent PTY state beats stateless shell commands.
untested
Analyze delivery metrics, hiring funnel, team structurepluginEngineeringOpsL2
vpe-advisor · VP of Engineering or Director of Eng optimizing delivery throughput (DORA), hiring funnel conversion, and org structure when execution velocity stalls.
untested
Access 32 production-ready engineering and security skillspluginEngineeringL2
engineering-skills · When shipping production-grade code requires discipline across architecture, testing, deployment, and security domains rather than isolated linting.
untested
Audit and fix WCAG 2.2 accessibility violations in frontendpluginEngineeringProductL2
a11y-audit · When shipping accessible UI requires automated detection of common WCAG violations before manual testing.
untested
Generate, fix, and run production Playwright testspluginEngineeringL2
pw · When shipping e2e tests across multiple browsers and platforms requires templates, flaky-failure fixes, and reporter integrations rather than starting from scratch.
untested
Build Snowflake pipelines and SQL queriespluginEngineeringDataL2
snowflake-development · When building production data pipelines in Snowflake requires serverless compute, AI-native SQL functions, and dbt workflow management.
untested
Master 40 advanced engineering disciplinespluginEngineeringL2
engineering-advanced-skills · When shipping complex agent systems requires principled design across agent logic, retrieval, data layers, operations, and pre-production compliance gates.
untested
Spawn parallel agents to solve problemspluginEngineeringProductL2
agenthub · When a problem benefits from diverse solution approaches and time permits parallel exploration with an objective win criterion.
untested
Automatically optimize files by metricspluginEngineeringProductL2
autoresearch-agent · When optimizing a single file's performance, quality, or cost over time requires hands-off autonomous loops with clear metric tracking.
untested
Design and audit chaos experimentspluginEngineeringOpsL2
chaos-engineering · When improving system resilience requires controlled failure injection with documented hypothesis and error-budget impact, not guesswork.
untested
Create guided code walkthroughspluginEngineeringProductL2
code-tour · When onboarding developers or explaining architecture requires guided walkthroughs tailored to reader expertise level rather than generic comments.
untested
Build optimized Docker containerspluginEngineeringOpsL2
docker-development · When production containers require optimized build time, minimal image size, and security hardening rather than default Docker patterns.
untested
Architect and manage feature flagspluginProductEngineeringL2
feature-flags-architect · When shipping features requires disciplined flag management with rollout rings, stale-flag cleanup, and audit trails rather than ad-hoc toggles.
untested
Grill plans against recorded decisionspluginProductEngineeringL2
grill-with-docs · Crystallizing terminology and architectural decisions incrementally as a plan develops, preserving them in version-controlled docs instead of tribal knowledge
untested
Build Kubernetes Helm chartspluginEngineeringOpsL2
helm-chart-builder · Accelerating Helm chart authoring by enforcing dependency management, security patterns, and testing discipline from the start
untested
Enforce Karpathy active coding rulespluginEngineeringL2
karpathy-coder · Catching unsafe abstractions and unfocused changes before code review by surfacing assumptions, complexity drift, and vague goals
untested
Design Kubernetes OperatorspluginEngineeringOpsL2
kubernetes-operator · Building production Operators by enforcing the Operator pattern disciplines (CRD design, reconcile loops, idempotency, error handling) rather than generic Kubernetes knowledge
untested
Version and test production promptspluginProductEngineeringL3
prompt-governance · Managing prompt changes in production by preventing silent quality regressions and running structured experiments before rollout
untested
Catch security anti-patterns before deploypluginEngineeringL2
security-guidance · Preventing command injection, XSS, SQL injection, unsafe deserialization, code injection, and GitHub Actions workflow injection at the moment of writing, before code reaches review
untested
Design SLOs and error budgetspluginOpsEngineeringL2
slo-architect · Structuring service reliability goals with defensible error budgets instead of ad-hoc alerting or targets disconnected from business risk
untested
Design and manage Terraform infrastructure at scalepluginEngineeringOpsL4
terraform-patterns · Structuring Terraform projects with reproducible module layouts, multi-environment state management, and policy enforcement instead of ad-hoc scripts
untested
Extract data from any website intelligentlypluginDataEngineeringL2
universal-scraping-architect · Scraping web content with automatic fallback to local extraction when Firecrawl quota is low, avoiding token blowouts on large batch jobs
untested
Build multi-agent workflow automation scriptspluginEngineeringOpsL3
workflow-builder · Structuring multi-agent work by proposing proven orchestration topologies upfront instead of requiring users to architect their own workflows
untested
Author and publish agent skills quicklypluginEngineeringL2
write-a-skill · Creating high-quality, reusable skills with consistent structure and documentation instead of ad-hoc prompt files or private scripts
untested
Convert Markdown into interactive HTML instantlypluginMarketingEngineeringL2
markdown-html-skills · Publishing markdown documents (code reviews, long-form guides, slide decks, presentations) as shareable, visually polished single-file HTML instead of raw markdown or PDF
untested
Design apps compliant with Apple HIG standardspluginProductEngineeringL2
apple-hig-expert · iOS/macOS teams shipping premium apps when HIG compliance + accessibility + 2026 Liquid Glass aesthetic are critical brand signals.
untested
Monitor Claude Code spend per projectpluginFinanceEngineeringL3
budgetclaw · Teams running Claude Code agents on metered LLM budgets who need hard spend guardrails with immediate notification of overages.
untested
Verify and audit Claude Code operationspluginEngineeringOpsL3
claude-code-audit-stack · Cloud automation teams that deploy daemons via Claude Code and need adversarial verification that restarts actually succeeded (not just reported success).
untested
Display Claude Code activity in real-timepluginEngineeringProductivityL2
claude-hud · Claude Code operators who want immediate visual feedback on token consumption and tool execution without context-switching to inspect dialogs.
untested
Export and sync Claude Code across machinespluginEngineeringOpsL2
claude-snapshot · Teams that onboard developers frequently and want to replicate a standardized Claude Code config across machines without manual setup.
page 85 / 86