The library

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

untested
Implement projection mapping toolsubagentEngineeringL2
interactive-projection-tool-builder · Implement in isolation so multiple builders can work in parallel without conflicts
untested
Update roadmap and release notessubagentEngineeringL1
roadmap-docs-editor · Keep public release wording honest and match verified shipped state
untested
Design submission architecturesubagentEngineeringL2
submission-architect · Avoid directory rejection by mapping every form field to a source before builders start
untested
Design feature specs and wireframessubagentEngineeringL1
td-architect · Turn a vague idea into a spec multiple builders can implement in parallel
untested
Survey tdmcp feature opportunitiessubagentEngineeringL2
td-surveyor · Find gaps on one surface without cross-contaminating scope with other surveyors
untested
Synthesize tdmcp feature backlogsubagentEngineeringL2
td-synthesizer · Find gaps on one surface without cross-contaminating scope with other surveyors
untested
Verify tdmcp coverage improvementssubagentEngineeringL2
tdmcp-coverage-qa · after coverage writers finish
untested
Write focused tdmcp unit testssubagentEngineeringL2
tdmcp-coverage-writer · inside a coverage wave after tdmcp-coverage-lead assigns a specific seam
untested
Build individual tdmcp toolssubagentEngineeringL2
tdmcp-tool-builder · for implementing a single new tdmcp tool to a precise spec
untested
Identify and prioritize dead codesubagentEngineeringL2
drastic-paladin · this skill for deletion/governance passes over dead code, residue, and stale surfaces
untested
Debug MCP Bridge configuration issuessubagentEngineeringL2
mcp-bridge-expert · the mcp-bridge-expert agent to help diagnose this connection issue
untested
Keep LLM pricing data currentsubagentEngineeringL2
pricing-updater · this agent to update LLM pricing data in the default-pricing
untested
Test and validate LLM providerssubagentEngineeringL2
provider-tester · this agent when you need to test, debug, or validate LLM provider configurations
untested
Review MCP tool implementationssubagentEngineeringL2
tool-reviewer · this agent when you need to review MCP tool implementations for correctness, adherence to patterns, and best practices
untested
Write deterministic playwright testssubagentEngineeringL2
qa · is almost always a single shared issue
untested
Build Lua and Neovim pluginssubagentEngineeringL2
lua · for ANY task involving lua/kubectl/, Neovim API, resource views, keybindings, or plugin code
untested
Open dataset onboarding pull requestssubagentEngineeringL2
pr · When you need pr functionality for your workflow
untested
Drive Elixir features through testssubagentEngineeringL2
tdd · when driving new context functions, LiveViews, or Oban workers through tests
untested
Refresh and compress memory filessubagentL1
mb · only Claude Code tools allowed by this subagent frontmatter
untested
Build and manage CLI commandssubagentEngineeringL2
cli · `commander` for CLI framework — no custom arg parsing
untested
Create test plans and validate featuressubagentEngineeringProductL2
qa · hen convenient |
untested
Run automated regression testssubagentEngineeringProductL2
qc · the `find` Chrome MCP tool to locate elements by:
untested
Manage GitHub workflows and PR reviewssubagentEngineeringL2
gh · GitHub workflows that need exact gh invocations with --json scripting over GUI interactions.
untested
Manage backlog and acceptance criteriasubagentProductEngineeringL2
product-owner · Agile teams that need rigorous backlog discipline with testable acceptance criteria and epic-to-task traceability.
untested
Extract and process PDF documentssubagentOpsEngineeringL2
pdf · Document processing pipelines that need both text-based and image-based PDF content extraction with confidence scoring.
untested
Validate and safely push codesubagentEngineeringL2
git · Safety gates that prevent commits until preconditions (test pass, scope complete) are verified.
untested
Align engineering with product roadmapsubagentProductEngineeringL2
tpo · Multi-service systems where a single change spans repos and requires coordinated rollout with rollback safety.
untested
Build React components and UI featuressubagentEngineeringProductL2
web · Frontend teams that enforce strict TypeScript and reuse Shadcn/Radix components with React Hook Form validation.
untested
Optimize game factory layouts and recipessubagentL1
ada · Satisfactory factory planning that needs exact recipes, ratios, and bottleneck analysis with current game state verification.
untested
Build Laravel backend componentssubagentEngineeringL2
L · Thai/multi-language Laravel teams that follow strict MVC patterns with Eloquent, Vanilla JS, and audit trails.
untested
Design and audit UI componentssubagentProductEngineeringL2
ui · Mobile UI teams building KMP apps with consistent Material3 design across Android/iOS.
untested
Document architectural decisionssubagentEngineeringL2
adr · Teams that need to track architectural decisions over time for onboarding, audits, and reversing decisions later.
untested
Run format, test, and build checkssubagentEngineeringL2
ci · Teams automating build, test, and deployment with matrix testing and multi-environment promotion gates.
untested
Design clean, scannable interfacessubagentProductEngineeringL2
ux · Digital products that prioritize user research and design validation before engineering investment.
untested
Review WPF/.NET code and defectssubagentEngineeringL2
QA Engineer · Quality gates that prevent regressions through comprehensive test coverage and automated validation.
untested
Build SQLite schemas and migrationssubagentEngineeringL2
db · Data-intensive applications that need optimal schema design and query tuning from first principles.
untested
Define testable system behaviorsubagentEngineeringProductL1
QA · Quality assurance that validates features meet acceptance criteria before production release.
untested
Design and write database schemasubagentEngineeringL1
dba · When data layer must be explicit and performant before backend implements repositories.
untested
Analyze unit economics and marginssubagentFinanceL1
The CFO · Reality-checking startup assumptions when the board needs to hear if numbers actually work.
untested
Evaluate technology and hosting choicessubagentEngineeringL1
cto · Making infrastructure or agent-backbone choices with cross-cutting impact across teams.
untested
Build RAG and knowledge systemssubagentEngineeringL1
rag · Building semantic search over regulatory documents (Verordnungen) when 700-word chunks matter.
untested
Optimize database schema and queriessubagentEngineeringL1
dba · Building semantic search over regulatory documents (Verordnungen) when 700-word chunks matter.
untested
Manage projects and dispatch worksubagentOpsL1
pam · Front-door assistant when requests mix personal advice, capture, and project execution.
untested
Generate SEO tags and structured datasubagentMarketingL1
seo · Improving search ranking when structured data and crawlability are critical.
untested
Write production Python codesubagentEngineeringL1
sde · Staff-level coding when production discipline and maintainability matter over speed.
untested
Investigate PR history and repository statesubagentEngineeringL1
gitnexus-pr-facts-historian · Understanding PR scope before review when changed files, commits, and regressions matter.
untested
Conduct authorized security penetration testssubagentEngineeringL2
penetration-tester · Demonstrating real security risk when authorized exploitation and impact assessment needed.
untested
Guide architecture and codebase decisionssubagentEngineeringL1
edgartools-architect · Planning major EdgarTools changes when beginner-friendly simplicity must survive refactor.
untested
Onboard models to qai_hub_modelssubagentEngineeringL2
onboarding · Integrating edge models when monkeypatching and compilation workarounds need expert guidance.
untested
Solve CTF and hacking challengessubagentEngineeringL2
ctf-solver · Solving web/pwn/crypto CTFs when systematic methodology beats guessing.
page 112 / 121