The library
Everything we index — ranked by what works, never by stars.
forSalesMarketingHRFinanceLegalOpsProductEngineeringDataProductivitySupportsetup≤ plug & play≤ + a key≤ multi-tool
● works · ● untested / no effect · ● hurts — every rank is measured against a no-skill baseline
untested★0→untested★101→untested★1→untested★582→untested★1→untested★0→untested★6→untested★5→untested★5→
Validate features with learner perspectivesubagentProductSupportL1
etudiant-cap · When user testing for a learning app needs honest, persona-grounded feedback from a learner perspective (mobile, stressed, budget-conscious) before shipping.
Review domain methodology rigorsubagentDataProductL1
domain-reviewer · When a refactoring needs systematic validation that the code still compiles, passes tests, and maintains API contracts at scale across a large codebase.
Manage project task hierarchiessubagentOpsProductivityL1
todo-manager · When todos must cross-check against CURRENT state before worktree launch.
Find codebase patterns and examplessubagentEngineeringL1
codebase-pattern-finder · When working code examples beat documentation for learning and copy-paste reuse.
Update project documentationsubagentEngineeringL1
writer · Producing original long-form thought leadership and explainers on emerging topics when subject-matter expertise is available and citations are verifiable.
Review code and flag violationssubagentEngineeringL1
code-inline-reviewer · Validating LLM behavior against strict criteria (structure, safety, cost) that string assertions cannot verify.
Finalize completed taskcommandOpsL1
go · Tu viens de terminer une tâche (feature, bug, maintenance). `/go` est l'étape
Show quick status overviewcommandOpsL1
s · Quick status overview. Keep output compact — one line per item, no tables wider than 50 columns.
Start fancai development sessioncommandEngineeringL1
go · Start development session for fancai
←page 48 / 48