The library
Everything we index — ranked by what works, never by stars.
forSalesMarketingHRFinanceLegalOpsProductEngineeringDataProductivitySupportsetup≤ plug & play≤ + a key≤ multi-tool
WORKS 59★128WORKS 53★135WORKS 55★10WORKS 59★0WORKS 59★0WORKS 54★0WORKS 54★0WORKS 57★0WORKS 55★0WORKS 59★5,331WORKS 58★14WORKS 55★1WORKS 57★1WORKS 55★1WORKS 60★1WORKS 57★41,861WORKS 58★11,239WORKS 59★11,239WORKS 58★548WORKS 58★1,242WORKS 58★1,242WORKS 58★0WORKS 58★11,239WORKS 56★4,337WORKS 60★0WORKS 59★32WORKS 54★4WORKS 53★14WORKS 59★0WORKS 58★0WORKS 55★0WORKS 55★0WORKS 55★0WORKS 59★0WORKS 55★0WORKS 57★0WORKS 54★0WORKS 57★0WORKS 54★72WORKS 57★2WORKS 54★0WORKS 53★20WORKS 57★1WORKS 58★1WORKS 55★2WORKS 57★11,239WORKS 56★1,242WORKS 56★18WORKS 59★51WORKS 53★29
Measure page speed with real-user dataskillMarketingProductL2
seo-performance · Diagnose page speed issues with real-user field data
Generate competitive intelligence and battle cardsskillProductL3
sk-competitors · Early-stage founders completing Startup Kit Phase 3 to map competitive landscape and validate market opportunity before detailed GTM planning.
Conduct deep research with verified sourcesworkflowProductOpsL3
deep_research · Multi-source research with synthesis and adversarial fact-checking.
Run weekly site health check reportworkflowOpsProductL3
weekly-checkin · Unattended weekly health checks (GSC, deploy, links, schema, CWV).
Evaluate neurospatial API design comprehensivelyworkflowProductEngineeringL2
design-review · Multi-phase workflows requiring orchestrated agent handoffs and structured consensus.
Audit user flows for blockers adversariallyworkflowProductL3
qa-flow-audit · High-stakes architectural or strategic decisions requiring adversarial pressure-testing.
Design multi-agent tournament evaluationworkflowProductEngineeringL3
tournament-design · Design decisions with multiple valid approaches needing synthesis through pairwise-judged competition.
Validate spec and plan adversariallyworkflowProductEngineeringL3
superpower-validate · Spec/plan validation before build when requirements are vague or dependencies cross multiple systems.
Analyze site structure deeplyworkflowProductOpsL3
site-deep-analyze · Deep site analysis combining Playwright crawl, static DOM/CSS inspection, and vision-based UI classification.
Annotate specifications with structured feedbackcommandProductL2
annotate · Teams reviewing specifications, documentation, or design rationales where structured feedback (comments, deletions, image callouts) beats inline email.
Design viral loops for product-led growthskillProductMarketingL1
gtm · Founders with product that has embedded sharing potential (calendar tools, design tools, collaborative docs) who want to design the loop smartly instead of hoping for organic viral, and need launch sequencing that maximizes early K factor.
Tune Codex theme iterativelyworkflowEngineeringProductL2
codex-theme-tune · Orchestrating multi-phase autonomous workflows where fan-out and synthesis improve outcomes.
Tune Antigravity theme iterativelyworkflowEngineeringProductL2
antigravity-theme-tune · Orchestrating multi-phase autonomous workflows where fan-out and synthesis improve outcomes.
Triage feature scope and designworkflowProductEngineeringL3
fathomdb-v05-feature-triage · Orchestrating multi-phase autonomous workflows where fan-out and synthesis improve outcomes.
Plan phased build for collaborative editorworkflowProductL2
notion-clone-build-plan · Workflow notion clone build plan with multi-agent verification.
Unpack vague requirements before buildingskillProductL1
interview-me · Pre-spec phase where guessing wrong is still free—unpack vague asks like 'build me a dashboard' before committing to architecture.
Analyze user retention by cohortskillProductL2
cohort-analysis · Understanding long-term user engagement and identifying which cohorts churn early vs. stay engaged, informing retention experiments and feature adoption strategies.
Shift roadmap from features to outcomesskillProductL2
outcome-roadmap · Shifting teams from feature-driven to impact-driven roadmaps, especially when product flexibility and strategic alignment matter more than delivery precision.
Set up analytics in Flutter appsskillEngineeringProductL2
firebase-analytics · Implementing analytics tracking for user behavior, screen views, and conversion funnels in production Flutter apps.
Design mobile app analytics tracking planskillMarketingProductL2
app-analytics · Mobile teams who need structured metrics frameworks to answer business questions (retention/LTV/churn) rather than raw dashboards.
Remove first-run friction to boost activationskillProductL2
onboarding-optimization · Mobile teams with <40% D0 activation rate who need to cut onboarding friction to proven patterns vs custom design.
Redesign UI with Tailwind and shadcnworkflowProductL2
ui-redesign · Workflow ui redesign with multi-agent verification.
Rewrite roadmaps as outcome-focused planscommandProductL1
transform-roadmap · Product teams transitioning from output-focused to outcome-focused planning, especially before executive presentations or quarterly planning.
Pressure-test product requests before spec writingcommandProductL1
plan-ceo-review · Founders and product managers blocking time BEFORE spec writing to validate that the requested feature is actually the right product.
Migrate UI primitives to Lumina kitworkflowProductL3
migrate-engineering-primitives · Workflow migrate engineering primitives with multi-agent verification.
Generate ideas, dedupe, filter by rubricworkflowProductL2
generate-and-filter · Brainstorming where you want breadth first, then only the highest-quality, non-duplicate, rubric-passing ideas. Pass a bare topic string, or {topic, generators?, rubric?, threshold?, keep?} as args.
Audit feature gaps versus roadmapworkflowProductL3
feature-gap-review · Multi-dimensional acceptance criteria requiring independent per-AC verification.
Sweep GUI surfaces for jank and issuesworkflowProductL2
gui-audit · Triage workflows where items need independent lens-based analysis before synthesis.
Implement remaining PRD slicesworkflowProductL3
ship-prd · Topologically sorted task execution across human-in-the-loop and agentic work layers.
Implement and verify pending milestonesworkflowProductEngineeringL3
argus-implement · Complex workflows requiring parallel agents, synthesized judgment, or multi-phase triage.
Improve game dictionaries with dual-judge validationworkflowProductEngineeringL3
dictionary-improvement · Complex workflows requiring parallel agents, synthesized judgment, or multi-phase triage.
Audit active and parked epicsworkflowProductEngineeringL3
epic-audit · Triage workflows where items need independent lens-based analysis before synthesis.
Validate product demand with sourced evidenceworkflowProductMarketingL3
market-validation-research · Gathering and adversarially verifying market or technical evidence from multiple sources with cited claims.
Sequential product spec review workflowworkflowProductL3
autoplan · Orchestrating multi-phase agent workflows with structured handoff and consensus-driven decision gates.
Build release from plan with verificationworkflowEngineeringProductL3
release-builder · Decomposing complex release plans into parallel, worktree-isolated producer agents that verify outputs against exit criteria.
Build and review capability packs from researchworkflowProductOpsL3
agent-pack-factory-build · Building agent-adjacent capability packs where research findings are grounded into tested, reusable prompts.
Re-verify architecture audit decisionsworkflowEngineeringProductL3
architecture-audit-escalation · Finding subtle bugs or policy violations across large codebases that require consistent multi-agent consensus.
Generate and stress-test build optionsworkflowProductL3
build-options-judge-panel · Decomposing complex release plans into parallel, worktree-isolated producer agents that verify outputs against exit criteria.
Validate product opportunity before buildingskillProductOpsL3
agency-phase-0-discovery · De-risking product ideas before engineering effort by validating market, users, regulations, and competitive space.
Score technical approaches with judgesworkflowProductL2
judge-panel · Orchestrate multi-agent judge panel across parallel branches and synthesis.
Propose and verify iterative improvementsworkflowProductL2
improve · Orchestrate multi-agent improve across parallel branches and synthesis.
Design backward-compatible courses that convertskillMarketingProductL2
course-creator · When building courses that actually transform learners because you design backward from outcomes, ruthlessly cut bloat, and align format to goal.
Auto-generate and pick winning variationworkflowProductL3
auto-forge · Rapid design iteration when human review cycles are slow and you accept self-judged direction.
Build sequenced backend tasks from contractsworkflowProductL2
todos-build · Multi-agent backend implementation when strict pinned-contract enforcement prevents scope creep.
Sync Figma designs with auto-fallbackworkflowProductL2
figma-design-sync · Design→code sync when designers commit to Figma and engineers want single source of truth.
Validate A/B test results statisticallyskillProductL2
ab-test-analysis · Data-driven product decisions when A/B test results need validation against statistical rigor and guardrail constraints before shipping.
Triage app crashes by business impactskillEngineeringProductL2
crash-analytics · Mobile teams seeing >0.5% crash rate affecting App Store ranking and retention who need impact-based triage not frequency ranking.
Discover intent signals in nichesskillSalesProductL2
niche-signal-discovery · Product teams or GTM founders discovering underserved micro-niches with clear intent signals.
Conduct expert market researchskillProductL1
market-research-analysis · Complex multi-phase orchestration where deterministic ordering and structured outputs are critical.
Map competitive advantagesskillMarketingProductL1
marketing-advantages · Positioning when you need to choose 1-2 defensible advantages to own vs trying to win on 10 features.