The library

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

untested
Cluster and rank customer feedback themesworkflowProductL2
customer-feedback-theme-extractor · Bulk customer feedback analysis when you want quick theme extraction + ranking by frequency
untested
Audit sprint retro transcripts across lensesworkflowOpsL2
retro-audit-engine · Continuous monitoring of sprint health through multi-lens transcript audit when retro findings need adversarial validation.
untested
Complete partially-written content tracksworkflowMarketingL2
finish-track · Graduate-level monographs on statistical/mathematical topics where step-by-step derivations and honest real-world examples are mandatory.
untested
Validate infrastructure changes across dimensionsworkflowEngineeringL2
migdal-infra-change · Non-trivial infrastructure changes (network, IAM, scaling) where blast-radius analysis spans design, systems, devops, observability, and health.
untested
Dispatch parallel agent tasks with capped concurrencyworkflowEngineeringL2
fanout · Batched parallel work where cost/quota capping is required and partial-failure detection is needed.
untested
Extract grant facets into controlled taxonomiesworkflowFinanceL2
layer2-facet · Exploratory grant faceting where open-ended vocabularies evolve (seed values provided but new entries created per grant).
untested
Scan Python codebases for TODO commentsworkflowEngineeringL2
todo-scanner · Quick inventory of technical debt across a Python codebase when distributed priorities and actionable top-3 recommendations are needed.
untested
Validate and refine translation quality at scaleworkflowMarketingL2
sonnet-validate-fix · Second-tier quality gate on bulk machine-translated game localization when register, terminology, formatting preservation, and idiomatic rewrite are critical.
untested
Review and repair language-specific code findingsworkflowEngineeringL2
systems-check-workflow · Iterative code review when language-specific inspectors and optional specialist agents (security, perf, migration) are needed and findings must be actionable.
untested
Discover and refute bugs with majority verificationworkflowEngineeringL2
bug-hunt · Exploratory correctness/security/resource-leak testing when multiple independent finders and majority-refute skeptics must verify candidates.
untested
Process finance theme through critical review pipelineworkflowFinanceL2
fi-theme-pipeline · Off-the-battlefield historical narrative when locked house voice, fact-pack validation, and parallel critic review are mandatory.
untested
Migrate portfolio template to Sanity with visual parityworkflowEngineeringL3
kokimoto-migration · Version upgrades of complex config systems when automated transformation and validation must preserve backward compatibility.
untested
Re-author failed carousel content daysworkflowMarketingL2
author-carousel-missing-days · Editorial scheduling when author carousel coverage must be contiguous and gaps auto-filled.
untested
Rewrite paper sections in parallel for consistencyworkflowMarketingL2
paper-redraft · Batch academic/technical paper authoring when spec-driven drafting and multi-phase review are needed.
untested
Detect CLAUDE.md audit issues across codebasesworkflowEngineeringL2
claude-md-audit-detect · Multi-repo governance when CLAUDE.md documentation standards must be enforced and drift detected.
untested
Discover untested code paths and generate testsworkflowEngineeringL2
test-expander · Test suite expansion when round-trip generation and adversarial validation are needed.
untested
Execute parallel workflows with convergence verificationworkflowEngineeringL3
wf-execute · Complex multi-phase workflows when barrier synchronization and per-phase label tracking are required.
untested
Run phase-4 code review tracks in parallelworkflowEngineeringL3
forge-phase4-review · Stage-gate project reviews when distributed team consensus and blockers are tracked.
untested
Multi-perspective code review with adversarial verificationworkflowEngineeringL3
wf-review · Post-workflow synthesis when parallel-phase outputs must be reconciled into actionable findings.
untested
Benchmark code across 8 concurrent workersworkflowEngineeringL3
bench-s2-parallel · Model selection when parallel-agent latency and throughput baselines must be measured.
untested
Score competing implementations adversariallyworkflowEngineeringL3
tooltuner-judge · Tool optimization when results must be ranked against a baseline and winner declared.
untested
Debate code findings to consensusworkflowEngineeringL3
lens-debate · Code reviews where structural fit matters more than style, paired with expedited fix application.
untested
Audit all product surfaces for functional gapsworkflowProductL3
surface-functional-audit-2 · Comprehensive UI audit where engagement flows (like/save/comment) must be traced end-to-end.
untested
Scan files for concerns with adversarial verificationworkflowEngineeringL3
review-files · Scanning a subset of files for a concrete concern (e.g., hardcoded secrets, missing validation).
untested
Review TUI code across 5 quality dimensionsworkflowEngineeringL3
ratatui-tui-review · Systematic dimensional review of ratatui apps before release, catching architecture + safety drift.
untested
Synthesize bug bounty methodology from researchworkflowL3
bb-methodology-core · Assembling a comprehensive, cross-verified security curriculum from existing + new research.
untested
Execute build chunks with auto-fix and structured feedbackworkflowEngineeringL3
session-orchestrate-build · Large features where chunked implementation avoids bloat + auto-escalation prevents silent failure.
untested
Audit design-to-code gaps with verificationworkflowEngineeringProductL3
m1m8-gap-audit · Verifying that large real-time systems stay synchronized between intent (design) and implementation.
untested
Detect and fix API specification driftworkflowEngineeringL3
api-contract-drift-detector · Catching API shape evolution that outruns documentation, automated on every release.
untested
Build Discord-first growth execution planworkflowMarketingOpsL3
acgs-growth-plan · Pivoting a project's growth strategy while grounding decisions in actual codebase state + market data.
untested
Run multi-stage deep research pipelineworkflowOpsDataL3
mishkan-deep-research · In-depth multi-angle research reports where contradictory sources must be reconciled by skeptic review.
untested
Cross-verify findings with independent skepticsworkflowEngineeringL3
adversarial_review · Quality gates where reducing false positives via skeptic consensus beats upfront filtering.
untested
Remediate reference changes in parallelworkflowEngineeringL3
references-audit-remediate · Batching reference-fix decisions (from a prior classification gate) for parallel execution.
untested
Ingest and verify candidate artifactsworkflowEngineeringL3
loop-c-ingestion · Validating backlog artifacts against live source before promoting to canon.
untested
Rank items by pairwise comparison tournamentworkflowOpsDataL2
tournament-sort · Ranking hundreds of items by a nuanced criterion without exhausting a single agent's context window.
untested
Execute top-level module-result workflowsworkflowEngineeringL3
module-result · Testing and exercising the module-result contract in the Workflow runtime.
untested
Pipeline PRD through architecture to threat modelworkflowProductEngineeringL3
mishkan-init · Fast-tracking project bootstrap by starting research stages as soon as their upstream dependencies become available.
untested
Search and retrieve icons from 116 style packsmcp_serverProductL2
icons8mpc · Generate icon assets for UI projects when needing massive, styled collections with style consistency.
untested
Access source code and documentation on GitHubmcp_serverEngineeringL2
gread · Equip agents to understand library source code and docs without web searches.
untested
Install MCP servers across coding agentsmcp_serverEngineeringOpsL2
add-mcp · Bootstrap MCP setup across multiple agents uniformly without manual JSON editing.
untested
Route calls to cheapest available LLMmcp_serverOpsFinanceL2
tickerr-live-status · Route agent calls to cheapest/fastest available LLM model dynamically based on live pricing and failure signals.
untested
Automate Azure infrastructure operationsmcp_serverOpsEngineeringL3
mcp · Automate Azure infrastructure tasks (deploy VMs, manage databases, configure storage) within agent workflows.
untested
Query Malaysian transit and faresmcp_serverOpsL2
mcp-malaysiatransit · Build Malaysia-specific transit assistance (ETA, fare estimates, route planning) for multi-modal journey queries.
untested
Manage GitLab workflows and CI/CDmcp_serverEngineeringL2
mcp-gitlab · Integrate GitLab workflows (CI/CD, code review, issue tracking) into agent-driven development pipelines.
untested
Compress MCP tool descriptionsmcp_serverEngineeringL2
caveman-shrink · Reduce token cost of large MCP tool catalogs by 20-40% without changing tool semantics.
untested
Calculate derivative and portfolio riskmcp_serverFinanceL2
quantoracle · Enable agents to price derivatives and compute portfolio risk without external finance APIs.
untested
Build MCP tool explorer dashboardsmcp_serverEngineeringL2
client · Create browser-based MCP tool explorers and dashboards for non-technical users.
untested
Bridge Genkit and MCP frameworksmcp_serverEngineeringL3
mcp · Use Genkit's multi-model orchestration with MCP tools as drop-in resource providers.
untested
Connect local clients to remote MCPmcp_serverEngineeringL2
mcp-remote · Connect Claude Desktop or Cursor (stdio-only) to cloud-hosted MCP servers without client upgrade.
untested
Search vectors with hybrid retrievalmcp_serverEngineeringDataL2
turbopuffer · Add semantic search to agent systems needing fast, scalable vector DB without managing infrastructure.
page 133 / 161