The library

standards-verify · fan-out parallel research with synthesized results

phase-e-mass-ungate · fan-out parallel research with synthesized results

consolidate-memory · unifying distributed agent state into a single source of truth

pathfinder-v2-verdict-pass · fan-out parallel research with synthesized results

demo · fan-out parallel research with synthesized results

fetch-images · Chunked batch download with parallel agents and sequential within-chunk ordering.

loom-research · Multi-angle research with parallel search, aggregation, and adversarial contradiction resolution.

UI Audit · Comprehensive multi-phase scan across heterogeneous source corpus with parallel validation.

translate-miru-privacy · Localizing privacy policies and UI text into 24 languages with strict JSON validation and placeholder preservation.

claude-md-audit-remediate · Comprehensive multi-phase scan across heterogeneous source corpus with parallel validation.

references-audit-classify · Comprehensive multi-phase scan across heterogeneous source corpus with parallel validation.

scaffold-team · Multi-phase scaffold-team orchestration with structured phase control and receipts.

health-audit · Comprehensive multi-phase scan across heterogeneous source corpus with parallel validation.

loop-until-dry · Multi-phase loop-until-dry orchestration with structured phase control and receipts.

news-graph-extract · Building knowledge graphs from news corpora where entities and relationships must be structured for Neo4j ingestion.

implement-test-plan-reviewer · Building QA tools where the plan must be the authoritative spec and implementation is adversarially validated.

recipe-grind-r2 · Automated recipe repair where root cause must be diagnosed from real CI failure output.

boardroom-blind-review · High-stakes decisions where reviewer independence must be enforced structurally via separate agent contexts.

qa · Budget-gated QA where lite testing is the gate before heavier runs.

parallel-swarm.workflow · Batch operations where each item can be independently processed in parallel.

wait-for-pr-review · CI pipelines where Claude-generated reviews must complete before merging.

sprite-restyle-judge · Game asset QA where visual consistency to canon must be both scored and gated per character.

stale-ticket-drafts · Automated ticket triage where stale tickets need human-readable status drafts without direct edits.

judge-independent-audit · Auditing complex ML systems.

team-refine · Use when implementing team-refine patterns.

review · Use when implementing review patterns.

phase-b0-cyclebreak · Use when implementing phase-b0-cyclebreak patterns.

emergence-scan · Use when implementing emergence-scan patterns.

t · Use when implementing t patterns.

qa-parallel-suite · Budget-gated QA where lite testing is the gate before heavier runs.

bench-s0-monolith · Use when implementing bench-s0-monolith patterns.

trace-concurrency-cap · empirically validating the workflow runtime's true parallel capacity before launching production workloads

frontier-tail-survey · auditing true build state across multiple frontiers without false confidence from presence of stub files

cr-threshold-gate · mechanical OR-gated CR dispatch (LOC > 50 OR core-module hit) without human judgment

translate-keys · Localizing customer-facing UI (like ordering combos) into 37 languages with strict JSON schema + placeholder + markup preservation.

benchmark-audit · spotting performance regressions in CI without re-running expensive GPU benchmarks

grill · Finding unstated assumptions and failure modes before design is locked

markit · Extracting markdown from any document type in CI/analysis pipelines

.skill · Lightweight agent-driven repo validation without external runners

wechat-article-to-markdown · Archiving WeChat articles for AI summarization or knowledge base ingestion when image localization and metadata preservation matter.

skill · Adding dynamic GitHub profile visualizations to README badges or portfolio pages when static HTML badges are insufficient.

mem · Reducing token overhead by 10x when querying project history—compact search results then drill into specific observations only when needed.

ask-search · Privacy-first web search without API keys—useful for local development, aggregating multiple engines, and piping URLs to web_fetch for full content.

daily · Automated daily billing and activity accountability when you need time-tracking summaries without manual work.

pw2agent · Handing secrets to agent subprocesses without printing them in chat logs—prevents accidental exposure in transcripts.

Skill · Comprehensive page auditing (visual, accessibility, performance, network) when you need multi-layer diagnostics beyond screenshots.

Skill · Rapid test-data generation for web apps when you need to respect entity relationships and field types without manual SQL.

skill · Creating customer-facing API docs when clarity and accuracy of UI labels are non-negotiable for business users.

trackmedaddy · Seamless time logging from CLI when you need to track work without leaving the terminal—avoids context switching.

skill · Creating audio-reactive visuals when aesthetic consistency and lore injection matter more than generic animation.