cyberneticlibrary

The library

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

ArtifactsCapabilitiesRecipes
kindallskillworkflowmcp_servercommandsubagentplugin|✓ proven✗ harmfulmeasured only6,001 artifacts
forSalesMarketingHRFinanceLegalOpsProductEngineeringDataProductivitySupportsetup≤ plug & play≤ + a key≤ multi-tool
WORKS 54
Fan-out verify standards per agentworkflowOpsEngineeringL2
standards-verify · fan-out parallel research with synthesized results
WORKS 54
Remove gates fix errors per-crateworkflowEngineeringL2
phase-e-mass-ungate · fan-out parallel research with synthesized results
WORKS 54
Merge duplicate memory entriesworkflowOpsProductivityL2
consolidate-memory · unifying distributed agent state into a single source of truth
WORKS 56
Root-cause test failures verdictworkflowEngineeringL2
pathfinder-v2-verdict-pass · fan-out parallel research with synthesized results
WORKS 57
Run demo workflowworkflowL2
demo · fan-out parallel research with synthesized results
WORKS 60
Source royalty-free images for articlesworkflowMarketingL2
fetch-images · Chunked batch download with parallel agents and sequential within-chunk ordering.
WORKS 60
Research and cite web sourcesworkflowOpsL2
loom-research · Multi-angle research with parallel search, aggregation, and adversarial contradiction resolution.
WORKS 58
Audit server list smoke testworkflowEngineeringL2
UI Audit · Comprehensive multi-phase scan across heterogeneous source corpus with parallel validation.
WORKS 53
Localize privacy policy into 24 languagesworkflowLegalL2
translate-miru-privacy · Localizing privacy policies and UI text into 24 languages with strict JSON validation and placeholder preservation.
WORKS 57
Apply CLAUDE.md fixes in parallelworkflowEngineeringL2
claude-md-audit-remediate · Comprehensive multi-phase scan across heterogeneous source corpus with parallel validation.
WORKS 56
Classify reference taxonomyworkflowDataL2
references-audit-classify · Comprehensive multi-phase scan across heterogeneous source corpus with parallel validation.
WORKS 54
Audit team scaffold consistencyworkflowOpsL2
scaffold-team · Multi-phase scaffold-team orchestration with structured phase control and receipts.
WORKS 60
Detect vault health decay earlyworkflowOpsL2
health-audit · Comprehensive multi-phase scan across heterogeneous source corpus with parallel validation.
WORKS 54
Run discovery until completeworkflowOpsL2
loop-until-dry · Multi-phase loop-until-dry orchestration with structured phase control and receipts.
WORKS 57
Extract entities from news articlesworkflowDataL2
news-graph-extract · Building knowledge graphs from news corpora where entities and relationships must be structured for Neo4j ingestion.
WORKS 59
Generate and review QA test planworkflowEngineeringL2
implement-test-plan-reviewer · Building QA tools where the plan must be the authoritative spec and implementation is adversarially validated.
WORKS 55
Fix failing recipe buildsworkflowEngineeringL2
recipe-grind-r2 · Automated recipe repair where root cause must be diagnosed from real CI failure output.
WORKS 55
Run anonymous peer review panelworkflowOpsL2
boardroom-blind-review · High-stakes decisions where reviewer independence must be enforced structurally via separate agent contexts.
WORKS 60
Run lightweight code QAworkflowEngineeringL2
qa · Budget-gated QA where lite testing is the gate before heavier runs.
WORKS 53
Run parallel agent swarmworkflowOpsL2
parallel-swarm.workflow · Batch operations where each item can be independently processed in parallel.
WORKS 58
Wait for PR review completionworkflowEngineeringL2
wait-for-pr-review · CI pipelines where Claude-generated reviews must complete before merging.
WORKS 55
Judge sprite restyling candidatesworkflowProductL2
sprite-restyle-judge · Game asset QA where visual consistency to canon must be both scored and gated per character.
WORKS 55
Draft stale ticket updatesworkflowOpsL2
stale-ticket-drafts · Automated ticket triage where stale tickets need human-readable status drafts without direct edits.
WORKS 57
Run independent audit panelworkflowOpsL2
judge-independent-audit · Auditing complex ML systems.
WORKS 55
Refine work across teamworkflowOpsL2
team-refine · Use when implementing team-refine patterns.
WORKS 56
Review code for bugsworkflowEngineeringL2
review · Use when implementing review patterns.
WORKS 54
Classify dependency cycle typesworkflowEngineeringL2
phase-b0-cyclebreak · Use when implementing phase-b0-cyclebreak patterns.
WORKS 57
Detect emergent vault themesworkflowOpsL2
emergence-scan · Use when implementing emergence-scan patterns.
WORKS 56
Use when implementing t patterns.workflowL2
t · Use when implementing t patterns.
WORKS 57
Run parallel QA agentsworkflowEngineeringL2
qa-parallel-suite · Budget-gated QA where lite testing is the gate before heavier runs.
WORKS 59
Benchmark single-agent extractionworkflowEngineeringL2
bench-s0-monolith · Use when implementing bench-s0-monolith patterns.
WORKS 54
Measure agent concurrency limitsworkflowEngineeringL2
trace-concurrency-cap · empirically validating the workflow runtime's true parallel capacity before launching production workloads
WORKS 58
Audit build status and find gapsworkflowEngineeringL2
frontier-tail-survey · auditing true build state across multiple frontiers without false confidence from presence of stub files
WORKS 55
Gate code reviews by impactworkflowEngineeringL2
cr-threshold-gate · mechanical OR-gated CR dispatch (LOC > 50 OR core-module hit) without human judgment
WORKS 54
Localize UI text to 37 languagesworkflowProductMarketingL2
translate-keys · Localizing customer-facing UI (like ordering combos) into 37 languages with strict JSON schema + placeholder + markup preservation.
WORKS 59
Detect performance regressionsworkflowEngineeringL2
benchmark-audit · spotting performance regressions in CI without re-running expensive GPU benchmarks
WORKS 54
Adversarial interview and grillingworkflowL2
grill · Finding unstated assumptions and failure modes before design is locked
WORKS 48
Convert files and URLs to MarkdownskillL2
markit · Extracting markdown from any document type in CI/analysis pipelines
WORKS 48
Manage repository operationsskillEngineeringL2
.skill · Lightweight agent-driven repo validation without external runners
WORKS 48
Fetch WeChat articles to MarkdownskillMarketingL2
wechat-article-to-markdown · Archiving WeChat articles for AI summarization or knowledge base ingestion when image localization and metadata preservation matter.
WORKS 48
MZR Icons SVG toolkitskillL1
skill · Adding dynamic GitHub profile visualizations to README badges or portfolio pages when static HTML badges are insufficient.
WORKS 48
Query and manage memoriesskillProductivityL1
mem · Reducing token overhead by 10x when querying project history—compact search results then drill into specific observations only when needed.
WORKS 48
Search web via SearxNGskillL2
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.
WORKS 52
Generate daily session summaryskillProductivityL1
daily · Automated daily billing and activity accountability when you need time-tracking summaries without manual work.
WORKS 48
Pass password to agent securelyskillOpsL1
pw2agent · Handing secrets to agent subprocesses without printing them in chat logs—prevents accidental exposure in transcripts.
WORKS 59
Capture web page and accessibility treeskillL2
Skill · Comprehensive page auditing (visual, accessibility, performance, network) when you need multi-layer diagnostics beyond screenshots.
WORKS 48
Populate apps with realistic test dataskillProductEngineeringL2
Skill · Rapid test-data generation for web apps when you need to respect entity relationships and field types without manual SQL.
WORKS 48
Follow writing guidelinesskillL1
skill · Creating customer-facing API docs when clarity and accuracy of UI labels are non-negotiable for business users.
WORKS 48
Track time on work ticketsskillOpsProductivityL2
trackmedaddy · Seamless time logging from CLI when you need to track work without leaving the terminal—avoids context switching.
WORKS 48
Visualize audio dataskillEngineeringProductL2
skill · Creating audio-reactive visuals when aesthetic consistency and lore injection matter more than generic animation.
←page 14 / 121→