cyberneticlibrary

The library

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

ArtifactsCapabilitiesRecipes
kindallskillworkflowmcp_servercommandsubagentplugin|✓ proven✗ harmfulmeasured only1,482 artifacts
forSalesMarketingHRFinanceLegalOpsProductEngineeringDataProductivitySupportsetup≤ plug & play≤ + a key≤ multi-tool
WORKS 55
Audit and clean project issuesworkflowOpsEngineeringL3
pm-audit · Comprehensive review of codebase/content with structured audit findings.
WORKS 59
Audit and improve documentation roundsworkflowOpsEngineeringL3
magpie-doc-audit-round · Comprehensive review of codebase/content with structured audit findings.
WORKS 57
Synthesize consensus from expert panelsworkflowOpsProductL3
consensus-decision · Reaching agreement among multiple autonomous agents on decisions.
WORKS 51
Research topics across multiple sourcesworkflowOpsDataL3
research · Synthesizing evidence on academic/technical topics when you need multi-modality (text+code+data) sweep plus two-stage extraction-enrichment pipeline.
WORKS 48
Map change impact across systemsworkflowEngineeringOpsL3
mishkan-blast-radius · Refactoring when you need to know real impact before scheduling work, with automatic false-positive filtering via 3 orthogonal verification lenses.
WORKS 48
Monitor deployment health automaticallyworkflowEngineeringOpsL2
canary · Post-deployment health monitoring with parallel metric collection and automated judging.
WORKS 52
Audit security with adversarial verificationworkflowOpsEngineeringL3
security-audit · Conducting structured code/design reviews with multiple perspectives in parallel.
WORKS 48
Drive media pairing project to completionworkflowProductOpsL3
media-pairing-escalation-orchestrator · Orchestrating complex projects with implement->verify->escalate patterns.
WORKS 48
Redesign documentation with competing proposalsworkflowOpsProductL3
nirs4all-docs-restructuring-proposal · When redesigning OSS library documentation with competing philosophies needing adversarial comparison.
WORKS 60
Execute event pipeline end-to-endworkflowOpsL3
sweep-civ · When batch-upgrading timeline events with photos and verification across multiple gates.
WORKS 48
Conduct adversarial security threat auditworkflowOpsL3
threat-audit · When identifying threat vectors requires multiple independent adversarial security lenses.
WORKS 48
Scale agents within token budgetworkflowEngineeringOpsL2
loop-until-budget · When a task needs to run repetitively until completion or token budget exhaustion.
WORKS 48
Summarize Jira sprint digestworkflowOpsEngineeringL2
jira-digest · When generating team digests from Jira activity with structured, parseable output.
WORKS 48
Verify workshop slides and diagramsworkflowMarketingOpsL3
workshop-verify · Called by the workshop skill at the Phase 3->4 boundary (artifact review gate) and as Phase 4 verification, and by workshop-revise after edits.
WORKS 48
Adversarially review research paperworkflowDataOpsL3
review-paper · Use when workflow operations need review paper.
WORKS 48
Classify and synthesize memory entriesworkflowOpsProductivityL3
memory-gc · Use when workflow operations need memory gc.
WORKS 48
Orchestrate tiered task executionworkflowEngineeringOpsL3
wfl:run-task · Run a single Forge task through its full plan→implement→review→approve→commit pipeline via a deterministic JS driver instead of the LLM orchestrator.
WORKS 48
Dispatch bound doc reviewersworkflowOpsEngineeringL3
oagp-seat-doc-reviewer · Use when workflow operations need oagp seat doc reviewer.
WORKS 60
Dispatch and monitor pipeline executionworkflowOpsL3
software-factory-dispatcher · Orchestrating work across specialized factory agents with parallel task distribution.
WORKS 48
Execute planner-executor-verifier loopworkflowOpsL3
traveleditor-stream · Streaming editorial changes in a travel editor with real-time sync.
WORKS 55
Fan-out research with adversarial fact-checkworkflowOpsDataL3
research · Fan-out web research, dedup sources, synthesize with citations, and fact-check claims.
WORKS 48
Multi-panel refute findings with consensusworkflowDataOpsL3
verify-findings · Verify code audit findings using 3 independent skeptic lenses.
WORKS 48
Execute deterministic research pipelineworkflowOpsDataL3
research-pipeline · Execute research through fan-out collection, dedup, and analysis phases.
WORKS 48
Parallelize work on cheap modelsworkflowEngineeringOpsL2
cheap-fanout-synthesis · Fan-out cheap research when no single synthesizer can hold the full pool.
WORKS 51
Extract and verify factual claimsworkflowOpsDataL2
claim_verifier · Verify document claims are grounded in cited sources.
WORKS 48
Classify commits into feature bucketsworkflowEngineeringOpsL2
reclassify-commits · Batch-labeling hundreds of commits into coherent features without manual triage.
WORKS 48
Curate tech community research digestworkflowOpsDataL2
research-digest · Aggregating research signals from 7 heterogeneous sources with real-time relevance ranking and dedup.
WORKS 48
Inventory and catalog all DAGsworkflowEngineeringOpsL2
dag-inventory · Cataloging and classifying large numbers of DAGs for safe migration or archival decisions.
WORKS 51
Adversarial review with severity rankingworkflowEngineeringOpsL3
review · Multi-stage code review with parallel verification agents and structured decision gates.
WORKS 48
Daily AI system health scanworkflowOpsL2
daily-system-review · Monitoring AI ecosystem changes across vendor + community + internal tiers daily
WORKS 48
Generate and rank candidate plansworkflowProductOpsL2
judge-panel · Assembling diverse expert perspectives in a structured panel verdict
WORKS 48
QA rendered content for extraction errorsworkflowOpsL3
content-rendering-qa · QA text content when you need to detect HTML/entities, page numbers, OCR gibberish, dropped words, truncation in rendered fields.
WORKS 54
Plan proposals with adversarial reviewworkflowOpsL3
wf-plan · Designing workflows when you need to decompose a goal into agent-ready phase briefs and schemas.
WORKS 48
Batch improve and refresh skillsworkflowOpsL2
skill-improver-batch · Skill refinement when you have many skills needing updates based on failure logs or user feedback.
WORKS 48
Brainstorm with cross-specialist reviewworkflowOpsL2
wf-brainstorm · Synthesizing design decisions across conflicting expert perspectives.
WORKS 48
Generate and verify files at scale with metricsworkflowOpsL2
parallel-file-write-with-verify · Writing many files in parallel then auditing for quality metrics.
WORKS 48
Safely triage and quarantine untrusted inputsworkflowOpsL2
triage_quarantine · Isolating failing cases for targeted root-cause investigation.
WORKS 48
Audit system resilience with adversarial verificationworkflowOpsL3
system-audit · Validating critical system audit findings through multi-LLM consensus (2/3 agreement) rather than single-model verdicts, catching blind spots.
WORKS 48
Distill daily agent activity digestworkflowOpsL2
agent-daily-digest · Use when you need a structured agent daily digest workflow.
WORKS 48
Update and verify monitoring dashboardworkflowOpsL2
dashboard · Use when you need a structured dashboard workflow.
WORKS 48
Audit document structure and proseworkflowOpsL3
writing-review · Use when you need a structured writing review workflow.
WORKS 48
Run three-phase multi-loop review workflowsworkflowOpsL3
l3-phase · Use when you need a structured l3 phase workflow.
WORKS 48
Research gaps and synthesize cited reportsworkflowOpsL2
research · Use when you need a structured research workflow.
WORKS 48
Extract translation termbase from pairsworkflowOpsL2
glossary-extract · Extracting domain terminology from curated pairs while normalizing and deduplicating.
WORKS 48
Compile technical report with visualsworkflowOpsL3
cadence-report · Self-compiling LaTeX sections with visual verification and fixing before assembly.
WORKS 48
Map current state across dimensionsworkflowOpsL2
evolve-understand · Mapping current state of a codebase across multiple facets before design decisions.
WORKS 49
Classify documents by type at scaleworkflowOpsL2
layer1-classify · Initial categorical bucketing of items before detailed processing.
WORKS 48
Close sprint with parallel team reportsworkflowOpsL2
mishkan-sprint-close · Closing sprints with task completion audit and next-phase handoff.
WORKS 48
Reuse catalog items or create new onesworkflowOpsL2
driver-catalog-first-g1 · First-pass cataloging of driver entities with schema conformance.
WORKS 48
Draft and peer-review research paper sectionsworkflowOpsL2
ccgp-paper · Synthesizing research papers from sourced content with citations.
←page 24 / 30→