cyberneticlibrary

The library

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

ArtifactsCapabilitiesRecipes
kindallskillworkflowmcp_servercommandsubagentplugin|✓ proven✗ harmfulmeasured only1,180 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 49
Validate findings with structured rubricsworkflowL2
verify-findings-rubric · Multi-agent orchestration for verify findings rubric workflows.
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 48
Verify financial figures adversariallyworkflowFinanceL2
verifica-report · Auditing financial notes against transactional DB when you need claim-by-claim verification with source traceability.
WORKS 55
Analyze with adversarial score verificationworkflowDataL3
wf-analyze · Go/no-go decisions on architecture changes when you want scored evidence from multiple dimensions plus adversarial challenge built in.
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
Generate features with parallel filesworkflowEngineeringL2
scaffold-feature · Scaffolding a new feature when you want parallel file generation against a plan plus a built-in consistency review.
WORKS 48
Run 1000 parallel research and synthesis jobsworkflowEngineeringL3
agi-cli-parity-1000 · Large-scale CLI parity audits when you need cited evidence across many dimensions with auto-synthesis into consolidated artifacts.
WORKS 48
Host Claude across multiple CLI invocationsworkflowEngineeringL4
resident-daemon · Persisting resident Claude across CLI invocations when you need a Unix daemon that reuses existing ResidentPool without adding dependencies.
WORKS 48
Finish branch with leak scan and PR automationworkflowEngineeringL3
autopilot-finish-branch · Finishing a feature branch with hard-gated leak scanning and automatic PR creation/update in a single orchestrated flow.
WORKS 48
Audit LLM gateway production reliabilityworkflowEngineeringL3
otto-gateway-reliability-audit · Production-readiness audits of Go LLM gateways when you need multi-agent scanning + adversarial verification across reliability dimensions.
WORKS 54
Generate autonomous architecture plansworkflowEngineeringL2
lets-plan-workflow · Multi-phase orchestration when phases need to be planned sequentially with approval checkpoints.
WORKS 48
Batch design and architect clustersworkflowEngineeringL2
evolve-batch · Iterative batch refinement when you need multiple feedback cycles with controlled evolution.
WORKS 48
Centralize database connection poolsworkflowEngineeringL3
hardening-pool-centralization · Hardening systems when you need to consolidate fragmented resource pools into a single managed center.
WORKS 48
Execute reviewed database migrationsworkflowEngineeringL3
yasad-data-migration-wave · Large data migrations when you need staged waves with automatic rollback gates and data validation.
WORKS 55
Run multi-lens adversarial code reviewworkflowEngineeringL3
review-with-agent · Code review when you want an agent to async provide inline feedback on a specific diff.
WORKS 48
Audit tool migration UX and gapsworkflowEngineeringL2
agi-cli-migration-ux · CLI migrations when you need designed UX with clear deprecation paths and fallback.
WORKS 49
Find and propose missing test casesworkflowEngineeringL2
test-gap-finder · Test improvement when you need to identify which code paths are untested and which tests are weak.
WORKS 51
Map and summarize codebase architectureworkflowEngineeringL2
codebase-survey · Onboarding or refactoring when you want a comprehensive structure survey without running code.
WORKS 48
Orchestrate multi-verb fleet operationsworkflowEngineeringL3
hangar · Portfolio management when you need a workspace organizing multiple concurrent initiatives with clear blockers.
WORKS 48
Map subsystem dependencies and planworkflowEngineeringL2
understand · Deep dives when you need a thorough mental model of a complex system from an agent.
WORKS 48
Verify findings through adversarial refutationworkflowEngineeringL2
adversarial-verify · Decision-making when you want an agent to systematically argue against a claim before committing.
WORKS 50
Review repository with routing controlsworkflowEngineeringL2
routed_repo_review · Conducting structured code/design reviews with multiple perspectives in parallel.
WORKS 49
Audit test files against rulesworkflowEngineeringL2
finalize-testing-rules-audit · Conducting structured code/design reviews with multiple perspectives in parallel.
WORKS 48
Adjudicate design and conduct disputesworkflowEngineeringL3
vjs-first-instance · Orchestrating multi-agent workflows with bounded costs and structured outputs.
WORKS 57
Run mutation testing auditworkflowEngineeringL3
maw-audit · Conducting structured code/design reviews with multiple perspectives in parallel.
WORKS 48
Extract and index forge conventionsworkflowEngineeringL2
forge-conventions-extract · Extracting and indexing knowledge from distributed sources.
WORKS 55
Execute goal with review and fix loopsworkflowEngineeringL3
goal · Executing goals with checkpoint commits, review loops, and deep judging until complete.
WORKS 48
Verify worktree-isolated work partitionsworkflowEngineeringL3
parallel-verify · Running isolated writers in parallel then integrating and verifying once.
WORKS 48
Implement and review crypto coreworkflowEngineeringL3
env-ctl-phase1-vaultcore · Orchestrating multi-agent workflows with bounded costs and structured outputs.
WORKS 48
Review domain design with architect councilworkflowEngineeringL3
ddd-council-review · Conducting structured code/design reviews with multiple perspectives in parallel.
WORKS 48
Migrate codebase to TypeScriptworkflowEngineeringL3
typescript-migration · Coordinating large-scale code migrations with staged validation.
WORKS 48
Analyze customer churn and retention strategyworkflowSalesFinanceL2
columbia-churn-2024-2026 · Orchestrating multi-agent workflows with bounded costs and structured outputs.
WORKS 55
Design architecture with multi-perspective consensusworkflowEngineeringProductL3
kiln-architecture · Applying DDD council review patterns with cross-examination and devil's advocacy.
WORKS 46
Run smoke test validationworkflowEngineeringL2
submit_smoke · Orchestrating multi-agent workflows with bounded costs and structured outputs.
WORKS 41
Generate and synthesize best answer in parallelworkflowL2
fan-out-reduce · Orchestrating multi-agent workflows with bounded costs and structured outputs.
WORKS 48
Monitor deployment health automaticallyworkflowEngineeringOpsL2
canary · Post-deployment health monitoring with parallel metric collection and automated judging.
WORKS 48
Extract LoRA fine-tuning recipe with validationworkflowEngineeringL3
finish-l4-lora-recipe · Orchestrating multi-agent workflows with bounded costs and structured outputs.
WORKS 48
Validate reverse-engineering pipeline end-to-endworkflowEngineeringL3
synthetic-round-trip · Orchestrating multi-agent workflows with bounded costs and structured outputs.
WORKS 52
Audit security with adversarial verificationworkflowOpsEngineeringL3
security-audit · Conducting structured code/design reviews with multiple perspectives in parallel.
WORKS 48
Synthesize swarm results with adversarial arbitrationworkflowEngineeringL3
wf-swarm-synthesize · Gathering diverse perspectives and synthesizing a single authoritative result.
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 59
Build software features end-to-endworkflowEngineeringL3
software-factory-pipeline · When coordinating feature development with model-selection, telemetry, and integrated deployment.
WORKS 48
Resolve foundational design questionsworkflowProductEngineeringL3
vjs-supreme-court · When resolving constitutional questions requiring multi-justice written opinions and case law synthesis.
WORKS 48
Audit codebase and synthesize findingsworkflowEngineeringL3
audit · When finding latent defects across mixed languages with mechanical refutation of false positives.
WORKS 48
Evaluate versioning control sessionsworkflowEngineeringL3
vcs-eval-start-round · When measuring whether agents properly isolate before editing a shared repository.
WORKS 48
Build open-source agent infrastructureworkflowEngineeringL4
build-shell-v2 · When layering open-source packages with typed contracts that must stay green at each step.
←page 17 / 24→