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 48
Execute complete feature lifecycleworkflowEngineeringL3
feature · Feature delivery when you need end-to-end orchestration (design → implement → test → deploy).
WORKS 42
Analyze source files for needed testsworkflowEngineeringL2
test-analysis · Debugging tests when you need to distinguish flakiness from real failures and identify patterns.
WORKS 48
Harden trigger evaluation with adversarial queriesworkflowEngineeringL3
trigger-eval-harden · Automating testing when you need to harden Workflow triggers before production deployment.
WORKS 42
Auto-generate unit tests with coverageworkflowEngineeringL2
unit-test-gen · Test coverage when you have code without tests and need to bootstrap test suite.
WORKS 48
Run load tests with ramping VUworkflowEngineeringL2
load-test · Finding capacity limits through stepped load with automatic breaking-point detection.
WORKS 48
Validate dynamic roster skill invariantsworkflowEngineeringL2
fixture-dynamic-roster-missing-skill · Multi-phase orchestration with agent parallelism and structured verification.
WORKS 48
Improve toolkit with continuous evaluationworkflowEngineeringL4
toolkit-improvement · Multi-phase orchestration with agent parallelism and structured verification.
WORKS 48
Brainstorm with cross-specialist reviewworkflowOpsL2
wf-brainstorm · Synthesizing design decisions across conflicting expert perspectives.
WORKS 55
Execute work with deterministic verificationworkflowEngineeringL3
fierce-ralph · Iterative task execution with real-time progress verification and stagnation detection.
WORKS 48
Screen EHR products with parallel agentsworkflowProductL2
cheap-pass-100 · High-volume batch screening with fixed concurrent worker capacity.
WORKS 48
Debug resume parsing across model variantsworkflowEngineeringL2
trace-resume-model · Distinguishing prefix vs. content-addressed workflow resumption models.
WORKS 48
Ship code through architecture review gatesworkflowEngineeringL2
feature-dev · Multi-gate feature development with human approval at requirements and architecture phases.
WORKS 48
Refactor neural net primitives with bit-level verificationworkflowEngineeringL3
finish-l1-primitives · Refactoring monolithic code into bit-identical primitives with gated extraction.
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 52
Gate releases with adversarial quality reviewworkflowEngineeringL2
gate · Code review with parallel specialists and adversarial skepticism.
WORKS 48
Regenerate specs across voice styles automaticallyworkflowProductL3
spec-critique-voice-ladder-regen · Criticizing specifications from multiple evaluation angles with voice consistency.
WORKS 57
Audit code for correctness and deploy fixesworkflowEngineeringL2
go-audit-fix · Automated auditing and fixing of Go code issues.
WORKS 48
Map content type coverage and edge casesworkflowProductL2
type-field-coverage · Measuring type coverage across large codebases.
WORKS 48
Implement specs autonomously end-to-endworkflowEngineeringL3
sdd-implement-engine · Implementing complex systems driven by formal specifications.
WORKS 48
Safely triage and quarantine untrusted inputsworkflowOpsL2
triage_quarantine · Isolating failing cases for targeted root-cause investigation.
WORKS 48
Push completed work and open pull requestworkflowEngineeringL2
docking-workflow · Integrating components with automatic verification.
WORKS 51
Map codebase architecture in parallelworkflowEngineeringL2
fd-understand-codebase · Building knowledge of unfamiliar codebases through structured exploration.
WORKS 57
Investigate issues and synthesize findingsworkflowEngineeringL2
assess-investigate · Code review with parallel specialists and adversarial skepticism.
WORKS 48
Port database layer with integration testsworkflowEngineeringL3
phase1-repos · Processing multiple repositories in a phased workflow.
WORKS 48
Validate research manuscript for publicationworkflowL2
g3-readiness-review · Rigorously vetting academic manuscripts through multiple independent reviewer lenses before submission, with explicit synthesis of conflicts and prioritized fixes.
WORKS 48
Plan agent memory implementation strategyworkflowEngineeringL3
fathomdb-agent-memory-impl-strategy · Grounding implementation strategy for agent-memory gaps in the actual engine code, with adversarial re-verification against real mechanisms and invariants.
WORKS 48
Reverse-engineer trading strategies from resultsworkflowDataL3
polymarket-reverse-engineer · Designing independent, first-principles trading strategies from observed edge patterns, falsifiable through rigorous gauntlet testing, without relying on wallet-copying.
WORKS 48
Validate and land compiler features systematicallyworkflowEngineeringL3
drain-wave-1 · Draining large spec items with sub-agent isolation and orchestrator-side independent verification of runtime results, preventing sub-agent report blindness.
WORKS 48
Assess drug discovery feasibility scientificallyworkflowL2
insilico-feasibility-and-track-record · Honestly evaluating which in-silico predictions have real clinical track records versus hype, with explicit real_world_status per example.
WORKS 48
Scan and categorize edge cases systematicallyworkflowEngineeringL2
phase1e-scan · Surfacing external unknowns that could block Phase 2 launch through execute-access probing (RUN code, not just read), with optional skeptic verification gated on FAIL only.
WORKS 48
Implement features test-driven with reviewsworkflowEngineeringL2
evolve-implement · Sequential TDD-driven implementation of feature slices with build-log persistence and no parallel execution breaking the lint hook.
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
Benchmark serial agent execution performanceworkflowEngineeringL2
bench-s1-serial · Executing the bench-s1-serial workflow.
WORKS 48
Build deterministic test fixtures for variantsworkflowEngineeringL3
build-config-variant-gates · Executing the build-config-variant-gates workflow.
WORKS 48
Run parallel tasks with barrier synchronizationworkflowEngineeringL2
parallel-basic · Executing the parallel-basic workflow.
WORKS 48
Port code with mandatory layering reviewworkflowEngineeringL3
phase-e-proper-port · Executing the phase-e-proper-port workflow.
WORKS 48
Prepare release changelog and auditworkflowEngineeringL2
release-prep · Executing the release-prep workflow.
WORKS 48
Execute UI cinematics animationsworkflowProductL3
flow-canvas-wave2b-cinematics · Executing the flow-canvas-wave2b-cinematics workflow.
WORKS 48
Hunt and abstract EHR document batchworkflowDataL3
hunt-and-abstract-tranche · Executing the hunt-and-abstract-tranche workflow.
WORKS 48
Search iteratively until exhaustedworkflowDataL2
loop-until-dry · Executing the loop-until-dry workflow.
WORKS 48
Run parallel search strategiesworkflowDataL2
multi-modal-sweep · Executing the multi-modal-sweep workflow.
WORKS 48
Synthesize roadmaps across PM perspectivesworkflowProductL3
pm-council-clawcamp · Executing the pm-council-clawcamp workflow.
WORKS 48
Generate and evaluate code objectivelyworkflowEngineeringL2
pge · Executing the pge workflow.
WORKS 48
Generate project delivery summary reportworkflowEngineeringL2
kiln-report · Executing the kiln-report workflow.
WORKS 48
Find unreferenced code symbolsworkflowEngineeringL2
dead-code-scan · Use when you need a structured dead code scan workflow.
WORKS 48
Stress-test with adversarial challengeworkflowEngineeringL2
wf-grill · Use when you need a structured wf grill workflow.
WORKS 48
Implement feature with adversarial reviewworkflowEngineeringL3
writer-reviewer · Use when you need a structured writer reviewer workflow.
WORKS 48
Deep research OpenSpec with testable specsworkflowProductL3
opsx-propose-deep · Use when you need a structured opsx propose deep workflow.
WORKS 48
Distill daily agent activity digestworkflowOpsL2
agent-daily-digest · Use when you need a structured agent daily digest workflow.
WORKS 48
Implement feature and review iterativelyworkflowEngineeringL3
implement-and-review · Use when you need a structured implement and review workflow.
←page 21 / 24→