cyberneticlibrary

The library

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

WORKS 57
Validate spec and plan adversariallyworkflowProductEngineeringL3
superpower-validate · Spec/plan validation before build when requirements are vague or dependencies cross multiple systems.
WORKS 55
Migrate UI to ChipGroup componentsworkflowEngineeringL2
chips-badges-migration · Orchestrating multi-phase autonomous workflows where fan-out and synthesis improve outcomes.
WORKS 57
Execute feature sprint autonomouslyworkflowEngineeringL3
execute-contract · Tier 1 feature contracts (3-8 pts, mode C) needing autonomous sprint with fix loops.
WORKS 58
Implement issues with quality auditsworkflowEngineeringL2
rss-issue-sprint · Batching issue implementations with simultaneous quality audits.
WORKS 55
Tune Codex theme iterativelyworkflowEngineeringProductL2
codex-theme-tune · Orchestrating multi-phase autonomous workflows where fan-out and synthesis improve outcomes.
WORKS 57
Tune Antigravity theme iterativelyworkflowEngineeringProductL2
antigravity-theme-tune · Orchestrating multi-phase autonomous workflows where fan-out and synthesis improve outcomes.
WORKS 55
Triage feature scope and designworkflowProductEngineeringL3
fathomdb-v05-feature-triage · Orchestrating multi-phase autonomous workflows where fan-out and synthesis improve outcomes.
WORKS 55
Review JVM code for correctnessworkflowEngineeringL3
adversarial-code-review · Code/MR review across security, performance, conventions with adversarial refutation quorum gates.
WORKS 56
Port C library to Jai shardsworkflowEngineeringL3
10-port-sections · Orchestrating multi-phase autonomous workflows where fan-out and synthesis improve outcomes.
WORKS 57
Run minimal UI test demonstrationworkflowEngineeringL2
ui-test-minimal · Orchestrating multi-phase autonomous workflows where fan-out and synthesis improve outcomes.
WORKS 58
Migrate research workflow to productionworkflowEngineeringOpsL3
weekly-research-workflow-poc · Orchestrating multi-phase autonomous workflows where fan-out and synthesis improve outcomes.
WORKS 55
Audit docs for accuracy and clarityworkflowEngineeringL2
docs-audit · Orchestrating multi-phase autonomous workflows where fan-out and synthesis improve outcomes.
WORKS 60
Hunt bugs with adversarial LLM teamworkflowEngineeringL3
nereids-bug-hunt · Broad defect sweep of the NEREIDS workspace ahead of a release / paper. RUN FROM THE MAIN REPO ROOT (not a .claude/worktrees/ session) so SAMMY primary sources resolve and subagents are not sandboxed away from them. Complements /review-pipeline (which is per-PR-diff + fix + merge gates); this workflow is whole-crate DETECTION only — it finds and locates defects, cross-verifies them across two LLM families, and reports. It does NOT fix anything.
WORKS 59
Audit crawlability and Core Web VitalsskillMarketingEngineeringL2
seo-technical · Ensuring crawlability, mobile-first readiness, Core Web Vitals, and selective AI crawler blocking per brand strategy.
WORKS 58
Set up analytics in Flutter appsskillEngineeringProductL2
firebase-analytics · Implementing analytics tracking for user behavior, screen views, and conversion funnels in production Flutter apps.
WORKS 53
Update GEO-SEO toolkit to latest versionskillOpsEngineeringL2
geo-update · Keeping GEO-SEO toolkit in sync with upstream without manual file management.
WORKS 58
Structure and document Claude Code skillsskillEngineeringL1
write-a-skill · Teams and individuals building reusable workflows in Claude Code who need to document skills in a format that enables agent discovery and execution.
WORKS 58
Route and parallelize architecture workskillEngineeringL3
src · Large codebases with 5+ file changes spanning multiple domains—when parallel architecture design and implementation can run unblocked.
WORKS 55
Deduplicate codebase exhaustivelyworkflowEngineeringL3
phase-h-dedup · Workflow phase h dedup with multi-agent verification.
WORKS 60
Reduce unsafe patterns systematicallyworkflowEngineeringL3
phase-h-unsafe-wrap · Workflow phase h unsafe wrap with multi-agent verification.
WORKS 60
Test workflow executionworkflowEngineeringL2
workflow-slug · Workflow workflow slug with multi-agent verification.
WORKS 57
Execute parallel coder waves with gatesworkflowEngineeringL3
kryptonite-phase12 · Workflow kryptonite phase12 with multi-agent verification.
WORKS 57
Generate project health report with metricscommandEngineeringL2
report · Tech leads and engineering managers running quarterly health reviews who want a one-page snapshot of code quality, velocity, and dependency health.
WORKS 57
Review halmos skill across dimensionsworkflowEngineeringL2
qa-halmos-review · Workflow qa halmos review with multi-agent verification.
WORKS 60
Benchmark sentence segmentation librariesworkflowEngineeringL3
compare-segmenters · Compare this library against other sentence boundary detection libraries on public corpora and get a winner + rationale for every case where they disagree.
WORKS 57
Evaluate skill fitness across portfolioworkflowEngineeringL3
skill-fitness · Workflow skill fitness with multi-agent verification.
WORKS 60
Drive workflow phase to convergenceworkflowEngineeringL3
ldw-phase-runner · Workflow ldw phase runner with multi-agent verification.
WORKS 56
Trace dynamic workflow executionworkflowEngineeringL2
trace-dynamic-workflow · Workflow trace dynamic workflow with multi-agent verification.
WORKS 54
Panel judge architecture decisionsworkflowEngineeringL3
mishkan-architecture-panel · Design decisions where reasoning needs three competing priors evaluated in parallel.
WORKS 55
Stress test and refine planworkflowEngineeringL2
argus-refine-plan · Topologically sorted task execution across human-in-the-loop and agentic work layers.
WORKS 55
Fix performance issues in parallelworkflowEngineeringL3
fix-perf-issues · Complex workflows requiring parallel agents, synthesized judgment, or multi-phase triage.
WORKS 60
Draft and review implementation planworkflowEngineeringL2
codequality-gates-sliceA-plan · Multi-dimensional acceptance criteria requiring independent per-AC verification.
WORKS 54
Review rule adherence with skepticsworkflowEngineeringL2
gate-review · Multi-dimensional acceptance criteria requiring independent per-AC verification.
WORKS 57
Audit plugins against repo conventionsworkflowEngineeringL3
audit-plugins · Triage workflows where items need independent lens-based analysis before synthesis.
WORKS 58
Rank tech debt by criticality and impactworkflowEngineeringL3
tech-debt-triage · Triage workflows where items need independent lens-based analysis before synthesis.
WORKS 58
Implement and verify pending milestonesworkflowProductEngineeringL3
argus-implement · Complex workflows requiring parallel agents, synthesized judgment, or multi-phase triage.
WORKS 59
Multi-agent QA gate for merge decisionsworkflowEngineeringL3
qa · Complex workflows requiring parallel agents, synthesized judgment, or multi-phase triage.
WORKS 57
Grade adversarial test corpus with consensusworkflowEngineeringDataL3
ix-adversarial-llm-panel · Complex workflows requiring parallel agents, synthesized judgment, or multi-phase triage.
WORKS 59
Build stealth LinkedIn scraperworkflowEngineeringSalesL3
build-linkedin-scraper · Complex workflows requiring parallel agents, synthesized judgment, or multi-phase triage.
WORKS 54
Conduct multi-agent security reviewworkflowEngineeringL3
security-review · Multi-dimensional acceptance criteria requiring independent per-AC verification.
WORKS 55
Improve game dictionaries with dual-judge validationworkflowProductEngineeringL3
dictionary-improvement · Complex workflows requiring parallel agents, synthesized judgment, or multi-phase triage.
WORKS 54
Measure software performance comprehensivelyworkflowEngineeringDataL3
measure-performance · Perf fixes where file groups are disjoint and can edit in parallel without race conditions.
WORKS 55
Audit active and parked epicsworkflowProductEngineeringL3
epic-audit · Triage workflows where items need independent lens-based analysis before synthesis.
WORKS 58
Fix code-review findings with iterationworkflowEngineeringL3
fix-findings · Finding subtle bugs or policy violations across large codebases that require consistent multi-agent consensus.
WORKS 55
Analyze speech synthesis gaps per languageworkflowEngineeringDataL3
espeak-audit-all-langs · Finding subtle bugs or policy violations across large codebases that require consistent multi-agent consensus.
WORKS 55
Fix bridge module with adversarial verificationworkflowEngineeringL3
bridge-triple-insurance-fix · Orchestrating multi-phase agent workflows with structured handoff and consensus-driven decision gates.
WORKS 55
Build release from plan with verificationworkflowEngineeringProductL3
release-builder · Decomposing complex release plans into parallel, worktree-isolated producer agents that verify outputs against exit criteria.
WORKS 55
Audit app security and remediate findingsworkflowEngineeringL3
path-warden-security · Finding subtle bugs or policy violations across large codebases that require consistent multi-agent consensus.
WORKS 55
Compare TTS voice quality with human audioworkflowEngineeringDataL3
espeak-audit-tts-vs-human · Finding subtle bugs or policy violations across large codebases that require consistent multi-agent consensus.
WORKS 55
Find and rank type system escapesworkflowEngineeringL3
type-escape-sweep · Orchestrating multi-phase agent workflows with structured handoff and consensus-driven decision gates.
page 4 / 86