The library

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

no effect
Run multi-model council debate engineworkflowProductEngineeringL3+2pp measured
council-engine · Multi-model, multi-persona analysis of complex questions with synthesized verdicts.
works
Audit technical SEO for AI crawlabilityskillMarketingEngineeringL2+4pp measured
geo-technical · When GEO performance is low and you suspect technical issues like JS-rendering or AI crawler blocking in robots.txt.
hurts
Analyze coding growth and patternsskillEngineeringL2-4pp measured
developer-growth-analysis · Developers who want structured, evidence-based feedback on their work growth without waiting for code reviews, using their actual recent project history as the signal.
hurts
Automate code review on Bitbucketmcp_serverEngineeringL2-13pp measured
bitbucket-mcp-server · Code review and PR workflows on Bitbucket Cloud or Server.
hurts
Audit code quality security in CI pipelinesmcp_serverEngineeringL2-4pp measured
codacy-mcp · Continuous integration pipelines auditing code quality and security across teams.
untested
Audit milestones with adversarial reviewworkflowOpsEngineeringL3
wf-milestone-audit · Accelerating milestone validation with parallel dimension checks and adversarial bias detection.
untested
Generate code review reportsworkflowEngineeringL2
rpt-' + taskname + ' · Converting natural task commands into verified deterministic Workflow scripts with full auditability.
untested
Contribute code features end-to-endworkflowEngineeringL2
contribute-card · Automating AI-driven Magic card implementation with full plan-implement-review-verify gating.
untested
Audit codebases for security and performanceworkflowEngineeringOpsL3
code_audit · Parallel 3-phase security/style/synthesis audit with cross-file pattern detection.
untested
Review code via distributed councilworkflowEngineeringL3
council-round · Multi-perspective code review over complex PRs using adversarial 11-category dimension framework.
untested
Scan and fix AI patterns deterministicallyworkflowEngineeringOpsL4
de-ai-pipeline · Data-driven de-AI fix loop where detection is deterministic and fixing is AI-driven and bounded.
untested
Plan, code, and review with specialist agentsworkflowEngineeringL4
role-pipeline · Landing specialized sub-agents on specific models (opus/composer/codex) without turn-by-turn driving.
untested
Develop from specifications with review loopsworkflowEngineeringProductL4
spec-driven-dev · Driving code generation from formal specs ensuring spec-code correspondence.
untested
Analyze repository structure and modulesworkflowEngineeringL2
inspect_project · Understanding project topology and dependency flows for refactoring planning.
untested
Fix documentation and API drift weeklyworkflowEngineeringL3
doc-drift-fix · Keeping docs synchronized with code via automated drift detection and repair.
untested
Engineer portable OSS harness workflowworkflowEngineeringL3
oss-harness-engineering-workflow · Setting up comprehensive OSS testing infrastructure with reproducible CI.
untested
Audit patch health and robustnessworkflowEngineeringL3
patch-audit · Validating patches pre-merge against security, style, and breaking-change criteria.
untested
Dispatch and synthesize specialist teamsworkflowEngineeringL3
fan-out-workflow · Parallelizing independent specialist reviews where final synthesis is budget-aware.
untested
Audit workflow architecture and patternsworkflowEngineeringL3
wc-audit · Discovering quality gaps across multiple architecture and compliance dimensions.
untested
Implement and review rulebook backlogworkflowEngineeringL3
rulebook-driver · Implementing backlog items with enforced SDD+TDD gates and auto-commit.
untested
Run complete QA cycle phasesworkflowEngineeringL3
qa · Discovering and fixing bugs before ship with parallel test orchestration.
untested
Validate legacy to modern stack migrationworkflowEngineeringL3
migration-audit · Discovering quality gaps across multiple architecture and compliance dimensions.
untested
Document package API and extensibilityworkflowEngineeringL3
understand-package-api · Executing complex multi-phase workflows with typed outputs.
untested
Execute release checkpoint phasesworkflowEngineeringL3
release-checkpoint · Executing complex multi-phase workflows with typed outputs.
untested
Verify spec citations and sourcesworkflowEngineeringL3
bier-spec-audit · Discovering quality gaps across multiple architecture and compliance dimensions.
untested
Audit view and edit block parityworkflowEngineeringL3
view-edit-parity · Executing complex multi-phase workflows with typed outputs.
untested
Run parallel sprint agentsworkflowEngineeringL3
daily-improvement-v4-sprint · Executing complex multi-phase workflows with typed outputs.
untested
Benchmark harness on capability questionsworkflowEngineeringL3
hle-15-ablation · Executing complex multi-phase workflows with typed outputs.
untested
Benchmark capability across hardwareworkflowEngineeringL3
bench-capability-sprint-23 · Executing complex multi-phase workflows with typed outputs.
untested
Prepare release documentationworkflowEngineeringL2
release-prep-phase2 · Executing complex multi-phase workflows with typed outputs.
untested
Build deterministic n8n workflowsworkflowEngineeringL4
build-workflow-v2-greenfield · Executing complex multi-phase workflows with typed outputs.
untested
Orchestrate n8n workflow stacksworkflowEngineeringL4
build-stack-v2 · Shipping deterministic, contract-enforced multi-workflow stacks with bottom-up decomposition and enforced build order via code, not model discretion.
untested
Multi-agent code review workflowworkflowEngineeringL3
triptych · Blocking unsafe SceneView merges with enforced multi-lens coverage (correctness, API, parity, UX, safety) and a serial visual QA gate that prevents device-contention race conditions.
untested
Parallel adversarial code reviewworkflowEngineeringL3
review-fanout · Autonomous merge gates for SceneView PRs: reviewers catch issues, adversarial verify filters false positives, breaking-API change blocks auto-merge with traceback.
untested
Verify live artifact stateworkflowEngineeringL3
store-status · Verifying real live artifact availability after CI passes; CI-green is never proof of live for app stores, CDN, and package registries.
untested
Generate workshop slides and notesworkflowEngineeringOpsL3
workshop-generate · Generating workshop slides in phases: per-SECTION fan-out enforces intra-section flow and composability; assembly gate catches compile errors before marking success.
untested
Run parallel area auditsworkflowEngineeringOpsL3
area-audit · Fast multi-perspective code audits with adversarial filtering of false positives; HIGH findings must be independently verified before inclusion in report.
untested
Event emitter workflowworkflowEngineeringL2
emitter · Compiling high-level workflow IR specifications into executable Claude Code scripts with automatic phase ordering and schema declaration emission.
untested
Drive OpenSpec lifecycleworkflowEngineeringL3
openspec-lifecycle · Managing multi-stage product lifecycles with validation gates between phases.
untested
Monitor upstream documentation changesworkflowEngineeringL3
forge-watch · Multi-phase projects requiring parallel specialist execution and cross-stage coordination.
untested
Implement boilerplate hardening planworkflowEngineeringL3
boilerplate-hardening · Multi-phase projects requiring parallel specialist execution and cross-stage coordination.
untested
Shrink graph with compact IDsworkflowEngineeringL4
graph-symbol-ids · Multi-phase projects requiring parallel specialist execution and cross-stage coordination.
untested
Execute multi-wave implementation plansworkflowEngineeringL3
execute-plan · Managing multi-stage product lifecycles with validation gates between phases.
untested
Self-improving development workflowworkflowEngineeringL4
learning-anything-develop-flow · Managing multi-stage product lifecycles with validation gates between phases.
untested
Self-improve deepseek CLI appworkflowEngineeringL4
deepseek-cli-self-improve · Managing multi-stage product lifecycles with validation gates between phases.
untested
Ship agenthive v0.1.0 releaseworkflowEngineeringL4
ship-agenthive-v0.1.0 · Orchestrating multi-month release cycles with deterministic phase gates and artifact verification
untested
Verify merged PRs integrate cleanlyworkflowEngineeringL3
harmony · Catching union-breakage no single PR review sees after parallel merge window closes
untested
Run design-to-spec workflowworkflowProductEngineeringL4
az-design-room · Featured lore design and reveal-gate strategy where creative direction + safety must coexist
untested
Adjudicate agent code reviewsworkflowEngineeringL3
review-council · Architecture reviews and security audits where diverse lenses + adversarial code-tracing beats single-reviewer cost/coverage tradeoff
untested
Scaffold eight-role dev pipelineworkflowEngineeringOpsL4
dev-team-pipeline · End-to-end feature delivery when structured handoff-by-file-path and invariant gates matter more than ad-hoc coordination
page 1 / 86