The library

nested-workflow · Decomposing large orchestrations into reusable sub-workflows without duplicate concurrency budgets.

mock-review · Testing workflow structure and StructuredOutput schemas without cloud API costs.

mine-rules · Converting informal requirements into machine-readable rule sets.

howto-planning · Creating detailed instructional content with clear step progressions.

nimbus-landing-redesign · Design iteration cycles with rapid validation via A/B testing.

batch-fix-todo · Large-scale codebase cleanup targeting scattered markers.

sbc-canvas-config-gen-review · Complex embedded system configuration generation with multi-layer validation.

prior-art · Patent landscape and novelty analysis for IP assessment.

doc-audit · Systematic documentation quality assurance and gap identification.

daily-system-review · Monitoring AI ecosystem changes across vendor + community + internal tiers daily

presence-claims-audit · Verifying that docs genuinely document six key areas vs just existing as files

code-review · Reviewing files across multiple lenses (bugs, security, style) with adversarial verification

bug-discovery · Iteratively finding bugs from multiple angles (logic, null-safety, concurrency) with dedup

test-audit-llm · Auditing test quality on read-only lenses (faithfulness, intent, coverage, smell)

sota-scan-fanout · Scanning research papers in parallel across multiple sources

wf-swarm-converge · Converging multiple specialized agents into a unified swarm decision

writing-plans · Generating structured writing plans with outline and topic decomposition

classify-route · Classifying routing decisions dynamically based on context

judge-panel · Assembling diverse expert perspectives in a structured panel verdict

design-review · Systematically reviewing design artifacts across consistency and usability

lang-content-generate · Content localization when translating a spec into multiple languages (often with cultural/regional variants).

skill-improver-batch · Skill refinement when you have many skills needing updates based on failure logs or user feedback.

test-analysis · Debugging tests when you need to distinguish flakiness from real failures and identify patterns.

unit-test-gen · Test coverage when you have code without tests and need to bootstrap test suite.

load-test · Finding capacity limits through stepped load with automatic breaking-point detection.

fixture-dynamic-roster-missing-skill · Multi-phase orchestration with agent parallelism and structured verification.

wf-brainstorm · Synthesizing design decisions across conflicting expert perspectives.

cheap-pass-100 · High-volume batch screening with fixed concurrent worker capacity.

trace-resume-model · Distinguishing prefix vs. content-addressed workflow resumption models.

feature-dev · Multi-gate feature development with human approval at requirements and architecture phases.

parallel-file-write-with-verify · Writing many files in parallel then auditing for quality metrics.

gate · Code review with parallel specialists and adversarial skepticism.

go-audit-fix · Automated auditing and fixing of Go code issues.

type-field-coverage · Measuring type coverage across large codebases.

triage_quarantine · Isolating failing cases for targeted root-cause investigation.

docking-workflow · Integrating components with automatic verification.

fd-understand-codebase · Building knowledge of unfamiliar codebases through structured exploration.

assess-investigate · Code review with parallel specialists and adversarial skepticism.

g3-readiness-review · Rigorously vetting academic manuscripts through multiple independent reviewer lenses before submission, with explicit synthesis of conflicts and prioritized fixes.

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.

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.

evolve-implement · Sequential TDD-driven implementation of feature slices with build-log persistence and no parallel execution breaking the lint hook.

bench-s1-serial · Executing the bench-s1-serial workflow.

parallel-basic · Executing the parallel-basic workflow.

release-prep · Executing the release-prep workflow.

loop-until-dry · Executing the loop-until-dry workflow.

multi-modal-sweep · Executing the multi-modal-sweep workflow.

pge · Executing the pge workflow.

kiln-report · Executing the kiln-report workflow.

dead-code-scan · Use when you need a structured dead code scan workflow.