The library

competitor-monitor · Competitive intelligence teams running weekly monitoring on 5-15 competitors to surface material product, pricing, and leadership changes.

weekly-review · Preventing OKR drift and detecting energy/skill gaps before they accumulate into quarter-ending surprise.

legal-nda · Applying legal-nda as a specialized, reusable capability.

discovery-call-framework · SaaS AEs and consultants converting cold→warm leads who need repeatable structure to uncover six essentials before demo/pitch.

phase-todo-sweep · Applying phase-todo-sweep as a specialized, reusable capability.

lifetime-classify · Applying lifetime-classify as a specialized, reusable capability.

release-checklist · Applying release-checklist as a specialized, reusable capability.

artifact-eval · Applying artifact-eval as a specialized, reusable capability.

cello-review-only · Applying cello-review-only as a specialized, reusable capability.

security-audit · Multi-domain code quality auditing at scale across partitions.

vue-newsletter · Synthesizing weekly summaries across multiple heterogeneous sources (releases, blogs, social, people) with automated deduplication.

model-arena-daily · Benchmarking multi-tier LLM responses against a canonical prompt with regression detection and cost-efficiency scoring.

shadowkit-redesign · Preserving complex application logic while systematically restying UI to a new design system across multiple components.

shaders-parity-audit · Cross-system feature/data parity validation with section-by-section discrepancy discovery and adversarial verification.

fix-charlie-harness · Coordinating multi-agent workflows with explicit phases, budget guards, and structured JSON output schemas.

figma-landing-1to1-audit · Cross-system feature/data parity validation with section-by-section discrepancy discovery and adversarial verification.

bun-port-style · Implementing, verifying, and fixing artifacts with multi-vote adversarial review in an Implement → Verify → Fix loop.

bug-report · Discovering regressions and feature gaps across a large navigation surface via batched, isolated agent exploration.

fieldatlas-synth · Grounding research idea generation in corpus citations with novelty-checking and feasibility critique.

clean-epic-1662 · Coordinating multi-agent workflows with explicit phases, budget guards, and structured JSON output schemas.

audit-epic-1662 · Cross-system feature/data parity validation with section-by-section discrepancy discovery and adversarial verification.

bug-sweep · Discovering regressions and feature gaps across a large navigation surface via batched, isolated agent exploration.

pitch-atlas-craftsmen-research · Coordinating multi-agent workflows with explicit phases, budget guards, and structured JSON output schemas.

dev-pipeline-continue · Implementing, verifying, and fixing artifacts with multi-vote adversarial review in an Implement → Verify → Fix loop.

benchmark · Measuring performance across configuration variants with automated iteration and winner ranking.

spec-compliance-checker · Checking specification conformance against a canonical contract with phrase-based verification.

pipeline-vs-parallel · Implementing, verifying, and fixing artifacts with multi-vote adversarial review in an Implement → Verify → Fix loop.

phase-e-scopeguard-sweep · Coordinating multi-agent workflows with explicit phases, budget guards, and structured JSON output schemas.

phase-h-ci-tasks · Coordinating multi-agent workflows with explicit phases, budget guards, and structured JSON output schemas.

sessionvault-product-polish · Coordinating multi-agent workflows with explicit phases, budget guards, and structured JSON output schemas.

phase-h-idioms-audit · Cataloging anti-patterns across a codebase in a single pass with enforced coverage.

phase-h-windows-bughunt · Detecting platform-specific bugs (HANDLE leaks, UTF-16 bounds, error code mapping) statically.

phase-g-test-swarm · Massively parallel test crash categorization across shards without reimplement runners.

phase-d-subtree-batch · Staged multi-agent compilation loops with spec-grounded verification.

phase-d-build-queue · Staged multi-agent compilation loops with spec-grounded verification.

phase-d-unsafe-audit · Exposing raw-pointer aliasing bugs that rust-clippy misses and require semantic analysis.

phase-f-reviewed-refactor · Staged multi-agent compilation loops with spec-grounded verification.

review-and-fix-plan · Staged multi-agent compilation loops with spec-grounded verification.

phase-g-test-swarm-isolated · Massively parallel test crash categorization across shards without reimplement runners.

phase-h-main-parity · Staged multi-agent compilation loops with spec-grounded verification.

phase-h-windows-testfix · Detecting platform-specific bugs (HANDLE leaks, UTF-16 bounds, error code mapping) statically.

phase-h-libuv-audit · Verifying uv_* handle lifecycle rules and double-free detection without integration tests.

porting-md-zigleakage · Staged multi-agent compilation loops with spec-grounded verification.

env-ctl-phase1b-vault · Staged multi-agent compilation loops with spec-grounded verification.

deep-research · Adversarial deep research with multi-source verification and ranked evidence synthesis.

generic-harness-object-model-research · Adversarial deep research with multi-source verification and ranked evidence synthesis.

meridian-impl · Staged multi-agent compilation loops with spec-grounded verification.

tools · Staged multi-agent compilation loops with spec-grounded verification.

short_snake_case · Staged multi-agent compilation loops with spec-grounded verification.

doc-drift-fix · Iterative multi-phase workflows with safeguards.