The library

gsd:forensics · Understanding why a GSD workflow got stuck or failed, with data-grounded diagnostic findings rather than speculation.

gsd:from-gsd2 · Reverse-migrating legacy GSD-2 projects back to v1 format while preserving completion state and phase hierarchy.

sc-estimate · Planning timelines and resource allocation with transparent confidence levels rather than false precision.

gsd:graphify · Maintaining a queryable knowledge graph of project decisions, artifacts, and relationships without manual documentation.

gsd:health · Validating .planning/ integrity before running major workflow operations, catching configuration drift early.

delaying-tasks · Waiting for external state (CI pipeline, PR status, scheduled check) with bounded polling and clean output.

gsd:inbox · Batch triaging inbox of issues/PRs without manual review of each, surfacing incomplete submissions for rejection.

eigenflux-localtest · Autonomously validating completed changes in EigenFlux without manual test invocation, using source-to-test mapping to run only affected suites.

gsd:ingest-docs · Consolidating pre-existing planning documents (ADRs, PRDs, specs) into a GSD project without losing context or forcing new documentation.

gsd:intel · Maintaining searchable codebase intelligence index across multiple project subsystems.

svelte-engineering.skill · Enforcing Svelte 5 rune patterns and SvelteKit architecture consistency in team projects.

review-design · Catching architecture violations (anti-patterns, security, coupling) before code review.

linear · Automating Linear issue workflows without leaving the terminal or UI.

gsd:map-codebase · Generating first-time codebase documentation via parallel analysis of structure, tech, and risks.

forge · Abstracting GitHub/GitLab/Gitea differences so one workflow works across multiple forge providers.

codex-execpolicy · Defining and validating command execution policies so Codex respects org/project security rules.

deploy-planner · Orchestrating multi-phase rollouts with environment, approval, and risk gates.

fullstack-coder · Shipping end-to-end features (backend + frontend + tests) without context-switching between roles.

gsd:new-workspace · Isolating multi-repo feature work when you need independent .planning/ folders per feature branch.

ti-install-sig · Discovering mruby type landscape when starting a task in unfamiliar dynamic-typed codebases.

issue-triage-sensei-hacker-inav-claude · Quickly identifying readily-solvable issues when managing 100+ open GitHub issues in OSS projects.

graphql-implementation · Building strongly-typed flexible APIs when client query variations beat fixed REST endpoints.

schema-designer · Preventing data integrity issues when schema changes later become prohibitively expensive.

security-auditor-saas · Blocking deployment when OWASP Top 10 vectors would otherwise reach production.

system-architect · Eliminating spaghetti architecture when deliberate choices before coding prevent costly refactors.

test-engineer · Blocking bugs before QA when automated test coverage beats manual testing ROI.

optimize-agent-instructions · Applying Karpathy principles when instruction files drift from behavioral intent.

conductor-implement · Executing structured project tasks when workflow rules and TDD discipline reduce context thrashing.

os-architect · Automatically routing agent/skill evolution requests to the right orchestrator without manual classification.

os-eval-backport · Safely merging improvement-loop edits back to canonical plugin sources with selective review.

os-eval-lab-setup · Bootstrapping isolated test repos with consistent eval harness before autoresearch iterations.

os-eval-runner · Autonomously iterating skill improvements using empirical scoring gates instead of human feedback.

os-evolution-planner · Proposing and executing agent evolution paths (update/create/orchestrate) with structured planning.

os-evolution-verifier · Validating that evolved agents meet their original requirements before applying to production.

gsd:review · Gate-checking workflow completion before advancing to next phase.

os-experiment-log · Durable tracking of agent experiments with structured metadata and cross-run analysis.

gsd:scan · Quick status checkup showing active phase, pending tasks, and system health.

os-improvement-loop · Multi-agent systems needing concurrent eval-driven improvement cycles

os-init · Bootstrapping Agentic OS structure for new multi-agent projects

gsd:ship · Creating PRs and tracking merges after verify-work passes

self-evolution · Self-healing failed selectors and stale scripts via tier-gated edits

gsd:sketch-wrap-up · Distilling throwaway sketches into persistent design skills

todo-check · Pre-flight auditing a file for technical debt before committing

gsd:sketch · Exploring design directions with fast HTML mockup variants

agent-swarm · Partitioning large features into parallel independent sub-tasks

gsd:spec-phase · Clarifying phase requirements with Socratic interview before discuss-phase

dual-loop · Balancing dual concurrent execution cycles with separate eval gates

gsd:spike-wrap-up · Converting research findings into reusable project-local skills

gsd:spike · Fast exploratory research on technical unknowns before planning

orchestrator · Coordinating multi-agent task dispatch across a distributed team