The library

gsd:thread · When work spans multiple sessions but doesn't belong to a specific phase and needs persistent context.

triple-loop-learning · When you want autonomous continuous improvement of system instructions based on objective headless benchmarks.

gsd:ui-phase · When starting a frontend phase and need a design specification contract from research to verification.

memory-management · When you need a tiered recall system balancing hot-cache speed with deep semantic search across sessions.

gitnexus-exploring · When learning a large unfamiliar codebase and need execution flows and symbol relationships mapped.

rlm-audit · When you've added new files and need to identify exactly what's missing from the semantic cache.

rlm-cleanup-agent · When files are deleted or moved and the RLM ledger contains stale entries to remove.

gsd:undo · When you need to safely revert phase or plan commits with dependency checking, not blind git reset.

rlm-curator · When you need to distill files into the RLM Summary Ledger and keep the cache in sync with codebase.

rlm-distill-agent · When you have uncached files and need high-quality 1-sentence summaries written to the ledger.

gsd:validate-phase · When a phase is complete but validation coverage is unknown and needs retroactive audit and gap-filling.

rlm-init · When setting up RLM for the first time in a project or adding a new cache profile.

gsd:verify-work · When you want conversational user acceptance testing with automatic diagnosis of found issues.

rlm-search · When searching for architecture, code, or documentation and need O(1) RLM scan before semantic or exact search.

gsd:workstreams · When validating project work and need to execute gsd:validate-phase workflow.

vector-db-audit · When you need O(1) keyword lookup across RLM summaries without semantic search overhead.

vector-db-cleanup · When RLM Phase 1 keyword search is insufficient and semantic nearest-neighbor matching is needed.

vector-db-ingest · When RLM Phase 1/2 results are insufficient and you need precise regex or exact-match lookup.

vector-db-init · When you need to enable semantic search over project code without a remote server.

vector-db-launch · When multiple agents need concurrent read/write access to the vector store.

vector-db-search · When Phase 1 (RLM) returned no match and you need concept-based context retrieval.

audit-plugin-l5 · When you need uncompromising enterprise security and architecture review against a 39-point L4 matrix.

audit-plugin · When validating a Claude Code plugin against 10 structural and security compliance categories.

compile-apm-package · When your target harness requires a single top-level context file instead of distributed skills.

convert-plugin-to-apm · When adding APM governance to an existing plugin without disrupting current workflows.

US-081-pr-fix-skill · When you want to automatically resolve PR review comments, test, and push fixes without manual triage.

create-agentic-workflow · When converting a local skill into a GitHub-native agentic workflow for CI/CD automation.

script-to-node · When creating custom pixel-processing nodes from natural language descriptions without manual JSON.

create-apm-package · When building a new multi-runtime package from scratch with APM governance from day one.

create-azure-agent · When deploying an agent skill as a managed Azure AI Foundry service with Bicep infrastructure.

create-command · When automating repeated workflows with reusable slash commands that scale across the team.

create-docker-skill · When building containerized agent skills with pre-flight environment checks.

human-brainstorm · Unblocking feature roadmaps by surfacing architectural gaps that current implementation could support

create-github-action · Setting up repeatable, version-controlled CI/CD without runtime agent complexity

create-hook · Enforcing invariants or auto-approvals in Claude Code without creating a full skill

create-mcp-integration · Adding hosted service integrations (Slack, GitHub, Postgres) without manual MCP config authoring

create-plugin · Bootstrapping plugin structure with all mandatory bindings in place, including hermes compatibility

create-skill · Creating repeatable agent skills with TDD-ready evaluation structure and discovery-captured trigger phrases

create-stateful-skill · Building multi-step orchestration skills that maintain state across invocations and explicit escalation gates

SKILL.md_UPDATE_PLAN · Tracking doc-drift for skills undergoing major version bumps with feature set changes

create-sub-agent · Bootstrapping specialized agents with explicit permissions and lifecycle hooks instead of generic LLM responses

security-guardrails · Defending lending agents from adversarial manipulation while preserving legitimate borrower interactions

MS-298-ticket-work-skill · Autonomous ticket execution by separating outcome verification (AC) from workflow mechanics (skill)

ecosystem-standards · Pre-publish compliance checks ensuring skills/plugins meet naming, structure, and schema standards

add-admin-route.SKILL · Rapidly adding backend endpoints to Sofia without manual routing boilerplate

eval-autoresearch-fit · Identifying which skills are ready for autonomous improvement loops by assessing eval robustness

fix-plugin-paths · When you need systematic analysis and actionable recommendations.

scope-maintenance-task · When you need systematic analysis and actionable recommendations.

install-apm-package · When you need reproducible, byte-identical deployments with lockfile tracking.

l5-red-team-auditor · When you need uncompromising enterprise security and maturity assessment against 39-point rubric.