The library

crunch · Escaping rote algebra after conceptual understanding is locked in via /learn

add-skill · Incrementally building a curated skills portfolio without manual array formatting

evaluate-skill · Rapid quality assessment of buddy skills before shipping

deploy · Preventing silent production bugs by enforcing code quality and config checks before deploy

design · Converting vague user stories into implementation-ready design specs with no designer follow-up

hermit · Orchestrating parallel work on multiple independent issues without waiting for serial completion

verify · Catching convention mismatches and bulk-boundary inconsistencies in advanced mathematics

devspark.quickfix · Shipping rapid hotfixes while staying aligned with project constitution

implement_plan · Executing multi-phase technical implementations with built-in phase verification and pause points

fix-bug · Rapidly fixing startup/tooling bugs without broad code exploration

trace · Finding where a feature or bug lives by tracing the complete data flow with file:line accuracy

docs · Keeping documentation in sync with code changes across the entire project

create-skill · Authoring new agent skills that follow Cursor conventions without manual boilerplate

bootstrap · Starting work in a new session with full context awareness

doit.roadmapit · Building prioritized product roadmaps aligned with constitution principles

summary · Capturing session work products (code reviews, fixes, findings) immediately after completion without manual re-scanning.

release · Multi-platform Debian-based software releases requiring coordinated PPA, PyPI, Homebrew, and GitHub synchronization with RC iteration.

fix-grammar · Light grammar-only fixes on blog posts before publication; simple file-level corrections without structural changes.

tdd · Tasks requiring disciplined test-first development with explicit Red-Green-Refactor cycles and framework-agnostic guidance.

prune-resume · Extending long-running Claude Code sessions by pruning token-heavy conversation history while preserving session context and resuming automatically.

start-18-2.en · Structured product management workflow where requirements must be extracted from customer research and prioritized using MoSCoW method within a single lesson session.

rss-add · Building tech-weekly collections from multiple RSS feeds with automatic categorization and no manual file creation.

bump-ruby-wasm · Coordinated Ruby patch bumps in Rails+WASM projects where version changes cascade across build config, Rust toolchain, and CI cache invalidation.

debug-pipeline · Rapid triage of multi-stage data pipeline failures in production with clear diagnostic separation per pipeline stage.

check-security · Pre-launch or post-incident Flutter security audits with scored rubric and priority-ranked remediations tailored to French/multilingual teams.

library · Centralized contract clause and document management with full lifecycle (approval → deprecation → archive) and semantic search across large clause libraries.

deslop · Pre-merge cleanup of AI-generated code that introduced verbose comments, unnecessary error handling, or type-unsafe patterns inconsistent with codebase norms.

speckit.implement · Large feature implementations with interdependent tasks, spec-driven contracts, and multi-stage quality gates (setup, test, build, integration, polish).

memcord-read · Quick memory retrieval during a session without manual slot name specification when project binding is configured.

pwned · Structured post-exploitation of compromised systems with automated privilege escalation detection, credential harvesting, and domain reconnaissance.

new-dmn-check · Rapid scaffold of new DMN-based business rules (eligibility checks) with corresponding API tests in library-api without manual XML/Bruno setup.

fix-build · Quick resolution of typical TypeScript type errors in AxioDB builds without deep language knowledge.

spec-init · Creating language-agnostic single-source-of-truth specifications for new projects with enforced contracts and versioning.

import-sprint-story · Bulk history extraction from Azure DevOps sprints with complete revision tracking and external relations (commits, PRs) for archival or migration.

2_research · Objective technical investigations in large codebases requiring evidence-based answers to specific architectural or behavioral questions.

teaching · When you need structured, calibrated teaching with progress tracking and real-time Q&A capture

tasks-spec · When you have a feature design doc and need to break it into parallel-executable LLM-friendly tasks

brainstorm · When you want structured criticism and risk analysis BEFORE coding anything

coverage · When you must enforce 100% coverage on safety-critical functions (tree operations)

jira:prepare · When you need to break a large Jira epic into executable subtasks WITH a design doc in Confluence

build-debug · When you need incremental Debug builds to test changes without Release overhead

feedback · When you have GitHub review feedback and want to apply fixes and mark comments resolved

devlyn.resolve · When you have a mysterious bug and need deep root-cause analysis with test-driven validation

hallucination-check · When LLM-generated PRs add new framework names and you need to catch AI hallucinations before merge

incident · When you have a production incident and need to create properly-escalated tickets immediately

close-day · When you need a complete end-of-day wrap with email→meeting routing, transcript capture, and prep

create-pr · When you have UI changes committed and want to auto-generate desktop+mobile screenshots in the PR

finalize · When you've built a feature through iterations and want to remove all experimental branches

sync · When you need to apply pending migrations and verify database consistency

reins-add-constraint · When you need to add new validation/constraint rules to control system behavior