The library

master-adrs-001 · Analyzing architectural decision patterns and identifying gaps in documentation.

gc · Standard git workflow when you need a single command to review, stage (by name), commit, and push safely.

uadf-handoff · Transitioning between sessions when the next agent needs to resume without reading full conversation history.

build · Building Python features with automatic type and style validation as a Stop hook.

marmite · Post-session reflection when you want a training log of YOUR patterns (not the codebase), capturing when you steer vs coast.

tdd · Feature implementation with clear input/output contracts when you want tests to drive design and catch regressions.

new-adr · Documenting architectural choices when you need a standardized decision log that future developers can reference.

new-post · Bilingual blog publishing when you want one-command post creation with automatic slug generation, frontmatter, and dual-language output.

import-from-chatgpt · Research workspace bootstrap when you want to convert a ChatGPT exploration into a structured Tao project.

pr-create · GitHub workflow when you need a PR auto-generated from branch commits and project template conventions.

ns-create · Project anchoring when you need an immutable baseline of success criteria that constrains all future decisions.

ui-session · Frontend teams needing rapid visual feedback loop without manual page reloads or Git complexity.

inspect-db · Developers needing quick schema exploration without writing SQL or GUI tools; safe read-only introspection.

plan-sprint · Teams running time-boxed sprints on modular features where end-to-end vertical slices are critical for demo readiness.

switch-repo · Multi-repo workflows where maintaining distinct contexts without git mutations is essential for context isolation.

move-page · Documentation sites where URL stability matters (SEO, existing links) and bulk link maintenance is manual burden.

doc · R package maintainers avoiding manual .Rd editing and ensuring docs stay in sync with code.

why · Finance/product teams requiring problem validation before spec work; catches missing evidence early.

run · Educational environments where students run exercise scripts without CLI friction.

recreate-pr · Teams receiving multiple rounds of review where a fresh PR with consolidated feedback beats amended commits.

speckit.specify · Agile teams converting informal feature requests into structured specs without heavyweight process overhead.

clarify · Quick clarification before moving to planning; filters out avoidable ambiguity without heavyweight refinement meetings.

commit-and-push · Teams enforcing commit message hygiene and co-authorship tracking without manual trailer editing.

cipher-scan · Security teams auditing TLS server configurations for compliance and known vulnerabilities.

query · Answering questions from existing vault knowledge with librarian rigor and explicit citations.

read-activity-log · Understanding how a tkinter app logs from background threads safely and handles graceful cancellation.

configurar-projeto · Post-clone setup for multi-instance Next.js+AI projects with automated port assignment and GitHub integration.

gsd:scan · Lightweight alternative to full codebase mapping for a single concern area.

new-page · Rapid MDS prototyping page creation with automatic layout grid and component discovery.

compound:learn-that · Converting conversational discoveries into reusable lessons without losing tacit knowledge.

create · Publishing atomic knowledge notes with enforced taxonomy, proper linking, and validation before commit.

char-slim · Slimming verbose character profiles while preserving personality, relationships, and unique traits.

voiceover · Creating quick Darija voiceover scripts for Karim's F2-format short-form content without full kit generation.

cm · Creating intentional, audited Conventional Commits with proper scoping before pushing to origin.

seo-auditor · Bulk documentation SEO improvement across all pages: titles, descriptions, keywords, readability, link integrity, and sitemap consistency.

update-docs · Post-creation workflow ensuring new skills reach all platforms (Codex, Gemini, OpenClaw), marketplace stays current, and docs auto-generate.

ralph_research · Systematic issue research workflow: prioritize, investigate codebase and external sources, synthesize findings, attach to issue and move to review.

harness · Prevent infinite loops and unwanted file changes in autonomous Claude Code sessions via iteration caps, timeouts, protected paths, and required checks.

council · Soliciting diverse perspectives on architecture/tech/implementation decisions by running a query through multiple LLMs and synthesizing a consensus.

gsd:add-todo · Context-preserving task capture during active work: record idea/task without derailing current session, with enough detail for future Claude to understand.

review-the-review · Secondary review gate: catch sycophancy, false positives, and missed issues in bot reviews; converge on approve/request-changes/defer via up to 10 rounds.

func-commit-message · Commit message generation: analyzes staged changes and drafts a message following conventional commit format, seven rules, and imperative mood.

ddd · Multi-phase development workflow: start with requirements, move through specs/plan/implementation/documentation, with explicit approval gates between phases.

git · Enforced git workflow: branch names (type/scope-description), commits (conventional format), avoids destructive ops, detects and prevents secret commits.

release-checklist · Structured release process: pre-release validation, tests/security/docs verification, staging tests, production deployment, post-deploy monitoring, rollback plan.

publisher-x · Turning long-form content into multi-format social media threads with minimal effort

gstack-plan-ceo-review · CEO/founder-level plan review where scope control and ambition calibration matter

vibe-check · Pre-commit quality check when AI agents have contributed code

analysis-learn · Structured onboarding to data analysis workflows with feedback loops and skill progression

validate-consensus · High-stakes design decisions where independent expert review reduces blind spots