Claude_Code_Boilerplate_Framework

Ask which skill or flow fits your situation. A router over the user-invoked skills in this repo.

Stages all changes and generates a lean Conventional Commits message via caveman-commit — user reviews and commits manually. Triggers on any commit intent: "commit", "stage my changes", "ready to push", "let's commit", "make a commit", "commit this", "push changes", "squash and commit", or any variation. Use whenever the user signals they're done with changes and ready to commit, even if they don't mention "message" or "caveman". Does NOT run git commit — outputs a ready-to-run command for the user to execute after review.

Autonomous ML research - agent modifies GPT training code, runs 5-min experiments, keeps improvements

Always use browser-harness for any web interaction: automation, scraping, testing, or site/app work.

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

AI spend analytics — see where your token budget goes by task, model, tool, and project across 31 AI coding tools including Claude Code. Use when the user asks about AI costs, token usage, spend breakdown, or wants to optimize their AI budget.

A standalone adversarial PLAN-review loop where Claude Code (builder) and OpenAI Codex (read-only critic) tag-team an implementation plan before any code is written. Use this when you ALREADY have a plan or a clear idea and just want the cross-model stress-test — no requirements interview first. Claude drafts/loads the plan into PLAN.md, Codex reviews it in a read-only sandbox and returns VERDICT:APPROVED or VERDICT:REVISE, Claude revises and re-submits to the SAME Codex session (context preserved) until APPROVED or a configurable MAX_ROUNDS cap is hit. Human approves the converged plan before code. Use when the user says "/codex-review", "codex review my plan", "have Codex review my plan", "argue this plan with Codex", "adversarial plan review", "make Claude and Codex argue/fight over the plan", or is about to build something high-stakes (auth, schema, concurrency, migrations, payments) and wants a second-model sanity check on the PLAN before implementation. For a guided requirements interview BEFORE the rev

Full memory hygiene cycle — compresses memory-sessions.md, deduplicates memory-decisions.md, and syncs key project facts to the memory MCP graph. Run monthly or when context feels heavy.

Turn a loose idea into a sequenced map of investigation tickets, then drive them to resolution one at a time.

Delegate tasks to OpenSpace — a full-stack autonomous worker for coding, DevOps, web research, and desktop automation, backed by an extensive MCP tool and skill library. Skills auto-improve through use, reducing token consumption over time. A cloud community lets agents share and collectively evolve reusable skills.

Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".

Load a ready-made brand design system (DESIGN.md) from the awesome-design-md collection into your project. 73 brands available including Linear, Stripe, Vercel, Notion, Figma, Spotify, Tesla, Supabase, and more. Use when the user wants to build a UI that looks like a known brand, wants to use a specific company's design language as a reference, or says things like 'make it look like Linear', 'use Stripe's design system', 'build something Notion-style', 'I want the Vercel aesthetic', or names any specific brand as a visual reference.

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.

Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.

Extract the full design language from any website URL. Produces 8 output files including AI-optimized markdown, visual HTML preview, Tailwind config, React theme, shadcn/ui theme, Figma variables, W3C design tokens, and CSS variables. Also runs WCAG accessibility scoring. Use when user says 'extract design', 'get design system', 'design language', 'design tokens', 'what colors/fonts does this site use', or '/extract-design'.

Inventory all currently installed skills and plugins. Shows what's in ~/.claude/skills/ (global) and .claude/skills/ (project), with descriptions from each SKILL.md. Cross-references with enabled plugins from settings.json. Use when you want to know what skills/plugins are available in the current environment. Triggers: "what skills do I have", "list my skills", "what plugins are installed", "show installed skills", "what commands are available", "/find-skills"

Web scraping, site crawling, URL discovery, web search with content extraction, and AI-powered structured data extraction using Firecrawl. Invoke this skill whenever the user wants to scrape a page, extract content from a URL, crawl a website across multiple pages, search the web and retrieve page content, map all URLs on a domain, or pull structured data from web sources. Use it even for casual requests like "get the content from this site", "scrape this page for me", "crawl docs.example.com", "search the web for X and extract the results", or "what's on this URL" — any time web content needs to land in the session.

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

Two-act plan hardening. ACT 1 (you ↔ Claude) — Claude interviews you relentlessly about a plan or design, one question at a time, recommending an answer for each and exploring the codebase when it can answer itself, until every branch of the decision tree is resolved. ACT 2 (Claude ↔ Codex) — Claude writes the locked plan to PLAN.md and OpenAI Codex adversarially reviews it in a read-only sandbox (VERDICT:APPROVED/REVISE), Claude revises and re-submits to the SAME Codex session until APPROVED or a MAX_ROUNDS cap, then you sign off before any code. Use when the user says "/grill-me-codex", "grill me then have codex review", "grill me and stress-test the plan", "interview me about this plan then get a second model on it", or is about to build something high-stakes (auth, schema, concurrency, migrations, payments) and wants both alignment AND a cross-model sanity check before implementation. Builds on Matt Pocock's grill-me (MIT). For the docs-aware variant use /grill-with-docs-codex; if you already have a plan

A relentless interview to sharpen a plan or design.

Two-act plan hardening with living documentation. ACT 1 (you ↔ Claude) — Claude interviews you relentlessly about a plan, one question at a time, challenging it against your project's existing domain model and glossary (CONTEXT.md), sharpening fuzzy terms, stress-testing with concrete scenarios, cross-referencing code, and updating CONTEXT.md + ADRs inline as decisions crystallise. ACT 2 (Claude ↔ Codex) — Claude writes the locked plan to PLAN.md and OpenAI Codex adversarially reviews it in a read-only sandbox (VERDICT:APPROVED/REVISE), Claude revises and re-submits to the SAME Codex session until APPROVED or a MAX_ROUNDS cap, then you sign off before any code. Use when the user says "/grill-with-docs-codex", "grill me against the docs then have codex review", "stress-test this against our domain model then get a second model on it", or is about to build something high-stakes in a project with established terminology/ADRs and wants alignment, documentation, AND a cross-model sanity check. Builds on Matt Pococ

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.

Compact the current conversation into a handoff document for another agent to pick up.

Implement a piece of work based on a PRD or set of issues.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Graph-based RAG system for knowledge extraction and Q&A

Grill me about specs for the workflows I want to build, within this workspace.

Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.

Google NotebookLM integration - create notebooks, add sources, generate AI content (podcasts, quizzes, mind maps, briefings, slides), query notebooks, run research agents, and manage research workflows

Search, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, create, or organize notes in Obsidian.

Self-evolving skill system - skills that auto-fix, auto-improve, and auto-learn from usage. Provides collective intelligence where agents share improvements, 46% token reduction through skill evolution, and quality monitoring that tracks performance. Use for complex multi-step tasks, skill evolution, or accessing cloud skill community.

Browser automation via Playwright CLI — screenshots, scraping JS-rendered pages, PDF generation, link extraction. Runs directly via Bash (no MCP server, no token overhead).

Build a throwaway prototype to flesh out a design — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route.

Interactive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues. Explores the codebase in the background for context and domain language. Use when user wants to report bugs, do QA, file issues conversationally, or mentions "QA session".

Create a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue. Use when user wants to plan a refactor, create a refactoring RFC, or break a refactor into safe incremental steps.

Use when you need to resolve an in-progress git merge/rebase conflict.

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

Use when someone asks to roast an idea, pressure-test or stress-test an idea, validate a business idea, "convene the council", get a brutal second opinion before building something, or says "/roast". Spins up a 5-persona council that attacks the idea from every angle, then a Judge returns one GO / RESHAPE / KILL verdict with the cheapest test to de-risk it.