Menu
SkillsMP has collected 71 skills from kitfunso/claude-config. Open a skill to review its source and details.
Showing 40 of 71 collected skills.
Experiential-RL orchestrator that runs a problem from idea generation through ship with auto-critic gates, trajectory logging to SQLite, and per-episode learning. Wraps /dev-framework. Use when asked to "run an RL episode", "/dev-framework-rl", "solve this…
9-stage dev workflow with auto project-type detection and phase-aware overlays. Routes through discover→scaffold→plan→execute→verify→review→ship→deploy→learn with gates appropriate to UI/AI/backend/quant/CLI/library/mobile projects. Use when starting a new…
Maximize agent capability by spawning well-briefed sub-agents, using every available resource, and verifying everything before acceptance. Use when tackling complex or high-stakes tasks that demand thoroughness.
Full commodity model improvement workflow — from audit through exhaustive feature engineering, two-stage selection, Optuna optimization, multi-layer validation, data source verification, and production deployment. Use PROACTIVELY when the user asks to…
Rigorous development protocol for predictive models on market/time-series data (small samples, overlapping windows, point-in-time data). Use when building, validating, searching features for, or promoting any forecasting model on financial or time-series…
Review all changes made in the current session for mistakes, missed requirements, and regressions. Use when the user asks to review changes, check work, or verify correctness before wrapping up — including any phrasing like "please review your changes and…
Use when you have a spec or requirements for a multi-step task, before touching code
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or…
OpenAI Codex CLI wrapper — three modes. Code review: independent diff review via codex review with pass/fail gate. Challenge: adversarial mode that tries to break your code. Consult: ask codex anything with session continuity for follow-ups. The "200 IQ…
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or…
Give clear, numbered, click-by-click instructions for doing something in a graphical interface — Windows, a browser, Outlook, Excel, VS Code, the Airflow web UI, Bitbucket, an internal web app, or any other GUI. Use this whenever the user asks "how do I ...",…
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…
Fixed plain-English format for reporting ANY issue, blocker, or side-discovery found during work. Fires automatically whenever an issue must be told to the user, and whenever the user asks "what's left / what's remaining / what am I missing". Created…
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
Suggest which skill(s) to use for a task — a skill router. Use whenever the user asks "what skill should I use", "which skill", "is there a skill for X", "what's the right workflow for this", "how should I approach this", or describes a task and wants routing…
Plain-English debrief. Use when the user asks "wtf is X", "what did you do", "why did we build this", "do we need this", "explain what happened", "where are we", or invokes /wtf or /wtf status. Explains recent work, a named thing (repo, commit, page, plan,…
Patterns for autonomous agent loops — sequential pipelines, parallel generation, continuous PR loops, and de-sloppify passes. Use when setting up automated workflows, CI/CD agent loops, batch processing with Claude, or multi-agent orchestration. Covers loop…
Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final…
Cross-model benchmark for gstack skills. Runs the same prompt through Claude, GPT (via Codex CLI), and Gemini side-by-side — compares latency, tokens, cost, and optionally quality via LLM judge. Answers "which model is actually best for this skill?" with data…
Performance regression detection using the browse daemon. Establishes baselines for page load times, Core Web Vitals, and resource sizes. Compares before/after on every PR. Tracks performance trends over time. Use when: "performance", "benchmark", "page…
Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element…
Bump iOS/Android build numbers, build the Android .aab bundle, commit and push. Use this skill whenever the user says 'build release', 'bump build', 'build aab', 'bump and push', 'bump ios build number', 'build the aab file', or any combination of bumping…
Use when the user wants a realtime or near-realtime bridge to Claude Code from another agent, script, terminal, or workflow. Provides a JSONL mailbox protocol and helper scripts for sending prompts to `claude -p` and reading responses.
Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in. Opens a visible browser window where you can watch every action in real time. The sidebar shows a live activity feed and chat. Anti-bot stealth built in. Use when asked to…
Pattern for caching expensive file operations using SHA-256 content hashes instead of file paths. Use when building data pipelines that process files (PDF parsing, OCR, image analysis, signal computation) and need caching. File rename = cache hit. Content…
Save working context. Captures git state, decisions made, and remaining work so any future session can pick up without losing a beat. Use when asked to "save progress", "save state", "context save", or "save my work". Pair with /context-restore to resume…
Analyze and mimic the writing style, hooks, voice, and patterns of successful creators from your Airtable database and content frameworks. Match creator voice based on audience, platform, and content type. Use when testing different voices, creating content…
Chief Security Officer mode. Infrastructure-first security audit: secrets archaeology, dependency supply chain, CI/CD pipeline security, LLM/AI security, skill supply chain scanning, plus OWASP Top 10, STRIDE threat modeling, and active verification. Two…
Two-pass development pattern for cleaner output. Use after implementing a large feature, complex refactor, or any substantial code change. Separates implementation from cleanup for better results. Two focused agents beat one constrained agent.
Design consultation: understands your product, researches the landscape, proposes a complete design system (aesthetic, typography, color, layout, spacing, motion), and generates font+color preview pages. Creates DESIGN.md as your project's design source of…
Design finalization: generates production-quality Pretext-native HTML/CSS. Works with approved mockups from /design-shotgun, CEO plans from /plan-ceo-review, design review context from /plan-design-review, or from scratch with a user description. Text…
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after…
Live developer experience audit. Uses the browse tool to actually TEST the developer experience: navigates docs, tries the getting started flow, times TTHW, screenshots error messages, evaluates CLI help text. Produces a DX scorecard with evidence. Compares…
Post-ship documentation update. Reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped, polishes CHANGELOG voice, cleans up TODOS, and optionally bumps VERSION. Use when asked to "update the…
Eval-Driven Development (EDD) — treating evals as unit tests for AI-assisted development. Use when building or modifying AI workflows, agent pipelines, prompt engineering, or any feature where output quality needs measurement. Define success criteria BEFORE…
Combine multiple content frameworks (viral hooks + title patterns + AI video structures) for compound engagement effects. Layers persuasion techniques to create long-form content, video scripts, or multi-platform campaigns. Use when single frameworks aren't…
Restrict file edits to a specific directory for the session. Blocks Edit and Write outside the allowed path. Use when debugging to prevent accidentally "fixing" unrelated code, or when you want to scope changes to one module. Use when asked to "freeze",…
Full safety mode: destructive command warnings + directory-scoped edits. Combines /careful (warns before rm -rf, DROP TABLE, force-push, etc.) with /freeze (blocks edits outside a specified directory). Use for maximum safety when touching prod or debugging…
Systematic debugging with root cause investigation. Four phases: investigate, analyze, hypothesize, implement. Iron Law: no fixes without root cause. Use when asked to "debug this", "fix this bug", "why is this broken", "investigate this error", or "root…
Land and deploy workflow. Merges the PR, waits for CI and deploy, verifies production health via canary checks. Takes over after /ship creates the PR. Use when: "merge", "land", "deploy", "merge and verify", "land it", "ship it to production". (gstack)