Dev & Coding

Forces Claude to use trace-mcp's apply_codemod for any edit pattern repeated 2+ times instead of firing off repetitive Edit calls.

A routing skill that makes Claude use trace-mcp's semantic code tools instead of Read/Grep/Glob, cutting tokens while improving accuracy.

A skill that turns your CLAUDE.md into AGENTS.md and wraps OpenAI Codex CLI calls so Claude Code and Codex work together.

A short rule set that tells Claude to delegate implementation work to sub-agents so the main conversation keeps its context.

Convenes a panel of Feynman, Ada, Torvalds, Popper, Occam, Nietzsche and Wittgenstein to run an evidence-based, structured debate on architecture, debugging, refactoring and code review.

One-command code structure and blast-radius queries to run before you refactor anything.

Playwright POM patterns plus a decision framework for choosing between page objects, fixtures, and helpers.

Step-by-step guides for migrating a test suite from Cypress or Selenium/WebDriver to Playwright.

A skill that guides asdf (asdf-vm) installation, plugin management, .tool-versions workflows, and shim troubleshooting.

A skill that scans source code for endpoints and produces Markdown or OpenAPI 3.0 API documentation.

Enforces a five-stage ship pipeline — verify gate, commit strategy, docs, PR, human-approved merge — with code integrity checks.

A governance gate skill that reads harness.json and audits AI-generated project docs (PRD, spec, progress ledger) rule by rule, then emits a fix list.

Measures whether your Playwright, Puppeteer, Selenium or CDP browser presents a self-consistent fingerprint, scoring an existing Page object in place.

A rigid, step-by-step release orchestrator for bundle-plugins: pre-flight audits, doc sync, version bump, CHANGELOG, tag, and GitHub Release.

A disciplined refactoring playbook that drives trace-mcp tools to assess risk, map impact, rename atomically, and verify results.

A skill that designs serverless-first AWS architectures, drafts IaC templates, and reviews cost and security.

Reconstructs where your work stands by mining intent, decisions and rejected approaches from git commit history.

Gate your CI build on browser-fingerprint regressions using liarjs baselines and score floors.

Turns a vague "I want to package my skills" idea into an approved design document through a three-phase interview, then orchestrates scaffolding, authoring, wiring, and auditing.

A hybrid workflow skill for writing, completing, integrating, and improving SKILL.md files and agent definitions with enforced conventions and a lint step.