Claude Skills for developers
PR descriptions, code review, test generation, postmortems, ADRs, on-call runbooks, migration plans. The engineering workflow as installable Claude skills.
How to install
Claude Code (CLI): Download the pack, then unzip into your skills folder.
mkdir -p ~/.claude/skills
unzip ~/Downloads/developer-pack.zip -d ~/.claude/skills/For project-only skills, use .claude/skills/ in your repo root instead. Restart Claude Code (or the session) and the skills become available.
Claude.ai (web): Upload via Settings → Skills (where supported on your plan).
Skills in this pack
PR Description Writer
Generates a PR description from a diff — what changed, why, how to test, risks.
Code Review Helper
Reviews a diff for bugs, edge cases, naming, and test coverage. Direct, not nitpicky.
Test Generator
Generates unit/integration tests for a function or module — happy path, edge cases, failures.
ADR Writer
Writes an Architecture Decision Record — context, decision, alternatives, consequences.
Postmortem Writer
Writes a blameless postmortem from incident notes — timeline, root cause, action items.
On-call Runbook Builder
Builds a runbook for a specific alert — symptoms, diagnosis, remediation, escalation.
Migration Plan Drafter
Drafts a phased migration plan — risks, rollback, dual-run period. No big-bang switches.
Refactor Planner
Plans a refactor as small reversible steps — what changes per step, what to test between.
Bug Repro Builder
Builds a minimal reproducible example from a bug report — strips noise, isolates the failure.
API Documentation Writer
Documents an API endpoint or library function — examples, errors, edge cases.
Commit Message Writer
Generates conventional commit messages from staged changes — subject + body, why-not-what.
Release Notes Writer
Generates user-facing release notes from merged PRs — grouped, highlighted, breaking changes flagged.
Debug Helper
Walks a stack trace + repro into a root-cause hypothesis. Asks for missing context before guessing.
AI Output Verifier
Audits AI-generated code for hallucinated APIs, made-up signatures, and silent rewrites.
Loop Breaker
Diagnoses why an AI agent is stuck and produces a clean restart with the right context.
Context Grounding Brief
Builds a context bundle (real schema, real types, real signatures) before asking AI to write code.
Codebase Onboarding Doc Builder
Generates an audience-aware onboarding doc for an unfamiliar codebase — architecture, setup, conventions, what's load-bearing.
SLO + Error Budget Designer
Defines SLOs and error budgets for a service so reliability becomes a measurable trade-off, not a vibe.
LLM Cost + Quality Tuner
Profiles an LLM-powered feature for cost-per-call and quality, and finds where to cut without breaking outputs.
Dependency + CVE Auditor
Audits a project's dependencies for known vulnerabilities, abandoned packages, license issues, and upgrade risk.
CI/CD Pipeline Architect
Designs a CI/CD pipeline from scratch — build, test, gate, deploy — matched to your team size and stack.
MCP Server Builder
Builds a Model Context Protocol server exposing your tool/API/database as a resource AI agents can use.
Observability Designer
Defines what to log, what to metric, what to trace — and what NOT to — for a service you can debug at 3am.
RAG Architect
Designs a retrieval-augmented generation system end-to-end — chunking, embedding, retrieval, ranking, grounding — for your specific corpus.
Spec-Driven Workflow Builder
Defines the spec-first workflow for your team — what gets written before code, what gets reviewed before merge, what gets validated post-deploy.
Feature Flags Architect
Designs a feature flag system that gets cleaned up — including the kill-criteria and review cadence.
Tech Debt Tracker
Catalogs and ranks tech debt so it gets fixed deliberately, not just complained about in 1:1s.
Claude API Builder
Scaffolds and debugs Claude API / Anthropic SDK code — with prompt caching, streaming, and the right model defaults built in.
Browser Automation Driver
Drives a real browser from the CLI — navigate, fill forms, click, screenshot, scrape, and run end-to-end checks on a live web app.
React Performance Reviewer
Reviews and refactors React/Next.js code against the performance rules that actually move load time — waterfalls, bundle size, server cost, re-renders.
React Composition Refactorer
Refactors React components drowning in boolean props into compound components, lifted state, and clean composition.
Git Worktree Workflow
Sets up an isolated git worktree so parallel feature work, reviews, and AI agents don't trample your main checkout.
Postgres Performance Reviewer
Reviews Postgres queries, schema, and indexes against the rules that move latency — missing indexes, N+1, RLS cost, connection limits.
Test-Driven Development
Drives a feature or bugfix test-first — write the failing test, watch it fail, write the minimal code to pass, then refactor.
Codebase Architecture Reviewer
Finds shallow modules and proposes deepening refactors — small interfaces hiding real behavior — for a more testable, navigable codebase.
React Native Best Practices
Reviews React Native / Expo code against the rules that matter on mobile — list performance, animations, navigation, native modules.
Dev Branch Finisher
Closes out a finished branch the right way — verify tests first, then present merge / PR / cleanup options and execute the choice.
Implementation Plan Executor
Works through a written implementation plan task-by-task — review it first, execute each step, verify, commit — with checkpoints.
Hosting Stack Selector
Picks a host, database, and region from your project's actual shape — and names what you'd have to migrate later.
Auth & Payments Setup
Wires sign-in and paid checkout into an existing app — without rolling your own auth or ever touching card data.
Production Monitoring Setup
Stands up error tracking, uptime, and log access so you find out something broke before your users tell you.
Put these skills to work
Developer Workflow Pack — step-by-step playbooks that ship the work