finishing-a-development-branch
Implementation is complete, all tests pass, and you need to decide how to integrate the work
Git / commit / MRTự động hoá
Loading…
One place to find AI agent skills by domain, install them with one command, then learn to use them through guides and quizzes.
Every skill is checked automatically before it reaches the hub. Broken or heavily reported skills hide themselves.
557 skills
Copy one command and the skill sits in your project, always the latest version from its source repo.
Guides and courses with quizzes, written for people who use AI agents.
0 guides · 0 lessons
npx degit obra/superpowers/skills/brainstormingPick skills by domain, download several at once, and learn to work with agents through guides and quizzes.
npx degit obra/superpowers/skills/finishing-a-development-branchThe hub only stores a pointer to each skill’s source repo and always reads that repo’s latest SKILL.md. Every skill is checked before it is listed, and no copy is ever kept on the hub.
source:
repo: obra/superpowers
Send the link to the GitHub folder with its SKILL.md. The hub checks its quality and opens a pull request to the content repo for you; a maintainer reviews it before it goes live.
Ranked by the GitHub stars of the source repo, one skill per repo.
Implementation is complete, all tests pass, and you need to decide how to integrate the work
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
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 Node/TypeScript (MCP SDK).
Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.
Execute database migrations across ORMs and platforms with zero-downtime strategies, data transformation, and rollback procedures. Use when migrating databases, changing schemas, performing data transformations, or implementing zero-downtime deployment strategies.
Security hardening reviewer for GitHub Actions workflow files (.github/workflows/*.yml). Reasons about the Actions threat model that pattern matchers and general code linters miss — untrusted-input script injection, privileged triggers running fork code, mutable action references, and over-scoped tokens. Use this skill when asked to review, audit, harden, or secure a GitHub Actions workflow, when writing a new workflow, or for any request like "is this workflow safe?", "review my CI for security issues", "why is pull_request_target dangerous here?", "pin my actions", or "lock down GITHUB_TOKEN permissions". Covers script injection via ${{ }} interpolation, pull_request_target / workflow_run privilege escalation, SHA-pinning of third-party actions, least-privilege permissions, GITHUB_ENV/GITHUB_OUTPUT injection, secret exposure, OIDC over long-lived credentials, and self-hosted runner exposure on public repositories.