Skills by obra

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

This skill produces step-by-step implementation plans and instructs saving them to `docs/plans/YYYY-MM-DD-<feature-name>.md`. It includes explicit shell commands to run tests and git operations (e.g., `pytest tests/path/test.py::test_name -v`, `git add ...`, `git commit ...`), which directs command execution.

Use when implementing any feature or bugfix, before writing implementation code

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Use when executing implementation plans with independent tasks in the current session

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

This skill enforces running verification commands and reading their outputs before claiming work is complete. It explicitly instructs executing shell commands (e.g., `Run the command`, `Run test command`), which is a `shell_execution` behavior.

The skill automates creating and managing isolated git worktrees using ` .worktrees`/`worktrees` or `~/.config/superpowers/worktrees/<project-name>/`, verifies `.gitignore`, and runs project setup. It instructs executing shell commands like `git worktree add`, `npm install`, `pip install`, `cargo build`, and `go mod download`, implying local execution and inferred network package downloads.

This skill documents how to author and test agent `Skills` and bundles utility scripts (e.g., `render-graphs.js`) and runnable examples. It includes explicit instructions to execute local scripts (`./render-graphs.js`, `python scripts/analyze_form.py`) and references external endpoints (`api.example.com/v2/messages`, `https://platform.claude.com/docs/en/build-with-claude/context-windows`).

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

This skill guides finishing a development branch with explicit git workflows and four structured options. It instructs executing shell commands (`npm test`, `git checkout`, `git merge`, `git push`, `gh pr create`) and performing networked git/PR operations; no secret-reading or obfuscated behavior detected.

Use when user asks 'how should I...' or 'what's the best approach...' after exploring code, OR when you've tried to solve something and are stuck, OR for unfamiliar workflows, OR when user references past work. Searches conversation history.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

This skill applies Strunk's `The Elements of Style` to edit and improve prose and includes the full `elements-of-style.md` guide. It instructs the agent to `Dispatch a subagent with your draft and elements-of-style.md`, which spawns a subagent process.

This skill automates detection of semantically duplicate functions and provides scripts such as `./scripts/extract-functions.sh`, `scripts/prepare-category-analysis.sh`, and `./scripts/generate-report.sh` to extract, categorize, and report duplicates. It instructs running these shell scripts and dispatching `haiku`/`opus` subagents, i.e., executing local commands and making network calls.