A guided interview for turning a repeated activity into a written workflow specification. It asks one question at a time until another person or agent can build the workflow without needing more information.
A writing process that turns fixed source material into a guided sequence of sections, called beats. It introduces unfamiliar ideas before later sections depend on them, so readers can follow the piece without missing background.
An exploratory writing process that collects raw fragments in a Markdown file without imposing an outline. A fragment can be a sentence, observation, story, code sample, quote, or unfinished thought.
Skill "writing-shape" from vinvcn/mattpocock-skills-zh-CN, covering the loop, grounding, conversational feel, pulling from the pile and format arguments to actually have.
A Claude Code setup that blocks selected destructive Git commands before they run. Git is a tool for tracking code changes; the blocked commands include pushing, deleting branches, discarding changes, and hard resets.
A directory scaffold for course exercises, with sections, exercise folders, and optional problem, solution, or explanation versions. It creates the required Markdown files and checks the result with the repository's linter.
A setup for Husky pre-commit checks in a JavaScript or TypeScript repository. A pre-commit hook runs automatically before a Git commit and can format staged files, check types, and run tests.
A guided questioning process for testing a plan, decision, or idea. It maps dependent choices into a tree and asks only the questions that can be answered at each stage.
An instruction that asks the assistant to stop and request a clearer explanation when a message lacks enough context. It also asks for simple technical language and the project's established terms.
Guidance for writing instructions that coding agents can follow consistently. It covers skills and files such as AGENTS.md and CLAUDE.md, which tell agents how to work in a project.
A collection of engineering skills for AI coding agents, covering stages from defining a software change through delivery. It also includes separate roles for code review, security checks, and test engineering.
A command for carrying out the next unfinished coding task from a plan, including writing tests, implementing the change, checking the project, and committing it. TDD, or test-driven development, means writing a failing test before the code that makes it pass.
A planning command that breaks software work into small, verifiable tasks with dependencies and acceptance criteria. Acceptance criteria describe what must be true for a task to be complete.