Agent skill prompts

13 prompts

Prompts that write reusable instructions for AI agents: SKILL.md files, AGENTS.md and CLAUDE.md project guides, and the other standing instructions an agent loads before it starts work. Fill in your stack and conventions, and the result is a file you commit once and every later task benefits from.

6 results

  • Cursor .mdc Rules to Portable AGENTS.md Converter

    Converts your pasted Cursor .mdc rules into a single AGENTS.md that Codex, Copilot and Gemini CLI can read, plus a table of what does not carry over.

  • Brand Voice Guard Skill That Checks Drafts Against VOICE.md (SKILL.md)

    A SKILL.md that makes Claude write and edit in your brand's voice: it reads a VOICE.md in the project, or builds one from samples, then checks every draft against it.

  • Codex Writes an AGENTS.md for This Repository From the Real Setup

    Has Codex inspect your repository and write a short, accurate AGENTS.md with the real build, test and lint commands, conventions and boundaries, checked by actually running them.

  • Conventional Commit and PR Description Writer Skill (SKILL.md)

    A ready-to-save SKILL.md that makes your coding agent write Conventional Commits messages and pull request descriptions from the staged diff, never from guesses.

  • Release Notes From Git Log Skill for Users and Developers (SKILL.md)

    A SKILL.md that writes release notes from the commits between two tags, split into a plain-language section for users and a technical changelog for developers.

  • Test-First Bug Fix Skill: Reproduce, Fix, Prove (SKILL.md)

    A SKILL.md that forces your coding agent to reproduce a bug with a failing test before changing code, apply the smallest fix, and prove it with the test suite.

About Agent skill prompts

What is an agent skill?

A folder of instructions, and sometimes scripts, that an agent loads when a task calls for it. Its SKILL.md names the skill, says when to use it and lists the steps.

Where do the generated files go?

AGENTS.md and CLAUDE.md go in the repository root. Skills go wherever your agent looks for them, such as a skills folder in the project or in your user settings.

How do I check that a generated skill works?

Give the agent a task the skill is meant for and watch whether it loads the skill and follows the steps. If it doesn't, make the skill's description more specific.