- Claude Code
- Skill
- Intermediate
- Claude Code
- Claude
- ChatGPT
- Published
Write a SKILL.md From a Workflow You Keep Repeating
Interviews you about a task you do over and over, then writes a complete, save-ready SKILL.md with a trigger description, steps, output format and stop conditions.
You get: the full SKILL.md in one code block, the folder path to save it in, any extra reference files as separate code blocks, and three test requests I can use to check that it…
The prompt
Installs to .agents/skills/write-a-skill-md-from-a-workflow-you-keep-repeating/
mkdir -p .agents/skills/write-a-skill-md-from-a-workflow-you-keep-repeating && curl -sL "https://prompts-gpt.com/prompts/write-a-skill-md-from-a-workflow-you-keep-repeating/raw" -o .agents/skills/write-a-skill-md-from-a-workflow-you-keep-repeating/SKILL.mdAct as an author of agent skills for Claude Code and other agents that read SKILL.md files. I keep repeating this workflow: {describe the task you repeat}
First interview me with up to five short questions, one at a time: when the task starts, the exact steps I take, the tools or commands I use, what a finished result looks like, and the mistakes I want to prevent.
Then write the skill.
Rules:
1. Frontmatter with a kebab-case name and a description that says what the skill does and the phrases or situations that should trigger it. The description is what the agent matches on, so make it specific.
2. Body under 300 lines: numbered steps, the exact commands, an output format, and a "Stop and ask" section for situations where the agent must check with me.
3. Put long reference material in separate files the skill links to, not in SKILL.md.
4. No vague rules such as "write good code"; every rule must be something the agent can check.
Output format: the full SKILL.md in one code block, the folder path to save it in, any extra reference files as separate code blocks, and three test requests I can use to check that it triggers. List assumptions and risks, such as overlapping with an existing skill.Tips and common edits
Use in Claude Code, Claude or ChatGPT once you notice yourself pasting the same instructions again. Save the result to .claude/skills/<name>/SKILL.md (or ~/.claude/skills for all projects); Codex, Cursor and Gemini CLI read the same format.
Questions about this prompt
More like this
More in Claude CodeConventional 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.
Pre-Merge Code Review Checklist Skill (SKILL.md)
A save-ready SKILL.md that has your coding agent review a branch before merge: correctness, security, tests and migrations, with findings ranked by severity and no style nitpicks.
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.
Meeting Notes to Decisions and Action Items Skill (SKILL.md)
A SKILL.md that turns any meeting transcript or rough notes into a decision log, owner-and-date action items, open questions and a ready-to-send recap email.
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.
Spreadsheet and CSV Cleanup Report Skill (SKILL.md)
A SKILL.md that has your agent profile a messy CSV or spreadsheet, fix it in a copy with a script, and report every change so the cleaned data can be trusted.
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.
Characterization Tests Before a Refactor
Writes tests that lock in a module's current behavior, including edge cases and quirks, so you can refactor safely.
Codebase Tour for a Specific Task
Explores a repo through the lens of your task and explains the architecture, key files and data flow, then says where to start.
Failing Test First Bug Fix
Reproduces a bug with a failing test, finds the root cause, applies the smallest fix and shows the test passing.
Recurring Workflow to SKILL.md with Trigger, Steps and Verification
Claude Code interviews you briefly about a repeated workflow and writes a complete SKILL.md with a precise trigger description, steps, supporting files and a verification step.
Agent Run Post-Mortem: Trace Root Cause and Prompt or Tool Fixes
Analyzes a pasted agent trace to find the first real failure and proposes exact prompt rewrites or tool changes, each with a test.