sharpen-prompt
Skill127 starsChanged 5 months agoMITView on GitHub
Rewrite a vague request into a precise prompt — goal, context, scope, constraints, what done looks like, output format. Use when the user asks to improve, rewrite, sharpen or check a prompt.
In this repository5 other files it gives its agents.
- ccoSkill
- doc-digestSkill
- fresh-startSkill
- project-contextSkill
- token-checkSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 19
Constraints: must keep, must avoid, length, tone, tools, deadline.
- Distinctive: line 26
If you can fill the gaps from the conversation, write the improved prompt in a code block in the user's language.
- Distinctive: line 29
If one gap is essential and unknowable, ask that one question instead of guessing.
- Distinctive: line 31
Don't do the task itself unless the user asks you to.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Sharpen a prompt
A precise prompt saves the back-and-forth, and the tokens, that a vague one costs. Rewrite the user's prompt so another assistant could do the task right on the first try.
Check what the prompt is missing
- Goal: what should exist or be true at the end.
- Context: who it's for, what it builds on, what was tried.
- Scope: exactly which files, sections, data or part of the problem. Name them.
- Constraints: must keep, must avoid, length, tone, tools, deadline.
- Done looks like: how to tell it worked: tests pass, a sample output, a checklist.
- Output format: a list, a table, a diff, a file, a one-paragraph answer.
Then
- If you can fill the gaps from the conversation, write the improved prompt in a code block in the user's language. Keep it as short as the task allows, and list in one line what you added and why.
- If one gap is essential and unknowable, ask that one question instead of guessing. Never ask more than one.
- Don't do the task itself unless the user asks you to.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.