ds-sharpen
Skill80 starsChanged 15 days agoMITView on GitHub
Restate the user's goal, make the task deeper rather than bigger, rewrite the prompt, and optionally attack the plan to find weak spots. Use before starting vague or high-stakes work, for 'sharpen this', 'what am I really asking', 'stress test this plan', or /ds-sharpen.
In this repository28 other files it gives its agents.
- ds-adoptSkill
- ds-best-of-nSkill
- ds-blast-radiusSkill
- ds-blueprintSkill
- ds-catchupSkill
- ds-context-resetSkill
- ds-design-auditSkill
- ds-designSkill
- ds-explainSkill
- ds-helpSkill
- ds-jurySkill
- ds-ledgerSkill
- ds-lessonsSkill
- ds-modeSkill
- ds-plan-loopSkill
- ds-pr-commentsSkill
- ds-principlesSkill
- ds-prSkill
- ds-readySkill
- ds-review-loopSkill
- ds-reviveSkill
- ds-shipSkill
- ds-swarmSkill
- ds-tddSkill
- ds-unslopSkill
- ds-unstickSkill
- ds-verify-loopSkill
- ds-watch-prSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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 30
Do not apply fixes from the stress test.
≈ “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
ds-sharpen
A sharper prompt saves more tokens than any loop. Fix the ask before doing the work.
Steps
- Restate, in your own words, what the user wants and the problem behind it. Keep it to three sentences. If you cannot, ask one question.
- Deepen the task. Answer briefly:
- What would a top professional do here that the user did not ask for?
- What raw material would they start from, instead of a summary?
- What methods and tools would they use?
- What outside check, not you or the user, would show the result is right? Name a command, test, metric or source.
- Rewrite the prompt to ask for exactly that. Keep it no bigger in scope. Leave choices that belong to the user open and list them.
- Optional stress test, when the plan is risky or the user asks. Spawn two or three subagents with fresh context and give each the plan and the goal. Ask each to break it and back every finding with a run: a failing test, a probe script, or real command output. Drop findings with no run behind them.
- Present the restatement, the rewritten prompt, open choices, and any surviving findings with their commands and output.
Stop when
- The user accepts or edits the rewritten prompt.
- Or the stress test returns. Do not loop it more than once without the user.
Rules
- Deeper, not bigger. Do not add features.
- Do not apply fixes from the stress test. Report them.
- A finding without output is an opinion. Leave it out.
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.