agentleFS
Sign inStart free
drafaeldrafael/coding-harness/skills/sharpen/SKILL.md

sharpen

Skill1 starsChanged 6 months agoMITView on GitHub

Deepen a task without broadening its scope, then rewrite its prompt. Manual invocation only; use when the user explicitly invokes sharpen or requests this prompt-sharpening workflow. Do not execute the rewritten task or decide choices the user owns.

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 21 edited versions we read keep these.

  • 3

    Distinctive

    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
  1. Distinctive:

    Run only after an explicit request.

    line 12
  2. Distinctive:

    Before rewriting it, give four concrete answers:

    line 14
  3. Distinctive:

    Do not turn the exercise into brainstorming alternatives, implementation, or an investigation of the subject.

    line 23

“Common” is measured: kept by at least 6 in 10 of the 21 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Sharpen

Make the task deeper, not bigger. Improve the quality of the investigation and its evidence without adding deliverables or neighboring projects.

Run only after an explicit request. Use the supplied task or the clearly identified task in the conversation. If neither is available, ask for the prompt to sharpen.

Before rewriting it, give four concrete answers:

  1. Professional standard: What would a strong practitioner in this field do here that the task does not yet ask for?
  2. Raw material: What primary evidence would they start from instead of an already-digested account? Name the relevant source code, records, observations, data, or original sources.
  3. Methods and tools: Which specific techniques and available tools fit this task? Distinguish suggestions from capabilities or access actually available.
  4. Independent check: What observable result, reproducible check, external criterion, or qualified review would establish correctness beyond either person's opinion?

Then provide a rewritten prompt that asks for exactly that deeper work. Preserve the original goal, constraints, effort budget, and user-owned choices. Mark necessary unknowns rather than inventing requirements, evidence, access, or acceptance criteria.

Do not turn the exercise into brainstorming alternatives, implementation, or an investigation of the subject. Propose the methods; do not run them. Return the four answers followed by the rewritten prompt, then stop.

Download now (ZIP)

  • Other versions28 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 28

    1. backnotprop/pstack★ 3.3ksame name
    2. backnotprop/bro★ 166same name
    3. hamzafarooq/claude-code-starter★ 145same name
    4. joetawil7/first-pass★ 128same name
    5. jtaroreh/agystack★ 128same name
    6. dsebban/skills★ 71same name
    7. TheOnlyFusionCube/potetos-for-everyone★ 18same name
    8. creedants/pstack-t3★ 17same name
    9. mariusflorescu/pstack-t3★ 13same name
    10. adjohn/pstack★ 9same name

    18 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use ketchup-video, maintain-formal-verification-skill and 10 more.

    Other files people use alongside this one.

    Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
    • 3metaJunSkill

      ketchup-video

      Catch the user up like /ketchup, with a short subtitled video of slides for what happened and the waiting calls as text under it. Use for /ketchup-video.

      Also in 10 projects that use this

    • TheOnlyFusionCubeSkill

      maintain-formal-verification-skill

      Bring a project's formal verification back in line with the code after the code changes: find the commits that touched verified code, update the model, harness, or properties to describe the code as it is now, rerun, and say whether each failure is drift in the verification or a bug in the code. Use for /maintain-formal-verification-skill, \"is the model still true to the code\", or after merges and refactors that touched verified code without rechecking it.

      Also in 13 projects that use this

    • TheOnlyFusionCubeSkill

      create-formal-verification-skill

      Generate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in any language, with whichever verification tool fits. Use for /create-formal-verification-skill, \"model-check this race\", \"prove this invariant\", or when concurrency, retries, state machines, parsers, or unsafe code need more than tests.

      Also in 15 projects that use this

    • ianclearySkill

      poteto-help

      Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.

      Also in 10 projects that use this

    • ianclearySkill

      principle-explain-the-number

      Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.

      Also in 16 projects that use this

    • jaydubya818Skill

      principle-test-behavior-not-implementation

      Apply when tests mirror internals instead of asserting observable outcomes.

      Also in 17 projects that use this

    • +1 more from TheOnlyFusionCube
  • In this repository31 other files it gives its agents.

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free