agentleFS
sungjunleesungjunlee/craftkit/skills/craft-prompt/SKILL.md

craft-prompt

Skill0 starsChanged 46 days agoMITView on GitHub

Craft copy-paste-ready prompts. Use to write prompts, turn notes into templates, draft `/goal` conditions, or answer "프롬프트 만들어" requests.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. V-Songbird/foreman★ 35same name
    2. mrdainami/omni-video-director★ 16same name

    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.

  • In this repository5 other files it gives its agents.

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
  1. Distinctive:

    Boundaries: Add scope, non-goals, approval limits, or irreversible-action rules only where crossing them would matter, stated once.

    line 18

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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.

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

craft-prompt

Purpose

Turn a goal, scattered notes, or a raw ask into a prompt the user copies as-is into another model, agent, or product surface. The prompt is the product: when the user asked for one, deliver it even if the underlying task looks simple enough to do directly.

Workflow

Infer what the request and available context already establish; ask only when the answer would materially change the prompt.

  1. Outcome. State what should be true or delivered at the end. Keep a shape, length, tone, or language only when the user named it or the consumer requires it.
  2. Context. The prompt usually travels without this conversation, so include the facts the target cannot infer or retrieve; omit what its surface already provides through files, tools, or attachments. In coding or worktree prompts, paths are worktree-relative unless the user needs machine-specific ones.
  3. Boundaries. Add scope, non-goals, approval limits, or irreversible-action rules only where crossing them would matter, stated once.
  4. Evidence. Where done could be read more than one way, say what observable check shows it is done. Don't add generic "be thorough" caution.
  5. Controls on demand. A role, format contract, example, XML boundary, process step, or tool rule goes in only when the consumer requires it or it corrects a likely or observed failure — references/components-guide.md is the menu. Use the target's native controls (effort, verbosity, structured output) rather than simulating them in prose.

Special cases: for a /goal, read references/goal-conditions.md first. For a reusable template, turn each value that genuinely varies into a {{placeholder}}; bake specifics into a one-shot. For image, video, or system prompts, start from the matching file in templates/.

A one-sentence prompt for a simple task is a feature. If removing a line would not change a competent target's output, cut it.

Output format

One fenced code block, ready to copy-paste. If a placeholder or target setting needs explaining, add a brief note outside the block; no generic prompting advice.

Non-English prompts: write the body in the requested language; if XML earns its place, keep tag names in English.

Example

Input: "write me a code review prompt for GPT, keep it short"

Review the diff below for correctness bugs, security issues, and unnecessary complexity. Skip style nits.

Report only issues you're confident about, one per line: `file:line — issue — suggested fix`.

<diff>
{{diff}}
</diff>

Note outside the block: "Swap {{diff}} for the actual diff before sending."

References (load on demand)

  • references/components-guide.md — optional controls and when each earns its place
  • references/quality-checklist.md — deeper check and subtraction pass for high-risk or reusable prompts
  • references/goal-conditions.md — /goal completion conditions and reviewable goal specs
  • references/prompt-patterns.md — short worked prompts for common task types
  • references/shared-principles.md — the five principles behind the workflow
  • templates/image-gen.md, templates/video-gen.md, templates/system-prompt.md — special-case starting points

Download now (ZIP)

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.