Communityライティング&編集github.com

kit-prompt-writing-system

Build reusable prompts with clear facts, tasks and output examples, then identify missing or weak parts with local checks.

kit-prompt-writing-system とは?

kit-prompt-writing-system is a Claude Code agent skill that build reusable prompts with clear facts, tasks and output examples, then identify missing or weak parts with local checks.

対応~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/byoverseas/knacco-free-skills/tree/HEAD/skills/kit-prompt-writing-system

Installed? Explore more ライティング&編集 skills: steipete/notion, langchain-ai/langchain, bytedance/podcast-generation · View all 6 →

お気に入りのAIに質問する

このエージェントスキルを事前に読み込んだ状態で新しいチャットを開きます。

ドキュメント

Prompt Writing Guide

A prompt that works twice is built, not phrased. Four parts, each with one job: who is answering, what is true and what is missing, what must come back, and one passage of the output at the quality you want.

Status: v1.0 | Category: Frameworks | Price: Free

Read the product guide before you write a prompt. Run the included tools from this product folder. Keep your prompts and outputs in your own workspace.

What this framework does

  1. Takes a job you would otherwise describe in one sentence.
  2. Fills four parts: role, input, task, example.
  3. Assembles them into one labelled prompt that a model can follow in order.
  4. Checks the prompt against 14 rules and exits non-zero on a break.
  5. Grades the prompt part by part, names the weakest part and the repair that buys the most.
  6. Shows the test that matters: run it again with different facts and compare the shape.

Route

  • Write a new prompt → read GUIDE.md, then python3 tools/rit.py --example > brief.json, edit the four values, and run python3 tools/rit.py brief.json --out prompt.txt.
  • Find wording for one part → references/part-library.md.
  • Fix a failure you can see in the output → references/failure-list.md.
  • Improve a thin or average example → references/example-craft.md.
  • Judge a prompt you already have → python3 tools/rit_grade.py prompt.txt.

Rules that are not negotiable

  • The role names a discipline and a level of experience. It does not praise.
  • The input states the situation, names at least one constraint, and says what is missing. Absent material is named, not invented.
  • The task names a deliverable, its sections, its length, its register, and what the output must be usable for.
  • The example is a passage of the output, not a description of it. The shape, the depth and the register, and nothing else.
  • A prompt that cannot be rerun with different input is a question, not a prompt.
  • The checker reads the prompt. It does not promise what the answer will be.

Files

FileUse
GUIDE.mdThe full method: the four parts, the reuse test, the failure list, the voice route
references/part-library.mdPaste-ready blocks for all four parts, five variants each
references/failure-list.md24 named failures with symptom, cause and repair
references/example-craft.mdWhat a good example contains, and three ways a bad one poisons a prompt
tools/rit.pyAssembles a prompt from a JSON brief and checks it against 14 rules
tools/rit_grade.pyGrades a prompt out of 25 per part and names the weakest part

Individual skills in this repo

This repo contains 2 individual skills — each has its own dedicated page.

関連スキル