- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add shinpr/ai-coding-project-boilerplate --skill llm-friendly-context -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add shinpr/ai-coding-project-boilerplate --skill llm-friendly-context -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add shinpr/ai-coding-project-boilerplate --skill llm-friendly-context -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add shinpr/ai-coding-project-boilerplate --skill llm-friendly-context -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/shinpr/ai-coding-project-boilerplate/tree/HEAD/.claude/skills-en/llm-friendly-context來自發布者
The goal is stable downstream execution: the next agent should know what to read, what to do, what counts as success, and which unresolved decisions can change the result.
This skill governs the clarity of LLM-facing output — prompts, handoffs, and generated artifacts. The caller supplies the artifact type and any artifact-specific template or input contract; include only the information its consumer uses to decide, act, or verify. Use a declared contract's field names and value meanings when the consumer branches on them.
Use positive, executable instructions
Make vague instructions concrete
appropriate, proper, related, existing behavior, optional, as needed, if needed, per convention, unresolved alternatives, TBD, placeholderSpecify output shape
Provide the smallest sufficient context
Decompose complex work into verifiable steps
Permit uncertainty explicitly
Keep constraints proportionate
minimal, a few lines, an explicit line or file estimate — as one budget over the whole completed diff, not per file or per step. When the work cannot fit it, report the overrun and the reason instead of silently exceeding itUse these rewrites before treating a prompt, handoff, or artifact as complete.
Before sending a prompt or artifact to another agent, verify:
Before writing or finalizing a generated document:
Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream agents can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning
---name: llm-friendly-contextdescription: Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream agents can…---# .claude/skills-en/llm-friendly-context/SKILL.md總覽
Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream agents can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions.
常見問題
從發布者下載 .claude/skills-en/llm-friendly-context/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/shinpr/ai-coding-project-boilerplate。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。