Перейти к содержимому
TakoAPI
Назад к навыкам

agent-docs

от tylervovan

AI & LLMs
2.2kЧисло загрузок по данным clawskills.sh
4Звёзды
0Просмотры
0 лайковВойдите, чтобы поставить лайк навыку
—Ещё нет оценок
Ваша оценка

Кратко

Create documentation optimized for AI agent consumption.

Описание

Что делает этот навык

Guides writing documentation structured for AI agent consumption, covering token efficiency, RAG chunking, and context hierarchy. Applies to AGENTS.md constitutions, llms.txt indexes, SKILL.md files, and API docs read by LLMs. Based on Vercel benchmarks showing inline docs achieve 100% agent task pass rates versus 53% with retrieval-only approaches.

Inline AGENTS.md achieves a 100% agent task pass rate compared to 53% for tool-based retrieval alone, because agents skip fetching docs they assume they already know from training.

Когда его использовать

  • Writing AGENTS.md constitutions for a new codebase
  • Generating a llms.txt index for an existing project
  • Structuring API docs so an agent retrieves the right chunk
  • Auditing a README for token efficiency before adding it to agent context
  • Creating SKILL.md files for OpenClaw agent workflows

Пример сценария

ВВОД

User asks: Create an AGENTS.md for my Next.js project

АГЕНТ
  1. 1

    Identifies stack, architecture constraints, and critical governance rules

  2. 2

    Places security rules and build commands at the top to exploit primacy bias

  3. 3

    Writes a compressed docs index with file paths and function signatures, not full code

  4. 4

    Structures each H2 section to be self-contained for RAG chunk boundaries

  5. 5

    Validates total inline context stays under 4,000 tokens

ВЫВОД

AGENTS.md with governance rules, a docs index, and architecture constraints ready for agent context windows

Установка

clawhub install tylervovan/agent-docs

Выполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.

Ссылки