跳到主内容
智客 ZICQ

技能库 智客分类:Agent 工作流 agents-md

Agents Md

当请求的交付品包括创建、审查、移动、拆分或更新寄存器AGENTS.md;生成范围回放指南时使用。 不触发独立技能、 提示、 非 AGENTS 指令文件、 README、 更改日志或架构文件 .

1437 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

当请求的交付品包括创建、审查、移动、拆分或更新寄存器AGENTS.md;生成范围回放指南时使用。 不触发独立技能、 提示、 非 AGENTS 指令文件、 README、 更改日志或架构文件 .

何时用

- 创建、更新、审查、分拆、移动或修复一个存储器`AGENTS.md'

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Manage AGENTS.md、When to Use、When NOT to Use、Modes、Workflow、Rule Quality Rubric。 其中含规范建议的小节:分步指令。

文件分析

文件分析:除 SKILL.md 外,正文引用了 references/topology-and-handoff-guidance.md、scripts/analyze_project.py、references/normal-authoring.md、references/template-selection.md、assets/agentsmd-minimal.md、scripts/validate_agentsmd.py,属于带资源的技能包,这些文件按需再读。

官方 description(原文)

Use when the requested deliverable includes creating, reviewing, moving, splitting, or updating a repository AGENTS.md; produces scoped repo guidance. Do not trigger for standalone skills, prompts, non-AGENTS instruction files, READMEs, changelogs, or architecture docs.

Manage AGENTS.mdWhen to UseWhen NOT to UseModesWorkflowRule Quality RubricEscalation MatrixFinal ResponseDeterministic ToolsReferences

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
agents-md
description
Use when the requested deliverable includes creating, reviewing, moving, splitting, or updating a repository AGENTS.md; produces scoped repo guidance. Do not trigger for standalone skills, prompts, non-AGENTS instruction files, READMEs, changelogs, or architecture docs.
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。
指令中引用的文件 · 8
  • references/topology-and-handoff-guidance.md
  • scripts/analyze_project.py
  • references/normal-authoring.md
  • references/template-selection.md
  • assets/agentsmd-minimal.md
  • scripts/validate_agentsmd.py
  • scripts/semantic_check_agentsmd.py
  • references/contract-bearing-agentsmd.md

以下路径提取自原文;文件是否齐全请以来源仓库中的完整目录为准。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

该技能引用了附属文件,请从来源获取完整目录;仅复制 SKILL.md 可能缺少依赖。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「agents-md」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-17f7283fea62c2e0-%E6%8E%A2%E5%91%98-Md.html
请存为 .cursor/skills/agents-md/SKILL.md 或 .claude/skills/agents-md/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。
该技能还带 scripts/、references/、assets/ 等文件,请从 https://github.com/callicrate/skills 取完整目录,不要只建一个 SKILL.md。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

npx skills add 'https://github.com/callicrate/skills' --list

npx skills add 'https://github.com/callicrate/skills' --skill 'agents-md'

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版
--- name: agents-md description: "Use when the requested deliverable includes creating, reviewing, moving, splitting, or updating a repository AGENTS.md; produces scoped repo guidance. Do not trigger for standalone skills, prompts, non-AGENTS instruction files, READMEs, changelogs, or architecture docs." metadata: short-description: Create or update AGENTS.md. --- # Manage AGENTS.md `AGENTS.md` gives coding agents scoped, current, repo-specific instructions. It is not a README, runbook, architecture doc, changelog, tutorial, or evidence log. Good guidance is evidence-backed, concise, scoped to the file's directory tree, and behavioral: it tells agents what to do differently in this repository. ## When to Use - Create, update, review, split, move, or repair a repository `AGENTS.md`. - Capture verified local commands, repo contracts, path ownership, or recurring agent mistakes. - Convert repo evidence into rules that future agents can follow. ## When NOT to Use - Standalone skills, prompts, global instructions, READMEs, architecture docs, changelogs, or runbooks. - Broad documentation rewrites where `AGENTS.md` is not an explicit deliverable. - Aspirational process guidance that is not supported by current repo evidence. ## Modes - **patch**: small text fix, typo, stale path, or narrow rule change. Inspect the affected section and evidence only. - **create**: no suitable `AGENTS.md` exists. Run the analyzer, sample source/config/docs, then draft the smallest useful file. - **update**: existing file needs new or corrected guidance. Preserve valid rules, remove stale or duplicated material, and add only evidenced changes. - **split/move**: scope boundaries are changing. Inspect existing root and nested files, then use [references/topology-and-handoff-guidance.md](references/topology-and-handoff-guidance.md). - **review**: do not edit unless asked. Return findings by severity with evidence and residual risk. - **exhaustive**: monorepos, contract-heavy repos, safety-sensitive guidance, operational handoffs, major topology changes, or unclear evidence. ## Workflow 1. Pick the mode and target scope. Read the nearest existing `AGENTS.md`, nested `AGENTS.md` files that may overlap, and `git status --short` when available. 2. For create, update, split/move, or exhaustive modes, run `python /scripts/analyze_project.py --repo-root --format json`. Treat it as a sampling guide, not authority. 3. For normal authoring details, use [references/normal-authoring.md](references/normal-authoring.md). Inspect only the sources needed for the claims you will make. 4. Draft from the smallest applicable template in [references/template-selection.md](references/template-selection.md). Prefer [assets/agentsmd-minimal.md](assets/agentsmd-minimal.md) unless the repo clearly needs a specialized template. 5. Keep evidence in working notes or the final summary. Add an evidence file only when the repo already owns one or the user asks. 6. Validate with `python /scripts/validate_agentsmd.py --repo-root --agents-file --mode ` and `python /scripts/semantic_check_agentsmd.py --repo-root --agents-file `. ## Rule Quality Rubric Keep a rule only when it is: - **specific**: names actual paths, commands, contracts, or local conventions. - **current**: supported by live files or user-provided current facts. - **scoped**: applies to this `AGENTS.md` directory tree. - **behavioral**: changes what an agent should do. - **evidence-backed**: traceable to inspected repo evidence. - **safe**: avoids secrets, unauthorized access, destructive commands, and production execution. - **non-duplicative**: does not restate global instructions, language basics, or README content. - **concise**: short enough to scan during normal coding work. ## Escalation Matrix Load extra references only when the task needs them: | Trigger | Read | |---------|------| | Tool, CLI, MCP, API, generated file, migration, schema, or public contract guidance | [references/contract-bearing-agentsmd.md](references/contract-bearing-agentsmd.md) | | Split, move, nested scopes, stale topology, or ownership handoff | [references/topology-and-handoff-guidance.md](references/topology-and-handoff-guidance.md) | | Live operations, degraded tools, manual dispatch, stop states, or environment resets | [references/degraded-tool-surface.md](references/degraded-tool-surface.md), [references/evidence-invalidation.md](references/evidence-invalidation.md) | | Subagents or delegated review workflows | [references/subagent-coordination-patterns.md](references/subagent-coordination-patterns.md) | | Python, TypeScript, other stack, Databricks/Spark, or ML-specific evidence prompts | [references/language-specific/python-guidance.md](references/language-specific/python-guidance.md), [references/language-specific/typescript-guidance.md](references/language-specific/typescript-guidance.md), [references/language-specific/other-stack-guidance.md](references/language-specific/other-stack-guidance.md), [references/domain-specific/databricks-spark.md](references/domain-specific/databricks-spark.md), [references/domain-specific/ml-projects.md](references/domain-specific/ml-projects.md) | | Review-only or judgment-heavy audit | [references/manual-audit.md](references/manual-audit.md) | ## Final Response For edit modes, include changed files, rules added/changed/removed, evidence sources sampled, validation commands and results, and residual risks. For review mode, lead with findings ordered by severity. Each finding needs the affected `AGENTS.md` section or line, supporting repo evidence, why it matters, and the recommended fix. Then list open questions, test/validation gaps, and a brief summary only after findings. ## Deterministic Tools | Tool | Use | |------|-----| | [scripts/analyze_project.py](scripts/analyze_project.py) | Stack, config, test, path, and suggestion inventory | | [scripts/validate_agentsmd.py](scripts/validate_agentsmd.py) | Structural validation | | [scripts/semantic_check_agentsmd.py](scripts/semantic_check_agentsmd.py) | Path, command, link, and example validation | | [scripts/check_agentsmd_templates.py](scripts/check_agentsmd_templates.py) | Skill template and guidance hygiene | | [scripts/run_agentsmd_fixture_checks.py](scripts/run_agentsmd_fixture_checks.py) | Known fixture behavior for validator changes | ## References - [references/tool-contracts.md](references/tool-contracts.md) and [references/template-selection.md](references/template-selection.md) - helper CLI contracts, modes, and templates - [assets/agentsmd-minimal.md](assets/agentsmd-minimal.md), [assets/agentsmd-contract-bearing.md](assets/agentsmd-contract-bearing.md), [assets/agentsmd-operational.md](assets/agentsmd-operational.md), [assets/agentsmd-full.md](assets/agentsmd-full.md) - starter templates - [assets/example-validated-agentsmd.md](assets/example-validated-agentsmd.md), [assets/example-contract-bearing-agentsmd.md](assets/example-contract-bearing-agentsmd.md), [assets/example-operational-agentsmd.md](assets/example-operational-agentsmd.md), [assets/writing-tips.md](assets/writing-tips.md) - compact examples

相关技能

Agent 工作流

Skill Creator

创造有效技能指南。 当用户想创造出新的技能(或更新现有的技能),以专业知识,工作流程,或工具集成来扩展克洛德的能力时,应该使用这种技能.

Agent 工作流

Clawdhub

使用ClawdHub CLI搜索,安装,更新并发布从taladhub.com的代理技能. 需要获取苍蝇上的新技能时使用,将安装的技能同步到最新版本或特定版本,或者发布 npm-instainddhub CLI 的新/更新的技能文件夹.

Agent 工作流

Agent Team Orchestration

管弦乐团多代理团队,任务设定周期,交接协议,审查工作流程. 使用时间: (1)建立2+特派员队伍,具有不同专业,(2)确定任务路线和生命周期(收录框_ spec_建设_审查_完成),(3)在特派员之间制定交接协议,(4)建立审查和质量关口,(5)管理特派员之间的交流和文物共享.

Agent 工作流

Superpowers

Spec-first,TDD,子代理驱动的软件开发工作流程. 当:(1)构建任何新功能或应用——触发脑暴_计划_子代理执行回路,(2)调试出一个bug或测试失败——触发系统性的根起过程,(3)用户说"让我们构建","帮助我计划","我想添加X",或"这个被打破",(4)完成一个功…