跳到正文
cccskills
免费在 GitHub 公开

add-stack-context

Audit and establish current agent context for the technologies that define a project's stack. Use when setting up a project for agent work, after selecting or adding a framework, library, developer tool, or hosted service, or when entering an existing project whose agent context has not been audited.

中文简介正在准备中。当前显示原文说明。

toy-crane/claude-code-playbook-template星标 77(GitHub 77 + cccskills 0)

实测评分 未实测

查看安装方法

包含的文件(4)

  • SKILL.md3.2 KB
  • agents/openai.yaml237 B
  • evals/evals.json6.6 KB
  • evals/trigger-evals.json2.3 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Add Stack Context

Inventory the stack

Build a checklist of the direct technologies that shape how the project is built or operated from manifests and configuration files. Include frameworks, libraries, developer tools, and hosted services; exclude transitive dependencies. Use lockfiles to confirm installed versions, not to expand the checklist. If the project does not declare a stack yet, ask the user what they intend to use.

Discover skills and vendor context

For every checklist item, invoke find-skills when it is available and use it to discover relevant skills. When it is absent, search the current Skills ecosystem through the Skills CLI or an equivalent current source so this skill remains independently installable.

Verify candidate ownership against the technology vendor's current documentation or official organization; search rank, install count, and repository popularity do not establish that relationship. Inspect the documented installation method and expected changes, then install a vendor-controlled skill when it is missing. Assess a relevant community skill as an optional candidate, but install it only after explicit user approval and never count it as the technology's official context.

Continue through the vendor's current sources for official context that skill search does not cover, including installers, codemods, package-bundled documentation, and MCP servers. Match the installed version when the vendor provides version-specific context and apply the vendor's documented method. When no official channel exists, record the gap without letting a community candidate substitute for it.

Keep changing guidance live

Treat a vendor llms.txt or equivalent changing document as a current remote source, not a file to copy into the repository. Add or update a bounded managed instruction in the repository's established AGENTS.md or CLAUDE.md surface. Name the technology and official source, tell later agents to retrieve it when relevant work begins, and require them to reconcile it with the installed version.

Preserve user-authored context and existing links, imports, or other sharing between agent instruction files. When both files are independent and active, expose the same live retrieval behavior in each without replacing their other content. Treat vendor-managed blocks as vendor-owned and update them only through the official method.

Account for every technology

Finish only when every checklist item has one of four outcomes:

  • installed;
  • already present;
  • unavailable from an official source; or
  • blocked, with the reason stated.

Summarize the outcome and official sources checked for every item. For installed context, include the changes made and the vendor's documented update path. List community candidates awaiting approval separately. For live vendor guidance, name task-time retrieval as its update path and report a retrieval blocker instead of treating a cached copy as current.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Revise active `docs/specs/SLUG/` specs so they match what has shipped since they were written. Use when earlier work has landed and queued specs may now rest on stale assumptions, acceptance criteria, constraints, terms, or prototypes, or when implementation reports a spec as stale before changing source. Takes one or more spec folders, or every folder under `docs/specs/` when none is named. Do not use to shape a new spec from a problem and direction, which belongs to `shape-idea`, or to reconcile durable project context and retire shipped folders, which belongs to `maintain-project-context`.

中文简介正在准备中。当前显示原文说明。

toy-crane/claude-code-playbook-template772026年10月21日 更新

Build a complete dummy-data HTML prototype or a temporary comparison of up to three alternatives for a specific user situation. Use to settle a screen-based product before implementation or resolve a visual or interaction decision during shaping or prototype review. Do not use for production implementation or CLI, terminal, or voice interfaces.

中文简介正在准备中。当前显示原文说明。

toy-crane/claude-code-playbook-template772026年10月21日 更新

commit

免费

Create Git commits for the current request's in-scope changes as logical Conventional Commits. Always use this skill for an actual Git commit operation, including requests to commit or amend changes, save work in repository history, stage and record selected files, or group staged or unstaged changes into commits. Use it even when the request describes recording changes without saying "commit"; it performs the commit rather than only suggesting a message, and it does not push.

中文简介正在准备中。当前显示原文说明。

toy-crane/claude-code-playbook-template772026年10月21日 更新

Interview the user to define or revise the app's overall product direction, then preserve the confirmed meaning in root PRODUCT.md. Always use for a new app direction or any app-wide change to users, usage situations, problem, promised change, core loop, durable boundaries, experience principles, success signals, assumptions, or unknowns, even when PRODUCT.md is not named. Start from an existing definition or a rough app direction. Do not use for blank-page idea discovery, architecture, or shaping or specifying one feature or work unit.

中文简介正在准备中。当前显示原文说明。

toy-crane/claude-code-playbook-template772026年10月21日 更新

Render an explanation as a diagram, comparison, trace with real values, or annotated code. Use when the user asks to have a concept, decision, flow, or code explained, or says they do not follow.

中文简介正在准备中。当前显示原文说明。

toy-crane/claude-code-playbook-template772026年10月21日 更新

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

中文简介正在准备中。当前显示原文说明。

toy-crane/claude-code-playbook-template772026年10月21日 更新

查看 toy-crane 的全部技能

报告此技能的问题