跳到正文
cccskills
免费在 GitHub 公开

scout-vault

Echo's vault traversal skill. Read-only graph walk — find all notes related to a topic, trace wikilink chains, inventory a directory, or spelunk a codebase for definitions and call chains.

中文简介正在准备中。当前显示原文说明。

wrg32786/aigent-os星标 25(GitHub 25 + cccskills 0)

实测评分 未实测

查看安装方法

包含的文件(1)

  • SKILL.md2.0 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Scout Vault

You are Echo performing a vault reconnaissance pass. Read-only without exception.

What this skill does

Traverse the vault (or a codebase) to find all notes, files, or code symbols related to the user's query. Return structured findings: paths, line numbers, section headers, and wikilink connections. No synthesis. No opinions. Surface what exists.

Protocol

  1. Parse the query. Identify the topic, term, or symbol to search for.
  2. Grep broadly first. Run 2-4 Grep calls across the vault for key terms and aliases.
  3. Glob for structure. If the query is about a directory or file type, run Glob to inventory the shape.
  4. Read the top hits. Read the 3-5 most relevant files found. Pull frontmatter, headings, and wikilinks.
  5. Trace one level of wikilinks. For each note found, list its outgoing [[wikilinks]] — do not follow them unless the user asks.
  6. Return structured findings.

Return format

## Scout Report: <topic>

### Files found (N)
- `path/to/note.md` — <one-line summary of relevance>
- ...

### Key wikilinks mentioned
- [[Note A]] — appears in N files
- [[Note B]] — appears in N files

### Patterns / clusters noticed
- <observation about structure, not interpretation>

### Not found
- <terms searched that returned no results>

Constraints

  • No Write, Edit, Bash, or Agent tool calls.
  • If a file doesn't exist or a pattern returns no results, say so explicitly.
  • Do not guess at content not found. Do not infer from absence.
  • Run all Grep/Glob/Read calls in parallel where possible.

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

Track and surface sub-agent dispatch calibration ratios. Extract from JSONL transcript or read existing ledger. Per-agent clean/blocked/errored/partial trends.

中文简介正在准备中。当前显示原文说明。

wrg32786/aigent-os252026年10月29日 更新

Compose the AIgent's body state by reading existing signals. Lazy compute. Never polled. Reports the five pressures + recommended reflex.

中文简介正在准备中。当前显示原文说明。

wrg32786/aigent-os252026年10月29日 更新

brief

免费

Generate a structured delegation brief for any task

中文简介正在准备中。当前显示原文说明。

wrg32786/aigent-os252026年10月29日 更新

Quarterly skill that walks the skill-index against the actual SKILL.md files on disk, reports drift (skills indexed that no longer exist, skills on disk that aren't enrolled, skills whose descriptions have changed since enrollment). Hardens the auto-enrollment pipeline against silent rot.

中文简介正在准备中。当前显示原文说明。

wrg32786/aigent-os252026年10月29日 更新

When a [CADDY] hint fires and the principal is confused why, /caddy-explain walks the scoring transparently — which trigger matched, what points it earned, what the threshold was, what other skills were close. Pairs with the legibility thesis. Caddy's decisions should be inspectable on demand.

中文简介正在准备中。当前显示原文说明。

wrg32786/aigent-os252026年10月29日 更新

Enroll a skill into Caddy's index so it can be surfaced when the right prompt arrives. Use when a new skill is created, copied in, or when a skill needs updated triggers. Usage — "/caddy-enroll <path to SKILL.md>".

中文简介正在准备中。当前显示原文说明。

wrg32786/aigent-os252026年10月29日 更新

查看 wrg32786 的全部技能

报告此技能的问题