Agent skill

Stale Detector

Scan a Yuque knowledge base for stale or outdated documents and recommend updates or archiving.

MITAuto-check passedKnowledge Management

Install Stale Detector

skills CLI

$ npx skills add yuque/yuque-ecosystem --skill stale-detector -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install yuque/yuque-ecosystem stale-detector --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/yuque/yuque-ecosystem.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/stale-detector .claude/skills/stale-detector && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "stale-detector" agent skill from https://github.com/yuque/yuque-ecosystem/tree/main/skills/stale-detector into .claude/skills/stale-detector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stale-detector", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/yuque/yuque-ecosystem/tree/main/skills/stale-detector

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add yuque/yuque-ecosystem --skill stale-detector -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install yuque/yuque-ecosystem stale-detector --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/yuque/yuque-ecosystem.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/stale-detector .agents/skills/stale-detector && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "stale-detector" agent skill from https://github.com/yuque/yuque-ecosystem/tree/main/skills/stale-detector into .agents/skills/stale-detector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stale-detector", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add yuque/yuque-ecosystem --skill stale-detector -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install yuque/yuque-ecosystem stale-detector --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/yuque/yuque-ecosystem.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/stale-detector .cursor/skills/stale-detector && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "stale-detector" agent skill from https://github.com/yuque/yuque-ecosystem/tree/main/skills/stale-detector into .cursor/skills/stale-detector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stale-detector", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/yuque/yuque-ecosystem.git --path skills/stale-detector

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add yuque/yuque-ecosystem --skill stale-detector -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install yuque/yuque-ecosystem stale-detector --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/yuque/yuque-ecosystem.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/stale-detector .gemini/skills/stale-detector && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "stale-detector" agent skill from https://github.com/yuque/yuque-ecosystem/tree/main/skills/stale-detector into .gemini/skills/stale-detector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stale-detector", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install yuque/yuque-ecosystem stale-detector

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add yuque/yuque-ecosystem --skill stale-detector -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/yuque/yuque-ecosystem.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/stale-detector .github/skills/stale-detector && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "stale-detector" agent skill from https://github.com/yuque/yuque-ecosystem/tree/main/skills/stale-detector into .github/skills/stale-detector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stale-detector", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add yuque/yuque-ecosystem --skill stale-detector -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install yuque/yuque-ecosystem stale-detector --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/yuque/yuque-ecosystem.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/stale-detector .opencode/skills/stale-detector && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "stale-detector" agent skill from https://github.com/yuque/yuque-ecosystem/tree/main/skills/stale-detector into .opencode/skills/stale-detector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stale-detector", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: stale-detector
GitHub stars: 228
Token cost: ~1.5k tokens
SKILL.md length: 603 words
Files: 1
Skills in repo: 8
Repo updated: Jul 15, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Scan a Yuque knowledge base for stale or outdated documents and recommend updates or archiving.

Works in 6 steps: Identify the Target Knowledge Base → Fetch Document List → Classify Documents by Freshness → …
The user is cleaning up
SKILL.md covers When to Use, Required MCP Tools, Workflow and Guidelines, plus 1 more section
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Stale Detector is an agent skill from yuque/yuque-ecosystem. Scan a Yuque knowledge base for stale or outdated documents and recommend updates or archiving. Use when the user is cleaning up, maintaining, or periodically reviewing a knowledge base; trigger phrases include “帮我检查哪些文档过期了”, “知识库体检”, and “find stale docs”.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Requires the yuque-mcp MCP server connected with a personal Yuque token

It sits in Knowledge Management, covering Knowledge bases. The repository describes itself as: Yuque AI Ecosystem — MCP Server, Skills & Plugin for Yuque (语雀). The licence is MIT.

When your agent uses it

The user is cleaning up
Periodically reviewing a knowledge base
Trigger phrases include 帮我检查哪些文档过期了
Find stale docs

Example prompts

“帮我检查哪些文档过期了”
“find stale docs”
“/stale-detector”

Requirements

Compatibility (from SKILL.md): Requires the yuque-mcp MCP server connected with a personal Yuque token

Workflow steps

6 steps, taken from the step headings in SKILL.md.

Identify the Target Knowledge Base
Fetch Document List
Classify Documents by Freshness
Deep Analysis of Stale Documents
Generate Maintenance Report
Offer Follow-up Actions

What it can do on your machine

Read from SKILL.md and the folder at commit 2959228. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Compatibility
Requires the yuque-mcp MCP server connected with a personal Yuque token
From compatibility in the SKILL.md frontmatter.

Context cost

Stale Detector loads about 1.5k tokens when it runs. Until then it costs about 68 tokens; SKILL.md has 603 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~68
When it runs · the whole SKILL.md, loaded when a task matches: ~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from yuque/yuque-ecosystem at commit 2959228, republished under its MIT licence (© yuque). 603 words, ~1,549 tokens.

Download SKILL.mdSave it as .claude/skills/stale-detector/SKILL.md (or your agent's skills folder).

name: stale-detector
description: Scan a Yuque knowledge base for stale or outdated documents and recommend updates or archiving. Use when the user is cleaning up, maintaining, or periodically reviewing a knowledge base; trigger phrases include “帮我检查哪些文档过期了”, “知识库体检”, and “find stale docs”.
compatibility: Requires the yuque-mcp MCP server connected with a personal Yuque token
license: MIT
metadata.author: yuque
metadata.version: 1.0

Stale Detector — Knowledge Base Freshness Audit

Scan a Yuque knowledge base to discover documents that haven't been updated in a long time, analyze whether their content may be outdated, and generate a maintenance report with actionable recommendations.

When to Use

User wants to clean up or maintain their knowledge base
User says "帮我检查哪些文档过期了", "find stale docs", "知识库体检"
User wants to identify documents that need updating or archiving
User is doing a periodic knowledge base review

Required MCP Tools

All tools are from the yuque-mcp server:

yuque_list_books — List user's knowledge bases
yuque_list_docs — List all documents in a knowledge base with metadata
yuque_get_doc — Read document content for staleness analysis
yuque_get_toc — Get knowledge base structure

Workflow

Step 1: Identify the Target Knowledge Base

Case A — User specifies a knowledge base: Extract repo_id (namespace) from the provided link or name.

Case B — User wants to scan all knowledge bases: List all repos first:

Tool: yuque_list_books
Parameters:
  user_id: "<user_id>"

Present the list and let the user choose, or scan them one by one if the user confirms.

Case C — User is vague: Ask: "你想检查哪个知识库？我可以先列出你的所有知识库。"

Step 2: Fetch Document List

Get all documents in the target knowledge base:

Tool: yuque_list_docs
Parameters:
  repo_id: "<namespace>"

Extract key metadata for each document:

title — Document title
slug — Document identifier
updated_at — Last update timestamp
created_at — Creation timestamp
word_count — Document length
status — Publication status

If the knowledge base is empty (no documents), inform the user: "这个知识库目前没有文档。"

Step 3: Classify Documents by Freshness

Calculate the age of each document (days since last update) and classify:

Category	Criteria	Label
🟢 Fresh	Updated within 90 days	活跃
🟡 Aging	Updated 90-180 days ago	老化中
🟠 Stale	Updated 180-365 days ago	陈旧
🔴 Dormant	Not updated for 365+ days	休眠

Step 4: Deep Analysis of Stale Documents

For documents classified as 🟠 Stale or 🔴 Dormant, read the content of up to 10 documents (prioritize the oldest and most important-looking ones by title):

Tool: yuque_get_doc
Parameters:
  repo_id: "<namespace>"
  doc_id: "<slug>"

For each document, analyze:

Time-sensitive content — Does it reference specific dates, versions, or events that may have passed?
- Software version numbers (e.g., "React 16", "Node 12")
- Date references (e.g., "2023年计划", "Q3 目标")
- Links that may be broken
- Policies or processes that may have changed
Evergreen content — Is the content timeless?
- Conceptual explanations, principles, personal reflections
- These may be old but still valid
Recommendation:
- Update — Content is valuable but contains outdated information
- Archive — Content is no longer relevant, move to archive
- Keep — Content is evergreen, no action needed despite age
- Review — Uncertain, needs human judgment

If yuque_get_doc fails (404/403), note the document as inaccessible and skip.

Show full SKILL.md (194 more words)Show less

Step 5: Generate Maintenance Report

markdown

## 🔍 知识库健康报告

**知识库**：[知识库名称](知识库链接)
**扫描时间**：YYYY-MM-DD HH:MM
**文档总数**：X 篇

### 📊 整体健康度

| 状态 | 数量 | 占比 |
|------|------|------|
| 🟢 活跃（90 天内更新） | X | XX% |
| 🟡 老化中（90-180 天） | X | XX% |
| 🟠 陈旧（180-365 天） | X | XX% |
| 🔴 休眠（365 天以上） | X | XX% |

**健康评分**：X/100
（计算方式：🟢×100 + 🟡×70 + 🟠×30 + 🔴×0，加权平均）

### 🔴 需要关注的文档

#### 建议更新

| 文档 | 上次更新 | 原因 |
|------|----------|------|
| [文档标题](链接) | YYYY-MM-DD | [e.g., 引用了 Node 12，当前已是 Node 22] |
| [文档标题](链接) | YYYY-MM-DD | [e.g., 包含 2023 年的计划，需要更新] |

#### 建议归档

| 文档 | 上次更新 | 原因 |
|------|----------|------|
| [文档标题](链接) | YYYY-MM-DD | [e.g., 已完成的项目记录，可归档] |

#### 建议保留（虽旧但有效）

| 文档 | 上次更新 | 原因 |
|------|----------|------|
| [文档标题](链接) | YYYY-MM-DD | [e.g., 通用方法论，内容不过时] |

#### 需要人工判断

| 文档 | 上次更新 | 原因 |
|------|----------|------|
| [文档标题](链接) | YYYY-MM-DD | [e.g., 无法确定内容是否仍然有效] |

### 💡 维护建议

1. [具体建议 1：e.g., 建议每季度审查一次「技术文档」分类下的文档]
2. [具体建议 2：e.g., 考虑创建一个「归档」知识库，将不再维护的文档迁移过去]
3. [具体建议 3：e.g., 有 X 篇文档超过 2 年未更新，建议集中处理]

Step 6: Offer Follow-up Actions

After presenting the report, offer:

"需要我帮你把建议归档的文档移到归档知识库吗？"
"需要我帮你逐篇查看需要更新的文档，给出具体的更新建议吗？"
"需要我定期（比如每月）帮你做一次知识库体检吗？"

These are suggestions only — do not take action without user confirmation.

Guidelines

Always answer in the same language the user used (Chinese or English)
Be conservative with "archive" recommendations — when in doubt, suggest "review" instead
Don't read every document in a large knowledge base — sample strategically
The health score is a rough indicator, not a precise metric — present it as such
Evergreen content (personal reflections, principles, methodologies) should not be flagged as stale just because of age
Focus on actionable recommendations, not just listing old documents
If the knowledge base has fewer than 5 documents, simplify the report format

Error Handling

Situation	Action
Knowledge base not found	Inform user and suggest listing their repos with `yuque_list_books`
Knowledge base is empty	Inform user: "这个知识库目前没有文档，无需体检"
`yuque_list_docs` returns error	Inform user of the issue, suggest checking the knowledge base link
Too many documents (100+)	Analyze metadata for all, but only deep-read the top 10 stalest documents
All documents are fresh	Congratulate the user: "知识库状态很健康！所有文档都在活跃维护中 🎉"
API rate limiting	Slow down requests, inform user if the scan takes longer than expected

Files

Just SKILL.md in skills/stale-detector of yuque/yuque-ecosystem.

Open the folder on GitHubat commit 2959228

Compare with similar skills

Stale Detector next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Stale Detector compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Stale Detector this skillyuque/yuque-ecosystem	228	—	~1.5k	Automated safety check: Pass	MIT	2 mo ago
Capture Conversationoutline/outline	41k	—	~474	Automated safety check: Pass	Custom licence	today
Project CairniBlinkQ/project-cairn	235	2 repos	~861	Automated safety check: Pass	MIT	3 days ago
LLM Wiki Knowledge GraphEgonex-AI/Understand-Anything	86k	1 repos	~1.5k	Automated safety check: Pass	MIT	2 days ago
Find And Citeoutline/outline	41k	—	~537	Automated safety check: Pass	Custom licence	today
Xhs Virtual Productchenjin-cmd/xhs-virtual-product	727	—	~862	Automated safety check: Pass	MIT	7 days ago

Similar skills

Capture Conversation
outline/outline
Save the current conversation, a decision, or a set of notes as a document in an Outline collection; use when the user wants to keep what was discussed in their knowledge base.
41k GitHub stars~474 tokensUpdated today
Knowledge ManagementAuto-check passed
Project Cairn
iBlinkQ/project-cairn
Standardize how an AI-collaboration project turns work into reusable knowledge.
235 GitHub starsUsed in 2 repos~861 tokens
Knowledge ManagementAuto-check passed
LLM Wiki Knowledge Graph
Egonex-AI/Understand-Anything
Detects a Karpathy-pattern LLM wiki and builds an interactive knowledge graph with entities, implicit relationships and topic clusters.
86k GitHub starsUsed in 1 repo~1.5k tokens
Knowledge ManagementAuto-check passed
Find And Cite
outline/outline
Answer questions from the Outline knowledge base with quotes and links to the source documents; use when the user asks what the team knows, documented, or decided about a topic.
41k GitHub stars~537 tokensUpdated today
Knowledge ManagementAuto-check passed
Xhs Virtual Product
chenjin-cmd/xhs-virtual-product
This skill helps plan, select, produce, and market Xiaohongshu (RED) virtual/digital products — templates, knowledge bases, test tools, study materials.
727 GitHub stars~862 tokensUpdated 7 days ago
Knowledge ManagementAuto-check passed
Openkb
VectifyAI/OpenKB
A skill your agent uses when the user asks about content in their OpenKB knowledge base — research topics, concepts compiled from their documents, cross-document synthesis — or mentions openkb, an…
4.7k GitHub starsUsed in 1 repo~2k tokens
Knowledge ManagementAuto-check: warnings

Questions about Stale Detector

What does Stale Detector do?

Scan a Yuque knowledge base for stale or outdated documents and recommend updates or archiving. Stale Detector is an agent skill from yuque/yuque-ecosystem. Scan a Yuque knowledge base for stale or outdated documents and recommend updates or archiving.

When should I use Stale Detector?

Stale Detector fits situations like: the user is cleaning up; periodically reviewing a knowledge base; trigger phrases include 帮我检查哪些文档过期了; find stale docs.

How do I install Stale Detector in Claude Code?

Run `npx skills add yuque/yuque-ecosystem --skill stale-detector -a claude-code`. Or copy the skill folder (skills/stale-detector in yuque/yuque-ecosystem) into .claude/skills/stale-detector in your project. Claude Code loads it when a task matches its description.

How do I install Stale Detector in Codex?

Run `npx skills add yuque/yuque-ecosystem --skill stale-detector -a codex`. Or copy the skill folder (skills/stale-detector in yuque/yuque-ecosystem) into .agents/skills/stale-detector in your project. Codex loads it when a task matches its description.

Can I use Stale Detector in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add yuque/yuque-ecosystem --skill stale-detector -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/stale-detector, .gemini/skills/stale-detector, .github/skills/stale-detector and .opencode/skills/stale-detector in your project.

What does Stale Detector need to run?

SKILL.md names no scripts, command-line tools or credentials: Stale Detector is instructions for the agent only. Compatibility (from SKILL.md): Requires the yuque-mcp MCP server connected with a personal Yuque token.

Does Stale Detector access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Stale Detector safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Stale Detector use?

Stale Detector is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Stale Detector use?

About 1.5k tokens (SKILL.md is roughly 6.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Stale Detector?

Skills that share tags, products or a category with Stale Detector: Capture Conversation (outline/outline, 41k stars), Project Cairn (iBlinkQ/project-cairn, 235 stars), LLM Wiki Knowledge Graph (Egonex-AI/Understand-Anything, 86k stars) and Find And Cite (outline/outline, 41k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Stale Detector?

yuque (a GitHub organization) maintains it in yuque/yuque-ecosystem, which has 228 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on July 15, 2026.

Source: yuque/yuque-ecosystem on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Stale Detector

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Compatibility

Context cost

Safety

SKILL.md

Stale Detector — Knowledge Base Freshness Audit

When to Use

Required MCP Tools

Workflow

Step 1: Identify the Target Knowledge Base

Step 2: Fetch Document List

Step 3: Classify Documents by Freshness

Step 4: Deep Analysis of Stale Documents

Step 5: Generate Maintenance Report

Step 6: Offer Follow-up Actions

Guidelines

Error Handling

Files

Compare with similar skills

Similar skills

More from yuque/yuque-ecosystem

Related

Questions about Stale Detector