Skip to main content
skill Claude Code CX Codex Cursor GitHub Copilot official · Anthropic

source-management — Claude Code skill: search sources, install

Manages MCP sources for enterprise search, including connection checks, query priorities, and rate-limit handling.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add anthropics/knowledge-work-plugins --skill source-management -a claude-code
Open on GitHub

What source-management does

The skill inspects available MCP tools to identify connected sources such as chat, email, cloud storage, project tracking, CRM, and knowledge bases. It guides users through adding another source in MCP settings, then includes that source in later searches.

It changes source priority by query type. Status questions start with the project tracker, document searches start with cloud storage, and people queries start with chat. These priorities weight results rather than removing other sources. That gives the search a stated scope.

The skill detects rate-limit errors, avoids an immediate retry, and continues with other sources. A new MCP server can be added through .mcp.json; when a source is rate limited, the resulting search is narrower until access resumes.

What it helps with

  • check which MCP sources are connected
  • order sources for status, document, or people queries
  • guide a user through adding an MCP source
  • continue a search after one source is rate limited
  • add a custom MCP server to .mcp.json

Example prompts for the agent

  • Check the connected MCP sources and report their current status.
  • Find where the project decision was recorded, prioritizing chat and email.
  • The knowledge base is rate limited. Search the other sources and state which ones were covered.

How to install source-management

1Skills CLI (Vercel)

npx skills add anthropics/knowledge-work-plugins --skill source-management -a claude-code

2Manually: put the files in place

~/.claude/skills/source-management/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/source-management/

From the same set89

The whole set →
data-visualization official anthropics Selects chart types based on data structure and produces Python visualization code in matplotlib, seaborn, and plotly. Useful for reports and research figures. Claude Code CX Codex Cursor +1 13,700installs documentation official anthropics A skill for technical writing that drafts READMEs, API references, runbooks, architecture docs and onboarding guides. Useful when the code exists but the description does not. Claude Code CX Codex Cursor +1 10,300installs build-dashboard official anthropics Builds a self-contained HTML dashboard with Chart.js charts, KPI cards, and filterable tables. Useful for turning raw data or queries into a standalone browser report. Claude Code CX Codex Cursor +1 9,100installs memory-management official anthropics This skill organizes workplace shorthand, names, and project details into files an agent can consult. It fits projects where requests rely on an internal vocabulary and shared context. Claude Code CX Codex Cursor +1 7,400installs task-management official anthropics Tracks commitments, active work, and follow-ups in a local TASKS.md file. Useful when managing project to-dos directly from the AI coding chat. Claude Code CX Codex Cursor +1 7,200installs architecture official anthropics Writes an Architecture Decision Record or reviews a system design: options, trade-offs, consequences. Useful when you have to pick between technologies. Claude Code CX Codex Cursor +1 6,700installs knowledge-synthesis official anthropics Merges search results across chats, emails, and documents into deduplicated answers with source attribution. Flags conflicting facts and scores source reliability. Claude Code CX Codex Cursor +1 6,400installs testing-strategy official anthropics This skill designs testing strategies and test plans for a project. Use it when you need test types, coverage goals, or gaps in existing checks. Claude Code CX Codex Cursor +1 6,400installs

Similar

configure official anthropics Checks iMessage channel setup in Claude Code and audits access rules. Use it when messages fail to reach the assistant or to see which contacts are allowed. Claude Code 3,861installs configure official anthropics Sets up the Discord channel for Claude Code by storing the bot token and enforcing allowlist access rules. Claude Code 3,861installs nuxt Anthony Fu This skill equips your AI agent with Nuxt 5 knowledge: server-side rendering, file-based routing, auto-imports, and Nitro v3 deployment. Use it when building Nuxt apps, server routes, useFetch calls, middleware, or hybrid rendering. Claude Code CX Codex Cursor +1 24,100installs mobile-ios-design Seth Hobson Guides native iOS interface work with Apple HIG and SwiftUI patterns. Use it when building views, navigation, or adaptive layouts. Claude Code CX Codex Cursor 23,659installs vscode-ext-commands official github This skill guides VS Code extension command work, covering naming, visibility, localization, icons, and related contribution details. GitHub Copilot 9,000installs technology-stack-blueprint-generator official github This skill scans a codebase and builds a blueprint of its stack, architecture, and coding practices. Use it to document an existing project before making changes or generating more code. GitHub Copilot 9,000installs find-skills vercel-labs Discovers and installs agent skills from skills.sh directly inside your coding assistant. Handy when you need domain-specific workflows for a project. Claude Code CX Codex Cursor +1 4,000,000installs frontend-design official anthropics This skill guides intentional visual design for new interfaces and redesigns. Use it when a generic generated UI is not enough. Claude Code Claude.ai 1,025,790installs

Questions about source-management

How do I install source-management in Claude Code?

Run npx skills add anthropics/knowledge-work-plugins --skill source-management -a claude-code, then run npx skills add anthropics/knowledge-work-plugins --skill source-management -a claude-code again. The skill file is available at ~/.claude/skills/source-management/SKILL.md.

What does source-management do?

It detects connected MCP sources, guides users through adding new ones, prioritizes sources by query type, and handles rate limits during search.

What happens when an MCP source is rate limited?

The skill avoids an immediate retry, continues with other sources, and tells the user which sources were searched. For digests, it records the time range covered before the limit.

Source text

SKILL.md · Apache-2.0
---
name: source-management
description: Manages connected MCP sources for enterprise search. Detects available sources, guides users to connect new ones, handles source priority ordering, and manages rate limiting awareness.
user-invocable: false
---

# Source Management

> If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](../../CONNECTORS.md).

Knows what sources are available, helps connect new ones, and manages how sources are queried.

## Checking Available Sources

Determine which MCP sources are connected by checking available tools. Each source corresponds to a set of MCP tools:

| Source | Key capabilities |
|--------|-----------------|
| **~~chat** | Search messages, read channels and threads |
| **~~email** | Search messages, read individual emails |
| **~~cloud storage** | Search files, fetch document contents |
| **~~project tracker** | Search tasks, typeahead search |
| **~~CRM** | Query records (accounts, contacts, opportunities) |
| **~~knowledge base** | Semantic search, keyword search |

If a tool prefix is available, the source is connected and searchable.

## Guiding Users to Connect Sources

When a user searches but has few or no sources connected:

```
You currently have [N] source(s) connected: [list].

To expand your search, you can connect additional sources in your MCP settings:
- ~~chat — messages, threads, channels
- ~~email — emails, conversations, attachments
- ~~cloud storage — docs, sheets, slides
- ~~project tracker — tasks, projects, milestones
- ~~CRM — accounts, contacts, opportunities
- ~~knowledge base — wiki pages, knowledge base articles

The more sources you connect, the more complete your search results.
```

When a user asks about a specific tool that is not connected:

```
[Tool name] isn't currently connected. To add it:
1. Open your MCP settings
2. Add the [tool] MCP server configuration
3. Authenticate when prompted

Once connected, it will be automatically included in future searches.
```

## Source Priority Ordering

Different query types benefit from searching certain sources first. Use these priorities to weight results, not to skip sources:

### By Query Type

**Decision queries** ("What did we decide..."):
```
1. ~~chat (conversations where decisions happen)
2. ~~email (decision confirmations, announcements)
3. ~~cloud storage (meeting notes, decision logs)
4. Wiki (if decisions are documented)
5. Task tracker (if decisions are captured in tasks)
```

**Status queries** ("What's the status of..."):
```
1. Task tracker (~~project tracker — authoritative status)
2. ~~chat (real-time discussion)
3. ~~cloud storage (status docs, reports)
4. ~~email (status update emails)
5. Wiki (project pages)
```

**Document queries** ("Where's the doc for..."):
```
1. ~~cloud storage (primary doc storage)
2. Wiki / ~~knowledge base (knowledge base)
3. ~~email (docs shared via email)
4. ~~chat (docs shared in channels)
5. Task tracker (docs linked to tasks)
```

**People queries** ("Who works on..." / "Who knows about..."):
```
1. ~~chat (message authors, channel members)
2. Task tracker (task assignees)
3. ~~cloud storage (doc authors, collaborators)
4. ~~CRM (account owners, contacts)
5. ~~email (email participants)
```

**Factual/Policy queries** ("What's our policy on..."):
```
1. Wiki / ~~knowledge base (official documentation)
2. ~~cloud storage (policy docs, handbooks)
3. ~~email (policy announcements)
4. ~~chat (policy discussions)
```

### Default Priority (General Queries)

When query type is unclear:
```
1. ~~chat (highest volume, most real-time)
2. ~~email (formal communications)
3. ~~cloud storage (documents and files)
4. Wiki / ~~knowledge base (structured knowledge)
5. Task tracker (work items)
6. CRM (customer data)
```

## Rate Limiting Awareness

MCP sources may have rate limits. Handle them gracefully:

### Detection

Rate limit responses typically appear as:
- HTTP 429 responses
- Error messages mentioning "rate limit", "too many requests", or "quota exceeded"
- Throttled or delayed responses

### Handling

When a source is rate limited:

1. **Do not retry immediately** — respect the limit
2. **Continue with other sources** — do not block the entire search
3. **Inform the user**:
```
Note: [Source] is temporarily rate limited. Results below are from
[other sources]. You can retry in a few minutes to include [source].
```
4. **For digests** — if rate limited mid-scan, note which time range was covered before the limit hit

### Prevention

- Avoid unnecessary API calls — check if the source is likely to have relevant results before querying
- Use targeted queries over broad scans when possible
- For digests, batch requests where the API supports it
- Cache awareness: if a search was just run, avoid re-running the same query immediately

## Source Health

Track source availability during a session:

```
Source Status:
  ~~chat:        ✓ Available
  ~~email:        ✓ Available
  ~~cloud storage:  ✓ Available
  ~~project tracker:        ✗ Not connected
  ~~CRM:   ✗ Not connected
  ~~knowledge base:      ⚠ Rate limited (retry in 2 min)
```

When reporting search results, include which sources were searched so the user knows the scope of the answer.

## Adding Custom Sources

The enterprise search plugin works with any MCP-connected source. As new MCP servers become available, they can be added to the `.mcp.json` configuration. The search and digest commands will automatically detect and include new sources based on available tools.

To add a new source:
1. Add the MCP server configuration to `.mcp.json`
2. Authenticate if required
3. The source will be included in subsequent searches automatically

© anthropics · Apache-2.0 · anthropics/knowledge-work-plugins

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor