Skip to content
Agentmart
Submit a tool

lookup

Use whenever the user mentions the CRM or wants to find someone's record — "crm", "check the crm", "is X in the crm", "look up X", "pull up X", "find X", "X's…

Skill by reggiechan74

IndexedMIT
Write a review

Chalk Labs

Need help deploying lookup?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/reggiechan74-lookup

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use whenever the user mentions the CRM or wants to find someone's record — "crm", "check the crm", "is X in the crm", "look up X", "pull up X", "find X", "X's file / dossier / record", "where is X's dossier", "who is X", "what's X's email / phone / org / title", "when did I last talk to X", "what did X say about Y". Finds the person or organization through the CRM's SQLite index and points to the exact dossier file without searching the repo. For a full pre-meeting brief ("brief me", "prep me"), use intel-briefing instead.

Use cases: sales, productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/lookup

What's inside

Skill name
lookup
Description
Use whenever the user mentions the CRM or wants to find someone's record — "crm", "check the crm", "is X in the crm", "look up X", "pull up X", "find X", "X's file / dossier / record", "where is X's dossier", "who is X", "what's X's email / phone / org / title", "when did I last talk to X", "what did X say about Y". Finds the person or organization through the CRM's SQLite index and points to the exact dossier file without searching the repo. For a full pre-meeting brief ("brief me", "prep me"), use intel-briefing instead.
License
MIT
Instructions
48 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • allowed-tools: must be a space-separated string

Files (1)

  • SKILL.md

SKILL.md (first lines)

## Purpose
The cheapest way to answer "who is this / where is their file / what do I have on them". The CRM keeps an SQLite index of every dossier, so a lookup costs ~100 tokens instead of a repo search. Read as little as possible: one index search, one outline, and at most one section.

Request: $ARGUMENTS

## Rules
- **Never locate records by searching files.** No Grep, Glob, `find`, `ls` or Read over the CRM folder to find a person — the index already has them. Only read a dossier file directly if the user asks you to edit it by hand.
- If the CRM tools are not available yet, load them first with ToolSearch: `select:mcp__plugin_crm_crm__crm_search,mcp__plugin_crm_crm__crm_outline,mcp__plugin_crm_crm__crm_read,mcp__plugin_crm_crm__crm_recent`. If they still cannot be loaded, the MCP server is not connected — tell the user to run `/crm:setup` and stop (do not fall back to searching files).

## Workflow

### 1. Nothing to look up
If the request is empty, call `crm_recent` (limit 10) and show it, then say: "Ask about anyone with `/crm <name>` or just mention them with 'crm'."

### 2. Find the record
Call `crm_search` with `query` = the name, company, alias or dossier code, `paths: true`, `limit: 5`.
- **One match** → go to step 3.
- **Several matches** → show the compact table (ID, name, org, category, last contact) and ask which one with AskUserQuestion. Do not read anything yet.
- **No match** → retry once with the surname, a nickname, or the company name. Still nothing → say so plainly and offer to create a dossier (`crm_create`).
- For organizations you can also filter: `orgType` (e.g. `PM`) or `orgGroup` (e.g. `LENDING`).

### 3. Point to the file
Call `crm_outline` for the matched ID and answer with a short card:

**<Name>** (<ID>) — <org> · <category> · <status> · last contact <date>
Dossier: `<folder path>`

| Section | File | Filled |
|---|---|---|
| index | `<folder>/INDEX.md` | 64% |
| … | … | … |

Keep it to the card — no summary of contents the user did not ask for.

### 4. Answer a specific question (only if asked)
If the request includes a question ("email?", "when did we last talk?", "what did she say about the offer?"), read **one** section with `crm_read` and answer from it:
- contact details, org, title, aliases → `index` (or `profile`)
- last conversation, what was said, follow-ups → `log`
- background, career → `profile`
- personality, motives → `intelligence-profile`
- a company's lending, deals, projects… → its type file (`lending`, `deal-flow`, `projects`, …) from the outline

Quote the answer with the file it came from. If that section does not answer it, say which section likely does and ask before reading more.

### 5. Next step
End with one line offering the obvious follow-up: `/crm:intel-briefing <name>` for a full brief, `/crm:post-meeting <name>` to log an interaction, or `crm_connections` to see who they are linked to.

From reggiechan74/crm-mcp-server, MIT.

More from reggiechan74/crm-mcp-server

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 25, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from reggiechan74

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get lookup running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying lookup?

CallGet help
Cite this page

lookup skill. Agent Mart. https://agentmart.dev/skills/reggiechan74-lookup (last updated 2026-10-24)