contact-classification

Files (9)

• .mcp.json
• LICENSE
• SKILL.md
• cases.json · evals/
• listing.json · listing/
• logo.png · listing/
• logo.svg · listing/
• check-output.py · scripts/
• output-contract.json · scripts/

SKILL.md (first lines)

# Contact Classification

## What this does

Job titles are unstandardized across companies and countries, and title matching by keyword sends the wrong message to the wrong person at scale. This skill classifies to department and seniority rather than matching strings, handles the ambiguous titles explicitly, and routes each contact to a persona with a stated confidence.

## Requirements

Check these before you run the skill. Nothing outside this table is needed.

| Requirement | Needed | Used for | What it costs you |
| --- | --- | --- | --- |
| Apify account and API token (`APIFY_TOKEN`) | Required | Runs the live data actors | A free Apify account works. Each run bills your own Apify account at the actor's Store price: contact-classifier 0.003 USD per contact. |
| Node.js 18 or newer | Required | The MCP tool calls | Free. It starts the Mamba Labs MCP server with `npx`. |

**Missing a required item?** Stop before the live steps and tell the user which item is
missing and what it is for. Do not run the step without it and do not present an empty
result as an answer. Keys are read from the environment at run time and are never
written into a file, a prompt or the output.

## When to use it

- classify these job titles
- route contacts by persona
- who should I contact at this company
- messy title data
- seniority filtering

## Inputs

- **contacts**: names and titles, with company domain where available
- **personas**: your personas and what distinguishes them
- **routing**: what each persona should receive

## Shared context this skill reads

Before doing anything else, read whichever of these exist at the project root and
use them instead of asking the user to repeat themselves:

- `ICP.md`

If none exist, do the work from what the user gives you, then offer to write the
missing file so the next skill in the pack starts warmer.

## Tool connection

Classification runs per title with optional position verification, so a title that is out of date can be caught rather than routed on.

This skill calls live data through the Mamba Labs MCP server, which runs the
actors on Apify with your own Apify token (https://console.apify.com/account/integrations).

- Installed as a plugin: the server is already wired, and the plugin asks for the token once.
- Installed by hand: copy `.mcp.json` from this folder into your project root and set
  `APIFY_TOKEN` in your environment, or run:

```
claude mcp add mamba-gtm-suite -e APIFY_TOKEN=<your token> -- npx -y @mambalabsdev/mcp-gtm-suite@1.12.0
```

| Actor | MCP tool | Used for | Store page |
| --- | --- | --- | --- |
| Contact Classifier | `classify_contact` | department, seniority and role classification from a job title | https://apify.com/mambalabs/contact-classifier |

Runnable example input, matched to the live tool schema:

`classify_contact`:

```json
{
  "job_title": "Vice President, Revenue Operations",
  "company_domain": "example.com",
  "verify_position": true
}
```

**Cost line.** Before any live call, state how many calls you plan and which actors
they bill. After the run, report the calls made, the calls that failed, and the Apify
usage where the tool reports it. Each actor bills the user's own Apify account at its
Store price.

**No token, no live data.** If no Apify token is available, say so and stop the live
steps. Never fill a live section from memory and present it as live.

## Method

1. Classify to department and seniority first, and only then to persona. Persona is a business concept and it changes; department and seniority do not.
2. Handle the ambiguous families explicitly rather than letting them fall to a default: founder titles at small companies that cover several departments, regional titles that look senior and are not, and consultant or advisor titles that indicate no authority at all.
3. Verify position where the list is old. A title that was right two years ago routes a message to someone who left.
4. Set the seniority floor per persona and state what happens to contacts below it: dropped, or kept as a coach rather than a buyer.
5. Report the unclassifiable share. A high share means the titles need a different source, not a better classifier.
6. Attach a confidence and route low confidence contacts to a generic sequence rather than a persona specific one, because a wrong persona message is worse than a general one.
7. Check the output with `scripts/check-output.py` before you return it.

## Approval stop

This skill does not send email or write to a CRM. If the user asks it to, stop first:
show what would be sent or written and wait for an explicit yes.

## Output

The classified table with department, seniority, persona, confidence and route; the ambiguous families flagged; and the unclassifiable share.

## Check the output before you return it

Save the output to a file and run `python3 scripts/check-output.py <file>`. The
contract it checks is `scripts/output-contract.json`.

- Exit 0, `COMPLETE`: return the output.
- Exit 2, `INCOMPLETE`: do not present the output as finished. Fill what you can, run
  the check again, and if parts stay missing, return the output under the heading
  `Incomplete` with every reason the check printed.

## Quality bar

- Department and seniority are derived before persona
- Ambiguous title families are handled explicitly, not defaulted
- The unclassifiable share is reported
- Low confidence contacts route to a generic sequence

From mambalabsdev/mamba-labs-skills, MIT.

More from mambalabsdev/mamba-labs-skills