company-identity-resolution

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)

# Company Identity Resolution

## What this does

Every enrichment downstream is only as good as the identity it was run on, and company names collide constantly across markets, subsidiaries and rebrands. This skill resolves name to domain with a stated confidence, and refuses a low confidence match rather than guessing, because a wrong match silently poisons every column after it.

## 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: company-identity-resolver 0.007 USD per company. |
| 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

- I have company names but no domains
- the enrichment matched the wrong company
- resolve these company names
- which domain is this company
- ambiguous company names

## Inputs

- **names**: the company names as they appear
- **hints**: any extra context: country, industry, a person who works there
- **threshold**: the confidence below which you would rather have nothing

## 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

Resolution takes a name, a domain, or a profile URL and returns the canonical record with the others filled in.

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 |
| --- | --- | --- | --- |
| Company Identity Resolver | `resolve_company_identity` | name, domain and profile URL reconciled into one canonical company record | https://apify.com/mambalabs/company-identity-resolver |

Runnable example input, matched to the live tool schema:

`resolve_company_identity`:

```json
{
  "company_name": "Example Co",
  "skipCache": false
}
```

**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. Normalize the input names first: strip legal suffixes, punctuation and trailing descriptors, because those are the main source of false misses.
2. Resolve with whatever identifier is strongest. A profile URL beats a domain, a domain beats a name, and a name alone is the weakest input there is.
3. Return a confidence per match and set a floor. Below the floor, return nothing rather than a guess, and mark the row for human review.
4. Watch for the three collision types: same name different company, parent versus subsidiary, and pre rebrand versus post rebrand. Each needs a different tiebreak.
5. Use the hints as tiebreaks, not as filters, so a wrong hint does not eliminate the right answer.
6. Report the resolution rate for the batch, because that number decides whether the list is usable at all.
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 resolved table with input, resolved domain, canonical name, confidence and method; the unresolved rows flagged for review; and the batch resolution rate.

## 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

- Low confidence matches return nothing rather than a guess
- The confidence floor is stated as a number
- Parent and subsidiary collisions are handled explicitly
- The batch resolution rate is reported

## Related skills

From mambalabsdev/mamba-labs-skills, MIT.

More from mambalabsdev/mamba-labs-skills