tam-building SKILL.md skillA
tam-building from getcargohq/gtm-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add getcargohq/gtm-skills/tam-building@v0.5.0Pins v0.5.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- getcargohq/gtm-skills
- Path
tam-building/SKILL.md- Versions recorded
- 11
- Latest version
- v0.5.0, committed Oct 4, 2026
- First version recorded
- Aug 28, 2026
- Size
- 23,100 bytes
- Repository stars
- 3
- License
- MIT
Stand up your account universe as a deployed model: an ICP read from your workspace context (or drafted from your website and customer stories when none is written), turned into an AI Ark company search that always sets industries, company size and countries, sized for free before it bills, and landed as one model in Cargo. Triggers: "our TAM is a stale CSV", "build our account universe", "source every company that matches our ICP", "keep our market list in Cargo…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Tam building
## The outcome
Your account universe as one model in Cargo: every company that matches a written ICP, sourced from
AI Ark. The cookbook is atomic. It deploys one connector, one model and one folder, and needs
nothing else to work: no CRM, no LLM, no play.
Two parts, and each fails in a different way.
**The ICP comes from the context layer.** If the workspace context already holds an ICP or a
scoring file, that is the definition. If not, the agent drafts one from the company's website, its
customer stories and those customers' LinkedIn pages, and the operator corrects it. Either way,
before any filter is built, three criteria are settled: **industries, company size, and
countries**. They are the floor of every TAM.
**Sourcing is arithmetic and it is where the money goes.** `aiArk.fetchCompanies` bills per
returned record, so the ICP filter in `infra/models/tam-companies.ts` is the invoice.
`aiArk.countCompanies` takes the same filter groups, returns `{"count": N}`, and is free: run it for
every candidate filter before anything is deployed.
What happens to the companies next (a CRM coverage check, enrichment, deduplication, scoring) is a
…Read the whole file at its exact version.
How to install
mdr add getcargohq/gtm-skills/tam-building@sha256:423a894eb6d4ee34The line at the top of this page pins the label v0.5.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_e5i2464ydleisk23)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 11 versions of this file, between Aug 28, 2026 and Oct 4, 2026, about one every 4 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.5.0 latest | 2026-10-04 | 25d7a43 | 23,100 B | A | view · diff |
| v0.5.0 | 2026-10-04 | 0ead532 | 23,244 B | A | view · diff |
| v0.3.1 | 2026-10-02 | 59c6320 | 25,737 B | A | view · diff |
| v0.3.1 | 2026-10-02 | da379e9 | 25,820 B | A | view · diff |
| v0.3.1 | 2026-10-01 | 9717763 | 25,799 B | A | view · diff |
| v0.3.1 | 2026-09-29 | 1531b78 | 25,721 B | A | view · diff |
| v0.3.0 | 2026-09-17 | 6b6530d | 23,971 B | A | view · diff |
| v0.3.0 | 2026-09-16 | a096621 | 24,104 B | A | view · diff |
| v0.3.0 | 2026-09-03 | cb5bbaf | 23,988 B | A | view · diff |
| v0.2.0 | 2026-09-02 | 561490a | 13,177 B | A | view · diff |
| v0.2.0 | 2026-08-28 | d78dffe | 12,924 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (23100 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
getcargohq/gtm-skills · 3 stars · license MIT · pushed 2026-10-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_e5i2464ydleisk23 GET https://markdownregistry.com/api/v1/resolve?ref=getcargohq/gtm-skills/tam-building GET https://markdownregistry.com/api/v1/blob/423a894eb6d4ee344699b95989559983a33c96eed0b851b372c79ba55ecf20b9
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.