create-gtm-skill
Skill2 starsChanged 29 days agoMITView on GitHub
Author a GTM skill in getcargohq/gtm-skills (one-off CLI job or deployed pipeline). Use when creating, adding, scaffolding, or reviewing a new skill, SKILL.md, cookbook, or pipeline folder in gtm-skills.
In this repository48 other files it gives its agents.
- llms.txtllms.txt
- account-scoringSkill
- agentic-engagementSkill
- apollo-to-cargoSkill
- ask-cargoSkill
- build-tam-listSkill
- call-captureSkill
- clay-to-cargoSkill
- contact-sourcingSkill
- crm-deduplicationSkill
- crm-enrichmentSkill
- enrich-company-dataSkill
- enrich-linkedin-profileSkill
- expansion-signalsSkill
- extract-sales-navigator-searchSkill
- find-b2b-leadsSkill
- find-companies-using-techSkill
- find-linkedin-urlSkill
- find-portfolio-companiesSkill
- find-stakeholdersSkill
- find-work-emailSkill
- goal-coverageSkill
- inbound-qualificationSkill
- linkedin-contentSkill
- meeting-prepSkill
- monitor-buying-signalsSkill
- new-hire-detectionSkill
- next-step-trackerSkill
- readiness-scoringSkill
- research-accountSkill
- score-leadsSkill
- social-listeningSkill
- stalled-deal-nudgeSkill
- standupSkill
- tam-building-advancedSkill
- tam-buildingSkill
- track-funding-roundsSkill
- track-job-changesSkill
- verify-email-listSkill
- visitor-identificationSkill
- waterfall-enrichmentSkill
- web-captureSkill
- website-auditingSkill
- website-buildingSkill
- weekly-planningSkill
- win-loss-reviewSkill
- workspace-healthSkill
- zoominfo-to-cargoSkill
The file
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 6 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 16
Read CONTRIBUTING.md first.
- Very specific: line 34
If the same job exists both ways, they compete for prompts.
- Distinctive: line 51
Do not give both kinds the same stem.
- Very specific: line 104
Do the job (exact cargo-ai orchestration action execute / execute-batch)
- Distinctive: line 152
Do not wrap a single connector action in a tool.
- Distinctive: line 153
Do not declare a segment that restates the play's own filter.
- Very specific: line 154
Do not add examples/example.md until a live install has sanitized audit findings, mappings, a plan summary, and lookup-backed credits.
- Distinctive: line 164
Write the system you write back to: If the outcome updates a CRM record, the play runs on that CRM extract and matches the CRM record id.
- Very specific: line 166
Do not sit a native unifyAccounts / ids map between the play and the write — the run looks successful and nothing lands.
- Distinctive: line 185
TypeScript in a cookbook: Keep it plain enough to adapt:
- Distinctive: line 188
no comments on types or schema fields, and docblocks of a sentence or two.
- Very specific: line 241
Do not claim an outcome for a pipeline skill until it is approved (demo workspace + two implementations in approvals.json).
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Create a GTM skill
This is an authoring skill for people writing this repo. It is not a
customer skill and does not install with npx skills add. The canonical
copy lives in .agents/skills so Codex, Claude Code, and Cursor all load
the same file (the last two via symlink).
Read CONTRIBUTING.md first. That file is the contract the validators
enforce; this file is the procedure.
One folder at the repo root is one customer skill. Install path:
npx skills add getcargohq/gtm-skills/<name>.
1. Pick the kind
| Kind | Frontmatter | Job |
| one-off | metadata.source: one-off | Runs once in a turn: exact cargo-ai command and a price |
| pipeline | metadata.source: cookbook | Deploys a standing play. Customer copy says pipeline, never "cookbook" |
metadata.source must be exactly one of those two strings. The validator
uses cookbook as the internal discriminator. Do not put that word in
README, plugin listings, skill body, or examples. Customers learn: some
skills run once; some deploy a pipeline that keeps running.
If the same job exists both ways, they compete for prompts. Pin the seam in
evals/routing.jsonl: one case that must hit the pipeline, one that must
hit the one-off sibling.
Name the folder after the job, not the vendor. name in frontmatter equals
the folder name. The slug is what an agent matches before it opens the file,
so the kind has to be readable from the name:
| Kind | Shape | Examples |
| one-off | verb + object | enrich-company-data, score-leads, build-tam-list |
| pipeline | the standing practice | tam-building, account-scoring, crm-enrichment |
| migration | x-to-cargo | clay-to-cargo |
A verb says "do this once." A standing noun says "keep this running." That
is how build-tam-list and tam-building stay apart, and why
score-leads pairs with account-scoring rather than score-accounts.
Do not give both kinds the same stem.
enrich-crm would read as a one-off next to enrich-company-data. A
pipeline that keeps CRM records filled is crm-enrichment. Contacts later
stay in that same slug. Accounts that are not in a CRM, if they land, are
account-enrichment. Planned pipelines stay nouns (contact-sourcing,
signal-based-tam, rep-cockpit). Do not rename existing skills to force
-ing vs -ment; the kind matters more than the suffix.
Inside a cookbook, resource slugs are snake_case: plays, workflows, tools,
agents, segments and folders (score_accounts, enrich_crm_contact,
account_enrichment, tam_tier_analyst, tam_tier_a,
crm_enrichment_plays), the same as @cargo-ai/cdk already requires of
connectors and models. Workers and apps are the exception: it requires
kebab-case for them. File names stay kebab-case (score-accounts.ts). A slug
is the resource's identity in cargo.state.json, so renaming one after a
deploy creates a new resource and orphans the old one: get it right before
the first deploy.
A model that extracts a system you hold (a CRM, a warehouse) pulls all the
data. Never filter or pick columns in its config: extract every record and
every column, and narrow in the SQL or the play filter that reads it. A
filter in the config is a second place the question is asked, invisible to
anyone reading the queries, and changing it means a redeploy and a
re-extraction instead of an edited query. A paid search source is the
exception, because there the search is the data source rather than a filter
on it: aiArk.fetchCompanies or a Sales Navigator search bills per returned
record, so its query in config is what decides what you buy.
Native models first. A worked example runs on Cargo native models, not a CRM connector, so it
deploys on a bare workspace. When the outcome needs accounts, contacts, opportunities or activity,
declare the shared gtm_* models exactly as references/native-models.md defines them;
scripts/check-native-models.mjs fails on drift. The CRM is the crm-backed variation.
2. Description (the only text before load)
Four parts, in order:
- The job in one sentence
Triggers:literal quoted phrases a user would type- Proper nouns (connectors, CRM, Cargo project)
Skip when:the sibling skill that should win instead
Quote any YAML value that contains colon-space. Unquoted, the installer skips the file with a warning nobody reads.
3. Write the kind
One-off
Copy the structure of enrich-company-data/SKILL.md:
- Setup (CLI install, login)
- Do the job (exact
cargo-ai orchestration action execute/execute-batch) - Example (see below)
- What it costs (table of
integration.action→ credits) - Worth knowing / Going further / star ask
Slugs and prices are not yours to invent. validate.ts asserts every
integrationSlug/actionSlug and every credit number against
getcargohq/cargo-skills playbooks. Copy from a sibling, then run
node scripts/validate.ts.
Register: skills.sh.json, root README.md table.
Pipeline
Copy the section order from tam-building/SKILL.md. The validator requires
these headings:
- Honest banner:
**State: to-be-approved.** ## The outcome## Example(see below)## Put it in your project(copy the procedure fromtam-building; each skill carries its own)## What you will be asked— derive before ask; more than ~4 asked rows means you skipped lookups## What you can change— offer unprompted; every variation has a cost## What should not change— name the concrete symptom if violated## Done when## What it costs## Composes into
Folder:
<name>/
SKILL.md
README.md
infra/ # or models/, plays/, agents/ — whatever the outcome needs
references/ # supporting agent docs; never a nested SKILL.md
evals/acceptance.mdIsolation: every model and connector the resources import lives in this
folder. No relative import may leave it. Two pipeline skills may both
carry an accounts model; the placing agent rewires to the project's
existing one.
Resources must earn their deploy:
- Do not wrap a single connector action in a tool. That is a one-off.
- Do not declare a segment that restates the play's own filter.
- Do not add
examples/example.mduntil a live install has sanitized audit findings, mappings, a plan summary, and lookup-backed credits. - A folder of resource code with no
SKILL.mddoes not belong at the root. Older examples live in history:git checkout 305cd88 -- <name>, then write the skill.
Credits. Pipeline markdown must not contain a numeric credit amount.
Fetch live prices at run time (cargo-ai connection integration get <slug>).
One-offs quote playbook numbers; pipelines do not.
Write the system you write back to. If the outcome updates a CRM
record, the play runs on that CRM extract and matches the CRM record id.
Do not sit a native unifyAccounts / ids map between the play and the
write — the run looks successful and nothing lands.
One shape in the file. A new pipeline's checked example runs on the
shared gtm_* native models (references/native-models.md); its
crm-backed variation names the HubSpot swap, and Salesforce and Attio adapt
that (connector, extractor, record-id, write action, fill-blank guard). A
pipeline whose whole job is a CRM (crm-enrichment, crm-deduplication) keeps
HubSpot as its checked example. No parallel branches.
Workflow bodies must compile. These fail cargo-ai project check / plan:
undefined/void, comma / SequenceExpression, Date#getTime().
Optional chaining (?.) and ?? are worse: they pass check and plan, then
fail at run time (OptionalMemberExpression), after an agent step has already
been paid for. Write the explicit check instead.
Seed native records without an id: Cargo generates it and rejects one you
pass. Create parents first and read the id back from the create.
TypeScript in a cookbook. Keep it plain enough to adapt:
- early-return
ifover ternaries, especially nested ones; - no comments on types or schema fields, and docblocks of a sentence or two;
- names that say what the value is:
…Resultfor an outcome union,raw…for an API object not yet reshaped, predicates that name their subject (hasEventEnded), numbers that name their unit (…Timestamp,…Ms); - precise return types (
string[], not(string | undefined)[]); - no
nowparameter: read the clock where it is needed, and pin it in tests with fake timers.
Register: skills.sh.json (its stage, at its place in the order: the order is
what an agent suggests next),
root README pipeline table, .github/data/approvals.json with
state: to-be-approved and empty evidence.
Both kinds: personas and the example
validate.ts requires these of every skill; the site renders them before
anyone installs.
metadata.personas, right aftermetadata.source: 1–3 ofsales-development,account-executive,revops,sales-leadership,marketing,gtm-engineering, primary first.## Example, in exactly this shape:## Example > Find work emails for the 40 people in webinar-attendees.csv. Illustrative output, fictional records: <table or fenced block, about 20 lines at most> <one closing line with the result in numbers>Fictional companies on the
.exampleTLD. A one-off's credits must add up from its own cost table; a pipeline quotes none and shows what the deployed play writes. Never a command in it, and never a table row that opens on a backtickedintegration.actioncell — the validator reads that as a price.
4. Finish
node scripts/build-catalog.mjs
node scripts/generate-llms-txt.ts
npm run typecheck
npm run validate
npm run format:checkcatalog.json and llms.txt are generated. Edit SKILL.md, then regenerate.
Do not claim an outcome for a pipeline skill until it is approved (demo
workspace + two implementations in approvals.json). The banner in
SKILL.md must match that file exactly.
Anti-patterns
- A new root skill that is the same job as an existing slug with extra
words (
crm-account-enrichmentvscrm-enrichment) - A pipeline named like a one-off (
enrich-crm,score-accounts,build-tam) or a one-off named like a pipeline (tam-buildingfor a list today) - Customer-facing "cookbook"
- Hardcoded credits in a pipeline
- Stub walkthroughs that restate
SKILL.md PLACEHOLDERvalues that survive into a "done" template when the checked example can use real HubSpot (or whatever) property names- Asking the operator for anything a connector or live schema can answer
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

