Agent skill

luma-inbound-webhook-enrich

DRAFT.

activeNeeds a keyInstructions only205 words

Filed under Prospecting and list building.

From getaero-io/gtm-eng-skills · 21 skill entries · 60 · pushed 2026-09-21

What it does when it runs

DRAFT. Design and harden a standing Luma registration/unsubscribe webhook that enriches guests and writes to CRM or customer DB — with backfill and versioning. Not installed by deepline skills.

Automated analysis of the skill and the 2 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply: ATTIO_API_KEY
HUBSPOT_API_KEY
LUMA_WEBHOOK_SECRET
Hosts it reaches: www.linkedin.com
Tool permissions it declares: No allowed-tools in the frontmatter. It only issues instructions, so there is nothing to bound.
Actions present in the files: None. Instructions only.

Our read

Computed from the artifact. Nothing here has been run, so none of it is a claim about how well the skill works — only about what it is and what it needs.

Maintenanceactive

Pushed within the last 30 days, with commits in the last 90.

CouplingNeeds a key

Needs something you have to obtain separately before it can run. Specifically: ATTIO_API_KEY, HUBSPOT_API_KEY, LUMA_WEBHOOK_SECRET.

Blast radiusInstructions only

No shell, no file writes, no network calls in the skill or its bundled files.

What it does to your systemsUnreviewed

The reading was not confident enough, or not yet confirmed, to publish.

Sends messages: No step found in the source
Writes records: Unreviewed
Spends credits: Unreviewed
Needs credentials: Yes, by pattern match
Declared in the skill's bundled files: ATTIO_API_KEY, HUBSPOT_API_KEY, LUMA_WEBHOOK_SECRET
drafts/luma-inbound-webhook-enrich/SKILL.md (bundled files) at ce24f7d ↗

Read from source, not tested by running. Machine-read from SKILL.md at commit ce24f7d with jev-1.13.0; labels that write, send or spend were also checked against the cited line by a second reviewer. How this is read

Substancebrief

Under 600 words, no bundled reference files.

LicenceMIT

Permits redistribution with attribution, per the repository.

Ask about luma-inbound-webhook-enrich

Opens your assistant with this page's verified links already in the prompt.

Is this safe to install?Claude ChatGPT

Adapt it to my stackClaude ChatGPT

What else do I need for it to workClaude ChatGPT

Rather ask a human? Talk to Cheetah

Install it

View source on GitHub ↗

git clone --depth 1 --filter=blob:none --sparse https://github.com/getaero-io/gtm-eng-skills.git /tmp/gtm-eng-skills
git -C /tmp/gtm-eng-skills sparse-checkout set "drafts/luma-inbound-webhook-enrich"
mkdir -p ~/.claude/skills/luma-inbound-webhook-enrich
cp -R "/tmp/gtm-eng-skills/drafts/luma-inbound-webhook-enrich/." ~/.claude/skills/luma-inbound-webhook-enrich/

Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗

Or take the whole library

This repo ships a .claude-plugin manifest, so Claude Code can install all 21 skills at once. Plugin skills are invoked as /<plugin>:<skill>, so they never collide with your own.

/plugin marketplace add getaero-io/gtm-eng-skills
/plugin

The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.

Before you install: this skill will not complete its job on a bare agent. It needs ATTIO_API_KEY, HUBSPOT_API_KEY, LUMA_WEBHOOK_SECRET, which you have to obtain separately.

The skill

Source on GitHub ↗

Reproduced in full from getaero-io/gtm-eng-skills/blob/ce24f7d2f73830ad3690ff2e6c57c375d818e6fc/drafts/luma-inbound-webhook-enrich/SKILL.md, which is licensed MIT (repository). 205 words, 6 headings.

Luma inbound webhook enrich (DRAFT)

Goal

Registration events become a durable system: webhook → validate → normalize LinkedIn → enrich → upsert CRM/DB → optional Slack notify. Not a one-off CSV import after the event.

Design checklist

Trigger: Luma registration / unsubscribe (document exact event names you subscribe to).
Idempotency: upsert key = email (plus event id).
Normalize: LinkedIn slug → canonical https://www.linkedin.com/in/... URL.
Enrich: cheap fields first; gate expensive providers.
Write: CRM or customer DB fields listed in references/field-map.md.
Failure mode: keep original failed payload; dead-letter queue; backfill later.
Versioning: bump play/workflow version on each mapping change; never silent overwrite of prod without dry-run.

Backfill pattern

Export failed webhook payloads (or Luma guest delta since last success).
Re-run through the current versioned play.
Leave original failed records intact for audit.
Report: attempted / succeeded / still failing.

Pair with

luma-event-campaign for outbound staging
event-ops-score-and-door for capacity decisions (separate from inbound enrich)

Guardrails

Do not log raw PII into public git.
Secrets only via secret store / workflow secrets — never in SKILL.md.
Ask before replaying large historical backfills (cost + CRM noise).

Files bundled with it

These load only when the skill asks for them, so they cost nothing until it runs.

Other skills for the same job

Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.

inbound-lead-audit-cx-map by zapier · 339
enrich-with-signals by Othmane-Khadri · 310
workflows-inbound-lead-routing by clay-run · 121
enrich-company by explorium-ai · 52
enrich-contact by explorium-ai · 52
outreach-enrich by emelia-io · 15
gtm-workflow-enrich-network by eliasstravik · 13
inbound-triggers-30 by Frontal-so · 5

Need help setting it up?

This page tells you what luma-inbound-webhook-enrich does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.