Install
$ agentstack add skill-hubspot-agent-cli-skills-audience-targeting ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Foundation
Read bulk-operations/SKILL.md first — pagination, JSONL piping, destructive-op safety. Reshape recipes in bulk-operations/resources/json-patterns.md. Resource: resources/contact-segmentation-filters.md is the filter-expression cookbook (lifecycle, lead status, email engagement, activity, deals, owner).
Filter syntax cheat sheet
Source of truth: hubspot objects search --help.
- One
--filterflag = one AND group:--filter "lifecyclestage=lead AND !hubspot_owner_id". - Multiple
--filterflags are OR'd. Use for enum-OR-enum. - Operators:
=,!=,>,>=,--limit 100 --format json | jq -r '.data[].properties. // empty' | sort -u.
Core fields used here: lifecyclestage, hubspot_owner_id (bare/! for owned/unowned; hubspot owners list for IDs), hs_email_optout (!=true excludes opted-out), hs_email_last_open_date / notes_last_contacted (recency), jobtitle / country / city (string = or ~), num_associated_deals (0 net-new, >=1 has-pipeline).
Firmographics (industry, numberofemployees, annualrevenue) live on companies — see cross-object section.
Common segments
# Recent leads (this quarter, not yet owned)
hubspot objects search --type contacts \
--filter "lifecyclestage=lead AND createdate>2026-01-01 AND !hubspot_owner_id" \
--properties email,firstname,lastname,createdate
# Decision-makers by jobtitle (OR across tokens)
hubspot objects search --type contacts \
--filter "jobtitle~director" --filter "jobtitle~vp" --filter "jobtitle~chief" \
--properties email,jobtitle,company
# Engaged but not yet MQL (opened recently, still lead, opted in)
hubspot objects search --type contacts \
--filter "lifecyclestage=lead AND hs_email_last_open_date>2026-04-01 AND hs_email_optout!=true" \
--properties email,firstname,hs_email_last_open_date
# Geographic — US contacts opted in
hubspot objects search --type contacts \
--filter "country=United States AND hs_email_optout!=true" \
--properties email,state,city
More patterns (lead status, deals, owners, combined AND/OR) in resources/contact-segmentation-filters.md.
Cross-object: companies-in-industry → their contacts
industry/numberofemployees/annualrevenue live on the company. Build the company set, then traverse — never xargs -I{} hubspot objects get per company. associations list emits {"id":"...","type":"company_to_contact"}, feeding directly into a single batched objects get.
# Step 1: target companies. Industry options are portal-specific — discover with:
# hubspot objects list --type companies --properties industry --limit 100 --format json \
# | jq -r '.data[].properties.industry // empty' | sort -u
hubspot objects search --type companies \
--filter "industry=SOFTWARE AND numberofemployees>=100" \
--properties name,industry,numberofemployees \
> target_companies.jsonl
# Step 2: gather association IDs (associations list has no batch --from), then ONE batched
# objects get for all contacts.
while read -r cid; do hubspot associations list --from "companies:$cid" --to contacts; done \
target_contacts.jsonl
# Optional: drop opted-out
jq -c 'select(.properties.hs_email_optout != "true")' target_contacts.jsonl > campaign_audience.jsonl
Saving and reusing a segment
A segment is a JSONL file. Re-use for updates, exports, or re-fetches:
# Save
hubspot objects search --type contacts \
--filter "lifecyclestage=lead AND hs_email_optout!=true" \
--properties email,firstname,lastname,jobtitle \
> segments/opted_in_leads.jsonl
# Assign owner (dry-run first per bulk-operations/SKILL.md)
jq -c '{id, properties:{hubspot_owner_id:"12345"}}' segments/opted_in_leads.jsonl \
| hubspot objects update --type contacts --dry-run
# Re-fetch with different properties later
jq -c '{id}' segments/opted_in_leads.jsonl \
| hubspot objects get --type contacts --properties email,lifecyclestage,hs_lead_status
Destructive ops on a saved segment follow the dry-run → digest → confirm flow in bulk-operations/SKILL.md.
Known limits
- No Lists API surface. Can't save as a HubSpot list or filter by list membership.
~is token-match, not substring. No regex operator.properties getdoes not return enum options — discover viaobjects list+jq.associations listhas no batch--from. Loop to gather IDs, batch the downstreamobjects get.- For >100 results, use the pagination loop in
bulk-operations/SKILL.md.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: HubSpot
- Source: HubSpot/agent-cli-skills
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.