Individual skill

harbor-crm-integration

Build integrated HarborCRM workflows that join event, CRM, finance, trade-show, import-batch, and policy endpoints into reconciled, classified, and structured outputs. Use when the task involves: (1) post-event CRM handoff or reconciliation, (2) trade-show exhibitor prospecting with qualification and tiering, (3) import-batch cleaning, deduplication, and CRM import preparation, (4) cross-domain data joining across HarborCRM API segments, or (5) template-driven JSON output construction with controlled-enum classification and sorting rules.

experiments/codex_skill_creator_comparison_deepseek_v4_pro_max/reports/skills/task_group_001/fewshot/deepagents/fewshot_attempt_01/SKILL.md

Read pinned source

Source commit 5082a777379156a048881e94940d640702e5e09a

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: No
Repository scan complete: No
Skill scan complete: No
Observed behavior: Not checked yet
Last checked: Nov 6, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 121
Repository last updated: Oct 29, 2026
License: Apache-2.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

agent Repository topic
ai Repository topic
benchmark Repository topic
llm Repository topic
self-evolving Repository topic
self-learning Repository topic
skills Repository topic
sales Derived category
finance Derived category
data Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 9,906 bytes
SKILL.mdcore · 9,906 bytes
references/endpoints.mddoc · 4,962 bytes

Read excerpt


# HarborCRM Integration

## Core workflow

Every HarborCRM task follows the same skeleton:

1. Fetch the answer template from the task payload and read every field, enum, and sort rule.
2. Discover the task's domain anchors (event_id, show_id, batch_id) from the prompt.
3. Pull all relevant domain records in parallel where possible:
   - **Core entity** — event, trade show, or import batch metadata.
   - **Related children** — orders/badges/sponsor-packages, exhibitors/meeting-interest, raw-contacts/suppression.
   - **CRM cross-reference** — accounts, contacts, opportunities, campaign members.
   - **Policies** — always fetch `/api/policies`; they encode qualification criteria.
4. Build an in-memory join graph across domains. Match on ids where available (account_id, event_id, company_id), and fall back to company/contact name matching when normalizing.