Menu

Individual skill

self_attempt_02

0upvotes

Not available

experiments/codex_gpt5_5_xhigh/reports/skills/task_group_001/self/self_attempt_02/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.

Standard SKILL.md format has not been attested at this commit. No installation command is available; inspect the source.

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.

Declared tags are partial or unavailable.

Files and excerpt

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

Browse files
Read excerpt
# HarborCRM Public-API CRM Handoff Skill

Use this skill for HarborCRM tasks that ask for an import-ready JSON answer from public API data, especially event sponsor/lead handoffs, trade-show prospecting lists, and contact import batches.

## Operating Procedure

1. Read the prompt and the provided answer template first. Treat the template as the contract: exact top-level keys, nested keys, enum spellings, null vs empty string, date format, and sorting rules.
2. Use only the HarborCRM base URL supplied by the runner or prompt. Query public endpoints named in the prompt, plus shared CRM/policy endpoints when listed. Do not inspect local source code or unstaged task files.
3. Fetch policy metadata early. It usually defines the controlled sponsor statuses, platform enums, and hygiene expectations, while the template defines the final field names.
4. Build small lookup tables before deciding records: accounts by account_id, normalized account name, and domain; contacts by contact_id, normalized email, and digits-only phone; campaign members by event/show and contact/account; invoices and opportunities by event_id/account_id.
5. Normalize once and reuse: lowercase trimmed emails; phone numbers as digits only; company/contact names trimmed; dates as `YYYY-MM-DD`; currency and counts as integers.
6. Classify every source record into exactly one output path when the template expects exclusions or removals. Keep reasons mutually exclusive and use only allowed enum values.
7. Produce one JSON object only. Do not add explanatory prose, markdown, comments, or undeclared fields.

## Data-Source Habits