PartLine
SkillAI & modelsLets your agent find exact replacement parts by phoning approved suppliers and comparing quotes.
Use PartLine in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add PartLine and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the PartLine skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; Ahel provides instructions and does not run this skill.
No other account needed.
Add Ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
About this skill
Safely source an exact industrial replacement part by calling approved suppliers with CALL-E and returning an evidence-backed comparison for human purchase approval.
What this skill tells your AI
The instructions your AI receives, as published by calle-ai/awesome-phone-call-agents in skills/partline-part-sourcing/SKILL.md and read by Ahel’s review.
Use this skill when a maintenance or procurement user needs current supplier facts that are best confirmed by phone: exact part identity, on-hand quantity, shipping cutoff, lead time and explicitly confirmed alternatives.
Required inputs
Collect all of the following before creating a preview:
- requester and facility
- sourcing request ID
- exact manufacturer and part number
- quantity and need-by timestamp
- non-negotiable physical or electrical specifications
- whether alternatives may be discussed
- one to five supplier phone numbers in E.164 format
- region, locale and a purpose-bound authorization reference for every contact
- the suppliers' local timezone and weekday calling window
Do not infer missing specifications. Do not search for personal phone numbers. Use business contacts provided or approved by the user.
Workflow
- Write the request to a JSON file matching
assets/example-request.json. - Run
partline preview REQUEST.json. - Show the masked recipients, call count, exact task, purchase boundary and approval token.
- Pause for explicit user approval. A request to preview is not approval to call.
- Only after explicit approval, run the exact command printed by preview.
- Poll the returned call ID. Never create a second task because polling timed out.
- Rank exact matches before compatible matches. Mark unknown, contradictory or unsupported results for human follow-up.
- Present evidence and caveats. Never purchase, reserve, negotiate or accept supplier terms.
Safety rules
- Preview by default.
- Never pass
--livewithout explicit approval in the current conversation. - Never call outside the configured weekday call window.
- Never include another supplier's name, quote or inventory in a call.
- Never claim compatibility unless the supplier confirms every required specification.
- Treat a proposed alternate as requiring engineering approval.
- Do not persist raw transcripts unless the user provides a retention purpose and location.
- A CALL-E result supplies research evidence, not purchasing authority.
Useful commands
The reference implementation lives in apps/python/partline.
cd apps/python/partline
python3 -m venv .venv && source .venv/bin/activate
pip install -e .
partline preview fixtures/example-request.json
partline summarize fixtures/completed-call.json --request fixtures/example-request.json
preview never places a call. It prints masked recipients, the call count and an
approval token that is bound to that exact request. A live run additionally
requires --live, the matching token and an open weekday call window.
Signals
- GitHub stars
- 104
- Forks
- 528
- Last commit
- Sep 2026
Ahel review
K1binfo
installs-packages
Automated review, not a security audit. Ruleset v1+k2.
Advanced
- Item type
- skill
- Key
partline-part-sourcing- Source
- github.com/calle-ai/awesome-phone-call-agents
github.com/calle-ai/awesome-phone-call-agents
More in AI & models
Skill · anthropics
More in AI & modelstriage
Skill · mattpocock
More in AI & modelswayfinder
Skill · mattpocock
More in AI & modelsalgorithmic-art
Skill · anthropics
More in AI & modelscode-review-and-quality
Skill · addyosmani
More in AI & modelsmarketing-psychology
Skill · coreyhaines31
More in AI & models