zime-ai/zime-gtm-skills

Install · Try it · See it work · Skill map · All skills · Connect your CRM · FAQ

If you’re building call-review or deal-inspection tooling in-house, start here. 71 Agent Skills audit sales call transcripts and CRM exports against GTM rubrics. You give a skill one file and get one audit back, with a quote or a cell behind every finding. It runs locally with no credentials, and nothing leaves your machine. It works with Claude Code, Cursor, Windsurf, OpenAI Codex, and any agent that reads the Agent Skills spec.

These skills credit a call only for what the buyer said, and each one targets what reps usually skip at that deal stage. A rep’s claim never counts as evidence. A topic the call never touched scores Missed. Every dimension lists what does not count (price worry is not a budget, a date for the next meeting is not a decision date, a job title is not authority) and gives the rep one question to ask next time.

Skills sort on two axes: deal stage (discovery through renewal) and initiative (MEDDICC, BANT, pain identification, and other frameworks that run at any stage).

Every skill follows one rule: a finding without a quote or a timestamp does not ship. Each dimension marked Covered, Partial, or Missed points at the line that earned it.

MIT, no gating, no telemetry, no lead capture. Fork it, rewrite the rubrics for your motion, and ship it internally. Zime builds and maintains this repo, and we would rather hand over the rubrics than talk anyone out of building.

Contributions are welcome, see CONTRIBUTING.md. To report a bug or ask a question, open an issue.

Ask your agent in plain words