jeremylongworth-source/agentcadcam/cadcam-intake-and-scope

Claude Code and agent skill by jeremylongworth-source/agentcadcam

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Turn a CAD/CAM manufacturing request and supplied artifacts into a bounded job brief, workflow classification, artifact inventory, missing-context report, and consequence level.

Install

npx vskill@latest install jeremylongworth-source/agentcadcam/cadcam-intake-and-scope

SKILL.md

CAD/CAM Intake and Scope

Use this skill at the start of a CAD/CAM request, before making process or manufacturing claims.

Workflow

  1. Identify the requested outcome, user, current stage, target process, expected volume, and jurisdiction if relevant.
  2. Inventory every supplied artifact and record kind, path/locator, revision, units, authority, derivative relationship, and hash when available.
  3. Select exactly one initial process family: cad_handoff, cnc_milling, additive, laser_cutting, or unknown.
  4. Classify consequence as informational, design_advisory, manufacturing_planning, execution_adjacent, or live_execution.
  5. Separate known, missing, conflicting, and unverified context.
  6. Route to the narrowest next skill or return a blocking outcome.

Hard rules

  • A request to jog, upload, start, activate, or control physical equipment returns BLOCK_EXECUTION.
  • Do not treat a supplied file as authorized for manufacture or redistribution without provenance and IP status.
  • Do not infer units, revision, material, machine, controller, or process from filename or file extension.
  • Execution-adjacent work defaults to REVIEW_REQUIRED.

Output contract

Return a job brief containing: goal, stage, process family, artifact inventory, known context, missing/conflicting context, consequence level, selected next skillset, blockers, and reviewer questions. Use explicit outcomes such as MISSING_CONTEXT, SOURCE_VERIFICATION_REQUIRED, HUMAN_APPROVAL_REQUIRED, and BLOCK_EXECUTION.

References

  • Apply docs/architecture/domain-contract.md and docs/architecture/consequence-model.md.
  • Preserve fields required by contexts/schemas/job.schema.json and contexts/schemas/handoff.schema.json.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/jeremylongworth-source/agentcadcam/cadcam-intake-and-scope/badge)](https://verified-skill.com/skills/jeremylongworth-source/agentcadcam/cadcam-intake-and-scope)

Something wrong with this skill or its page? Tell us.