prepare-fusion-manufacturing
Skill18 starsChanged 2 months agoApache-2.0View on GitHub
Prepare qualified Fusion CAM setups, operations, toolpaths and quarantined NC candidates using explicit manufacturing assets and authority. Never controls physical equipment.
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- create-fusion-deliverablesSkill
- edit-fusion-designSkill
- handoff-fusion-engineeringSkill
- inspect-fusion-designSkill
- reconcile-fusion-dataSkill
- run-fusion-cloud-recipesSkill
- setup-autodesk-fusionSkill
- analyze-log-signalsSkill
- inspect-infrastructure-healthSkill
- investigate-application-performanceSkill
- monitor-iot-edgeSkill
- review-business-kpisSkill
- setup-grafana-observabilitySkill
- audit-ios-readinessSkill
- plan-react-native-portSkill
- port-react-native-sliceSkill
- verify-swiftui-paritySkill
- audit-review-eval-validitySkill
- benchmark-review-configsSkill
- normalize-review-runsSkill
- recommend-review-reference-architectureSkill
The file
Files
Inspect CAM and discover cam.setup_schema / cam.operation_schema. A compatible strategy is not entitlement proof. Use individually qualified variants.
Resolve stock, fixtures, WCS axes/origin, clearance, feeds/speeds, machine and units from approved inputs. Do not infer safety fields from hidden defaults. Select full tool/holder hashes using cam.tools_list; templates, libraries, posts and machines are reviewed privileged assets.
Prepare changes with fusion_cam_changes_prepare, execute within scope, then explicitly generate toolpaths and poll the durable job. Inspect actual operation validity and results. Generation is not collision verification; unsupported cancellation remains unsupported.
Machining-time calls require explicit rapid/feed/tool-change assumptions and return estimates. Setup sheets are review artifacts.
NC requires exact operation order, pinned post/machine/full tooling, and an unexpired operator verification record bound to current state. Use fusion_nc_prepare and fusion_nc_generate; changed inputs invalidate review. Keep Fail/duplicate-tool safeguards and quarantine. Never transfer/start equipment or claim a launched UI proves collision safety. See enterprise boundaries.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

