run-fusion-cloud-recipes
Skill18 starsChanged 2 months agoApache-2.0View on GitHub
Prepare, submit and reconcile reviewed Fusion Automation jobs with exact sources, scoped authorization and explicit budgets. Not for arbitrary model-generated cloud scripts.
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- create-fusion-deliverablesSkill
- edit-fusion-designSkill
- handoff-fusion-engineeringSkill
- inspect-fusion-designSkill
- prepare-fusion-manufacturingSkill
- reconcile-fusion-dataSkill
- 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
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Use fusion_cloud_job_prepare to resolve actual dependencies and reservation.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Inspect fusion_cloud_status, authorization owner, reviewed recipes, scope and admission budget. Never reuse native MCP tokens, distribute a client secret or request a PAT.
Choose an installed recipe and declared typed inputs. Freeze exact source versions/configuration/hashes. A generic signed activity does not constrain code, data or cost.
Use fusion_cloud_job_prepare to resolve actual dependencies and reservation. Required hard-cap or immutability guarantees remain blockers when unsupported; do not weaken them silently.
For a bounded batch, use fusion_cloud_batch_prepare with one approved recipe, frozen common source context, approved object-storage destination, a stable request key and explicit unique variant IDs. Review the whole prepared mapping before submission. fusion_cloud_batch_resume admits only the requested bounded wave of unattempted children; it does not refresh expiry, bypass per-job budgets or publish into Fusion/ERP. Use fusion_cloud_batch_inspect after interruption, and retain each child job ID for detailed status, output validation and billing.
Submit the unchanged plan with an existing compute grant and unique idempotency key. Durable intent/reservation precedes submission. Lost acknowledgments and unknown states never justify blind resubmission.
Poll the plugin job ID. Provider success remains validating until trusted output checks pass. Cancel only where qualified; cancellation is not rollback or free compute. Final billing comes from the trusted reconciliation adapter; unknown exposure retains its reservation.
Unknown validation intent or a recorded output-identity collision blocks the batch. Do not clear records, regenerate keys, revalidate to erase a conflict or submit remaining variants as a workaround. A receipt ID collision check does not prove physical storage-key isolation; that is part of the trusted stager's qualification.
Report processing, validation, artifact and cost evidence separately. Offline mocks do not establish geometry, residency, metering or service compatibility. See enterprise recipes and batch recovery.
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.

