handoff-fusion-engineering
Skill18 starsChanged 2 months agoApache-2.0View on GitHub
Prepare a traceable local Fusion engineering review draft with source identities, artifacts and unresolved assurance gates. Not for sending, publication or release approval.
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- create-fusion-deliverablesSkill
- edit-fusion-designSkill
- inspect-fusion-designSkill
- prepare-fusion-manufacturingSkill
- 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
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 6
Use fusion_handoff_prepare to assemble the user's review evidence, and fusion_handoff_inspect to check an existing draft against current …
≈ “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
Use fusion_handoff_prepare to assemble the user's review evidence, and fusion_handoff_inspect to check an existing draft against current source and stored receipt state. Read the handoff contract when composing structured checks or interpreting freshness failures.
The accepted fields are title, plan_ids, document_ids, requirements, assumptions, reviewers, checks and external_evidence. Only the title is required; missing requirements, sources and checks stay explicit. Select actual producing plans to retain artifact and pending/uncertain job evidence. Do not invent unsupported job_ids, solver-result fields or approval flags.
Discover the active operation schemas and inspect the actual response before choosing check pointers. Automated handoff checks are limited to document.inspect, parameters.list, geometry.measure, geometry.check and cam.inspect. Numeric ranges require a value pointer and an exact observed unit pointer/string; there is no implicit unit conversion. Use identity assertions alongside array positions when the measured parameter or entity matters. Do not select credential fields or infer equality from redaction placeholders; rejected or redaction-altered comparisons cannot establish a result. Fixture values and response shapes do not qualify a live Fusion check.
Link requirements and reviewer IDs explicitly. Use manual procedures for unavailable solver, simulation, drawing, ECAD or engineering review work; they remain not_run. External evidence references and reported hashes are unfetched, unverified metadata. Reviewer assignments do not authenticate reviewers, notify them or record approval.
Known freshness_gaps, malformed coverage, changed source states and missing fingerprints prevent current use of dependent checks. A linked artifact must match its exact producing plan, document, preparation/completion source and implementation contract; an old-source or legacy receipt remains historical. Keep failed, pending and unknown plan outcomes visible. Do not rewrite a stored draft, drop unresolved evidence or refresh a stale assertion into a pass. Collect new observations into a new draft when the task calls for current evidence, keeping the original for comparison.
Return the local draft reference, its evidence scope and the unresolved decisions with their practical impact. A met criterion, screenshot, generated toolpath, setup sheet or provider success is not engineering, machine-collision or regulatory proof. These tools do not send the draft, publish artifacts, update enterprise systems or advance a release. Such actions require their own destination authority and qualified adapter; preparing an already authorized local draft does not require repetitive permission requests.
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.

