design-review-package
Skill16 starsChanged 16 days agoMITView on GitHub
Assembles a design-review package for a mechanical product — requirements traceability matrix, design FMEA with RPN and action priority, costed multi-level BOM with Pareto and lead-time critical path, risk register, and a PDR/CDR checklist — as one consistent document. Use when the user is preparing a design review, PDR, CDR, gate review, or asks for an FMEA, BOM roll-up, or requirements matrix.
In this repository34 other files it gives its agents.
- skills/cadsmith-text-to-cad/references/agents.mdAGENTS.md
- agentscad-fdm-dfamSkill
- am-alloy-screeningSkill
- am-literature-ragSkill
- cadsmith-text-to-cadSkill
- cfd-simulation-setupSkill
- dfm-reviewSkill
- drawing-gdt-reviewSkill
- engineering-calc-reportSkill
- equation-discoverySkill
- image2gcodeSkill
- lattice-inverse-designSkill
- linkage-synthesisSkill
- llm-3d-print-monitorSkill
- llm-mechanical-designerSkill
- lpbf-defect-predictionSkill
- lpbf-superresSkill
- machine-element-sizingSkill
- material-selectionSkill
- mechanical-teardownSkill
- mechanics-visualsSkill
- meltpool-geometrySkill
- parametric-part-cadSkill
- query2cad-freecadSkill
- quick-feaSkill
- rocketsmithSkill
- sketch-to-cadSkill
- sls-process-optimizationSkill
- stress-field-surrogateSkill
- thermal-fluids-calcSkill
- thermal-porositySkill
- tolerance-stackupSkill
- worked-problem-generatorSkill
- my-new-skillSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Every High action-priority row needs an action, an owner, and a due date.
- Distinctive: line 23
Assemble the document: Use the Docs artifact type, or docx/pdf if the user asks for a file.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
Design Review Package
Workflow
- Scope. Find out the review type (concept / PDR / CDR / production-readiness), the audience, and what already exists. Use what the user has. Generate only the missing pieces, and mark anything generated as a draft for the team to validate.
- Requirements matrix. Columns: ID | Requirement (shall-statement, measurable) | Source | Verification method (Analysis / Inspection / Demonstration / Test) | Evidence | Status. Rewrite vague requirements into measurable ones and show the original next to the rewrite.
- DFMEA. Build
fmea.csv(seescripts/example_fmea.csv). Rate severity, occurrence, and detection on the AIAG-VDA 1–10 scales inreferences/fmea_scales.md. Then rank:
Every High action-priority row needs an action, an owner, and a due date.python scripts/review_tables.py fmea fmea.csv --rpn-threshold 100 --out fmea_ranked - BOM roll-up:
Report unit cost, the parts that make up 80% of cost, and the longest-lead item (the critical path).python scripts/review_tables.py bom bom.csv --qty 500 --out bom_rollup - Risk register. Top 5–10 technical, schedule, and supply risks: likelihood × consequence (5×5), mitigation, owner, and the trigger that would escalate each one.
- Checklist. Score the design against
references/review_checklist.mdfor the review type. Mark each item Ready / Gap / N/A, with evidence. - Assemble the document. Use the Docs artifact type, or docx/pdf if the user asks for a file. Order: summary and decision requested → requirements → analysis evidence (link calc reports) → DFMEA → BOM → risks → checklist → action items. Keep numbers consistent: one source CSV feeds every table.
Quality bar
Each requirement traces to verification evidence or to an open action. Each High-severity failure mode traces to a design control. The summary states the decision the board is being asked to make.
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.

