agentleFS
adeerkhanadeerkhan/vitruvius/skills/design-alternatives/SKILL.md

design-alternatives

Skill10 starsChanged 5 days agoMITView on GitHub

Generate and compare engineering design alternatives for a given problem. Use when the user asks "what are my options", "compare approaches", "which solution is better", or needs structured trade-off analysis of 3+ engineering approaches — e.g. a pressure-vessel closure, a gearbox layout, a manufacturing process. Produces a comparison matrix with scored criteria. Do NOT use for single-solution design requests or routine calculations.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before searching, name the question, the artifact/scope (or say it is a literature review), the jurisdiction/edition, and the effort budget …

    line 27
  2. Very specific:

    Write outputs/design-alternatives/<slug>.provenance.md beside the analysis (sources consulted, accepted, and rejected.

    line 72
  3. Distinctive:

    All alternatives must have a basis in engineering practice — no speculative or unproven approaches.

    line 78

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- VITRUVIUS-COMPILED-SKILL:BEGIN v1 sha256=2e46c8c4601f96e95aac4ed3f5b135e6adfb6e569c050c9165b4590af911a985 -->

Design Alternatives

Generate structured engineering design alternatives and compare them against the problem constraints. This skill is for exploration and comparison, not final design.

Input Gate

Before searching, name the question, the artifact/scope (or say it is a literature review), the jurisdiction/edition, and the effort budget (user-set or thorough). Ask ONE clarifying question if the ask is too vague, then proceed. See references/input-gate.md.

Workflow

flowchart LR
    Input["Problem + Constraints"] --> Generate["Generate 3+ Alternatives"]
    Generate --> Criteria["Define Criteria"]
    Criteria --> Score["Score Each Alternative"]
    Score --> Matrix["Comparison Matrix"]
    Matrix --> Recommend["Ranked Recommendation"]

Invocation

/design-alternatives <problem statement>

Include constraints: performance targets, budget limits, spatial constraints, code requirements, environmental conditions, timeline.

Methodology

  1. Parse constraints — hard (must meet), soft (preferences), evaluation criteria. Ask if unclear.
  2. Generate 3-5 alternatives — technically feasible, distinct approaches. Each: Approach, Governing standards, Advantages, Limitations.
  3. Comparison matrix — score 1-5 on Performance, Cost, Feasibility, Durability, Risk, Code compliance. Weight by priorities.
  4. Recommend — best overall + best for specific priorities + trade-offs. Do NOT recommend a single answer.

Output

Inline Summary (chat response)

  • Problem restatement with constraints
  • 3-5 alternatives with one-line descriptions
  • Comparison matrix (scored)
  • Recommendation with trade-offs

Full Analysis (saved to disk)

Save to outputs/design-alternatives/<slug>.md: Problem Statement, Constraints, Alternatives (Approach/Governing standards/Advantages/Limitations each), Comparison Matrix (criteria × alternatives, scored 1-5 with weights), Recommendation (best overall + trade-offs).

Write outputs/design-alternatives/<slug>.provenance.md beside the analysis (sources consulted, accepted, and rejected; verification status). Minimal shape: references/provenance-sidecar.md.

Scope and Boundaries

  • This skill compares alternatives — it does NOT produce final designs.
  • Output is research and analysis, not construction documents.
  • All alternatives must have a basis in engineering practice — no speculative or unproven approaches.
  • Evidence quality: see references/evidence-quality-tiers.md.
  • Research-only, not for final engineering sign-off.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.