Skip to content
Agentmart
Submit a tool

option-generation

Generate at least two distinct implementation options for an engineering problem, each with a "trades away X to get Y" sentence, without picking one.

Skill by paulthorson

IndexedApache-2.0★ 4
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/paulthorson-option-generation

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Generate at least two distinct implementation options for an engineering problem, each with a "trades away X to get Y" sentence, without picking one.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/option-generation

What's inside

Skill name
option-generation
Description
Generate at least two distinct implementation options for an engineering problem, each with a "trades away X to get Y" sentence, without picking one.
License
Apache-2.0
Instructions
31 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Option Generation

Produce a set of genuine options. Input in, artifact out. No pick.

## Rules

- Options must differ in **what they optimize** (Rule 2): speed vs correctness, simplicity vs
  capacity, low latency vs low cost, small surface vs features.
- Each option carries a trade-off sentence: "This option trades away X to get Y."
- If two options have the same X and the same Y, they are one option. Say so.
- Three layouts of one idea are not three options.

## Output

```
## OPTIONS

| Option | What it optimizes | Trades away | To get | Rough cost | Risk |
|---|---|---|---|---|---|
| A | <dimension> | <X> | <Y> | <est> | <high/med/low> |
| B | <dimension> | <X> | <Y> | <est> | <high/med/low> |
| C (if any) | <dimension> | <X> | <Y> | <est> | <high/med/low> |

### Why these differ (not variations)
- <for each pair, the differing optimization>

### Constraint tension (Rule 3)
- <which option is fastest/cheapest, and what it gives up — flagged for the human gate>
```

From paulthorson/agentic-governance, Apache-2.0.

More from paulthorson/agentic-governance

Signals

Stars
4
Forks
2
Open issues
0
Last commit (this folder)
Sep 29, 2026 (1 month ago)
Last release
Oct 15, 2026 (14 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from paulthorson

Cite this page

option-generation skill. Agent Mart. https://agentmart.dev/skills/paulthorson-option-generation (last updated 2026-10-24)