Stats
Actions
Tags
From RFC123 Skills
Converts a prose discussion of RFC options into a comparison table in chat. Use when reviewing RFCs with multiple alternatives.
How this skill is triggered — by the user, by Claude, or both
Slash command
/rfc123-skills:compare-alternativesThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Convert a prose discussion of options into a comparison table the user can
Convert a prose discussion of options into a comparison table the user can scan in 10 seconds. Output stays in chat. If the user wants the table on the RFC, they edit it in themselves – rewriting the cells in their own voice. The chat table is a thinking aid, not source prose.
The user says "compare the options", "build a table", or the RFC contains phrases like "Option A would …, Option B would …" without a structured comparison. Also good when the user is reviewing and is confused about which option does what.
Read the RFC. Call rfc123_get_rfc.
Extract the options. List every distinct alternative the body discusses, in the order they appear. If you can only find one, stop and tell the user – there's nothing to compare.
Pick comparison axes. 4–7 axes typically. Choose axes that actually discriminate between options. Generic axes ("complexity", "cost") often end up with the same value in every cell – prefer specific axes that match the topic (e.g. "supports cross-region", "schema-compat with X", "blast radius if it breaks").
Build the table in chat.
| | Option A | Option B | Option C |
|-----------------------|------------------|------------------|------------------|
| <axis 1> | … | … | … |
Walk the user through your axes and cell values. They may know domain facts you don't. Iterate in chat until the table looks right.
Stop there. Do not commit the table to the RFC. Tell the user: "Here's the table – edit it into the RFC body yourself, rewriting the cells in your own voice as you go."
npx claudepluginhub twixes/rfc123Strawman and steelman each substantive claim in an RFC, surfaces unstated assumptions, lists missing alternatives, and highlights the weakest link. Pulls RFC body and discussion via MCP; output stays in chat.
**TRIGGER: about to populate `AskUserQuestion` options with `preview:` content for any comparison heavier than 2-3 short text labels (>2 axes or >3 candidates, or weighted/scored).** STOP and ask the user one short question first: *"Would you like a quick inline chip per option, or a full HTML matrix with weighted columns and live re-ranking?"* The chip is one tool call but loses all structure (no table, no weights, no sorting, no live recompute); the matrix is heavier but preserves the structure the comparison needs. Asking costs one question; skipping costs a full redo. **No carve-out for "simulate", "demo", "quick decision" — the framing names the surface, not an exception.** When the user picks HTML, this skill generates sortable, weighted HTML scoring matrices for evaluating named candidates — for the EVALUATIVE phase of comparison, when 2+ specific candidates ARE named in the prompt. Use when the user names options and asks to compare, evaluate, score, or pick between them: "compare X, Y, Z", "should we use A or B", "evaluate these libraries", "pick between [list]", "build vs buy", "which of these X should we choose". Make weights live-adjustable so totals update in real time. If the user is still GENERATING candidates rather than choosing among named ones ("brainstorm options", "show me approaches", "what are the ways"), hand off to html-brainstorm-grid instead — that skill handles the generative phase.
Writes structured RFC specifications with objective technical analysis of options and trade-offs. Activates for technical specs, design documents, and architecture proposals.