agentleFS
Sign inStart free
kwana117kwana117/claude-skills/decisions/SKILL.md

decisions

Skill0 starsChanged 5 months agoMITView on GitHub

Generate an interactive decisions page (HTML + JS) where each decision presents a Recommendation vs Alternative as clickable options, plus a free-text "Other choice". The page tracks selections in localStorage, shows live progress (X/N decisions), and produces a copy-to-clipboard summary. Saves locally and opens in browser. Use when the user says /decisions, "make a decisions page", "interactive page to decide X", "I want to decide Y with clicks", or asks for a structured decision-making page they can fill in interactively and copy the result.

11 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use adr-verbatim, file-tree and 4 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • davidondrejSkill

    adr-verbatim

    Record concise ADRs that preserve the user''s decisions without conversational noise. Use for "adr-verbatim", "new ADR", "document that as an ADR", "record this decision", or supplied ADR wording.

    Also in 3 projects that use this

  • davidondrejSkill

    file-tree

    Manually-invoked skill that prints a nice file tree of the current topic in a code block. Use when the user says "file-tree" or "file tree".

    Also in 3 projects that use this

  • attentiondotnetSkill

    setup-help

    Walk the user through setting up anything step by step. Use when the user asks for help setting up, configuring, installing, or getting something working — "help me set up X", "walk me through this", "setup-help". Differentiator: gives one current step at a time, then always lists every remaining setup step after each response.

    Also in 3 projects that use this

  • itgoyoSkill

    browser-harness

    Direct browser control via CDP. Use when the user wants to automate, scrape, test, or interact with web pages. Connects to the user's already-running Chrome.

    Also in 3 projects that use this

  • +2 more from davidondrej

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 2

    Distinctive

    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
  1. Distinctive:

    Use AskUserQuestion only if the decisions array is missing critical info.

    line 44
  2. Distinctive:

    If the topic has natural phases (some decisions block others), include an "Order of resolution" section at the top with 3 phase cards.

    line 46

“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “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

Decisions — Interactive decision page generator

Generates a single-file HTML page with a list of decisions (each with Recommendation / Alternative / Other choice clickable options), a sticky progress bar, and a copy-to-clipboard summary panel. Saves to /tmp/decisions/<slug>/index.html and opens in the browser.

The pattern

A structured decision page where each card has:

  • A clear Recommendation with supporting bullet points
  • A serious Alternative (or multiple alternatives) with bullet points
  • A Tradeoff — what you lose by picking the recommendation
  • A free-text "Other choice" textarea (auto-injected by JS)

The page generates a copyable summary of all selections when the user is done.

Visual palette

  • Background: parchment #F5F1EB
  • Accent: burnt orange #CC785C
  • Fonts: Inter (body), JetBrains Mono (code/labels)
  • Status chips: rose (decide first), amber (important), green (validated), muted (can wait)

Step 1 — Gather inputs

Required:

  • Topic — what is being decided (e.g. "project stack", "MVP scope", "legal structure"). Infer from conversation if possible.
  • Decisions — array of decision items. Each has:
    • num — short ID (e.g. "#1", "#2"…)
    • title — what the decision is about
    • phase — optional grouping (Phase A · Now / Phase B · 2 weeks / Phase C · Post-validation) — only use if there's a real dependency order
    • status_chip — one of: rose (decide first), amber (important), green (validated), muted (can wait)
    • recommendation — { title, bullets[] } — what you recommend
    • alternative — { title, bullets[] } — the serious alternative (or alternatives plural with multiple labelled bullets if 3+)
    • tradeoff — short paragraph: what you lose by picking the recommendation
  • Slug — kebab-case identifier for the output folder. Derive from topic if not given (e.g. stack-decisions, mvp-scope-decisions).
  • Recipient (optional) — shapes hero copy.

Use AskUserQuestion only if the decisions array is missing critical info. Prefer extracting from conversation context.

If the topic has natural phases (some decisions block others), include an "Order of resolution" section at the top with 3 phase cards. If not, skip it.

Step 2 — Generate HTML

Generate the full single-file HTML from scratch. Required structure:

<!DOCTYPE html>
<html lang="en">
<head>
  <meta charset="UTF-8">
  <meta name="viewport" content="width=device-width, initial-scale=1.0">
  <meta name="robots" content="noindex, nofollow">
  <title>[Topic] — Decisions</title>
  <!-- Inline all CSS — no external deps except Google Fonts -->
  <style>
    /* parchment palette + Inter + JetBrains Mono */
    :root {
      --bg: #F5F1EB; --surface: #FDFAF6; --accent: #CC785C;
      --green: #4A7C59; --amber: #B8860B; --rose: #B85C5C; --muted: #888;
      --text: #1A1A1A; --text-2: #555;
    }
    /* ... full styles ... */
  </style>
</head>
<body>
  <!-- nav: logo + tag -->
  <!-- hero: eyebrow, h1 with <span class="accent-highlight"> on key word, lead, anchor links -->
  <!-- optional #order section: 3 phase cards (classes a/b/c for rose/amber/green strip) -->

  <!-- #decisions section: one .detail-card per decision -->
  <!--
    Required card structure:
    <div class="detail-card">
      <div class="detail-head">
        <span class="detail-num">#N · PHASE X</span>     <!-- JS reads .detail-num for id -->
        <span class="status-chip status-rose">label</span>
        <span class="detail-title">Decision title</span>  <!-- JS reads .detail-title -->
      </div>
      <div class="detail-body">
        <div class="detail-grid">
          <div>
            <div class="subhead green">Recommendation</div>  <!-- JS detects this label -->
            <div style="font-weight:700">Option title</div>
            <ul class="bullets green">...</ul>
          </div>
          <div>
            <div class="subhead amber">Alternative</div>     <!-- or "Alternatives" -->
            <div>Option title</div>
            <ul class="bullets amber">...</ul>
          </div>
        </div>
        <div class="tradeoff-box">
          <strong>Tradeoff</strong>
          Short paragraph...
        </div>
        <!-- JS auto-injects "✎ Other choice" textarea — do NOT add manually -->
      </div>
    </div>
  -->

  <!-- #summary section -->
  <div id="summaryPanel">...</div>
  <div class="summary-actions">
    <button id="copyBtn">Copy summary</button>
    <button id="resetBtn">Reset</button>
  </div>

  <!-- sticky .decide-bar at bottom with progress + barCopyBtn -->

  <script>
    const STORAGE_KEY = '<slug>-decisions-v1'; // unique per page — prevents localStorage collision
    // ... JS engine ...
    // buildSummary() — update the order array to match your decision IDs:
    // const order = ['1','2','3',...] // IDs in the order you want them in the summary output
    // Update the summary header lines to match your topic
  </script>
</body>
</html>

JS engine requirements:

  • Option detection: reads .subhead text, matches /recommend/i and /alternat/i for auto-highlighting
  • Clicking an option toggles .selected on that column, persists to localStorage
  • buildSummary() iterates cards in order array, outputs selected option + any "other choice" text
  • copyBtn / barCopyBtn copy summary to clipboard
  • resetBtn clears localStorage and reloads
  • IDs that must exist: summaryPanel, doneCount, copyBtn, barCopyBtn, resetBtn

Save to /tmp/decisions/<slug>/index.html.

Step 3 — Open locally

mkdir -p /tmp/decisions/<slug>
# (file already written by Write tool)
open /tmp/decisions/<slug>/index.html

Step 4 — Report to user

Reply with:

  1. The local path (/tmp/decisions/<slug>/index.html)
  2. How many decisions are on the page
  3. One-line update command for future edits: re-run the skill or edit the file directly

Keep under 6 lines.

Rules

  • Never skip noindex — these are private decision pages.
  • Don't invent new CSS tokens — reuse the parchment palette variables.
  • Keep the JS engine intact — option-detection logic depends on .subhead text matching /recommend/i and /alternat/i.
  • STORAGE_KEY must be unique per page or pages will share decisions across tabs.
  • Tradeoff is mandatory for each decision — if you can't articulate a tradeoff, the decision isn't worth a card.
  • "Other choice" is auto-injected by JS — don't add it in HTML.

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.

Check your setup, free