Add rfspec plugin: multi-model spec generation

.factory-plugin/marketplace.json

@@ -23,6 +23,12 @@
       "description": "Core Skills for essential functionalities and integrations",
       "source": "./plugins/core",
       "category": "core"
+    },
+    {
+      "name": "rfspec",
+      "description": "Request for Spec: fan out a prompt to multiple AI models in parallel and pick or synthesize the best implementation spec",
+      "source": "./plugins/rfspec",
+      "category": "productivity"
     }
   ]
 }

README.md

@@ -48,6 +48,14 @@ Skills for continuous learning and improvement.
 - `frontend-design` - Build web apps, websites, HTML pages with good design
 - `browser-navigation` - Browser automation with agent-browser
 
+### rfspec
+
+Fan out a prompt to multiple AI models in parallel and pick or synthesize the best result.
+
+**Skills:**
+
+- `rfspec` - Multi-model spec generation and synthesis workflow
+
 ## Plugin Structure
 
 Each plugin follows the Factory plugin format:

plugins/rfspec/.factory-plugin/plugin.json

@@ -0,0 +1,9 @@
+{
+  "name": "rfspec",
+  "description": "Request for Spec: fan out a prompt to multiple AI models in parallel and pick or synthesize the best implementation spec",
+  "version": "1.0.0",
+  "author": {
+    "name": "Andy Taylor",
+    "email": "andrew.taylor@factory.ai"
+  }
+}

plugins/rfspec/README.md

@@ -0,0 +1,32 @@
+# rfspec
+
+Request for Spec -- fan out a prompt to multiple AI models in parallel and choose or synthesize the best result.
+
+## What it does
+
+`/rfspec` sends your prompt to three models simultaneously (Claude Opus 4.6, GPT-5.4, Gemini 3.1 Pro), each at its maximum reasoning tier. The results are presented side-by-side so you can pick the strongest one or synthesize a combination. No prescriptive system prompt is injected -- the models bring their own reasoning to your request.
+
+## Usage
+
+```
+/rfspec <describe what you want to build>
+```
+
+Example:
+
+```
+/rfspec add a dark mode toggle to the settings page with persistent user preference
+```
+
+The command will:
+
+1. Send the prompt to all three models in parallel via `droid exec`, each at its maximum reasoning tier (Opus: max, GPT-5.4: xhigh, Gemini: high)
+2. Collect and display each model's response (Options A, B, C)
+3. Ask you to pick one as-is or synthesize the best parts
+4. Save the chosen result to `specs/active/YYYY-MM-DD-<slug>.md`
+
+## Requirements
+
+- **droid CLI** -- must be installed and authenticated
+- **jq** -- for JSON parsing (`brew install jq` on macOS)
+- Access to at least one of the three models. Models that fail are skipped gracefully; the command only errors if all three fail.

plugins/rfspec/commands/rfspec

@@ -0,0 +1,2 @@
+#!/usr/bin/env bash
+exec "$(dirname "$0")/../skills/rfspec/scripts/run.sh" "$@"

plugins/rfspec/skills/rfspec/SKILL.md

@@ -0,0 +1,93 @@
+---
+name: rfspec
+version: 1.2.0
+description: |
+  Multi-model spec generation and synthesis. Use when the user wants to:
+  - Get competing proposals from different AI models
+  - Compare approaches to a problem from different perspectives
+  - Synthesize the best parts of several proposals into one spec
+  Keywords: rfspec, competing specs, multi-model, compare approaches,
+  multiple perspectives, request for spec, fan out, model comparison.
+  NOT for: single-model generation, code review, or running tests.
+---
+
+# rfspec -- Request for Spec
+
+Fan out a prompt to multiple models, compare their responses, and help the user pick or synthesize the best result.
+
+## Quick Reference
+
+| Task | Action |
+|------|--------|
+| Generate competing specs | `/rfspec <prompt>` |
+| Pick one result | Select via AskUser after comparison |
+| Synthesize results | Combine strongest elements when user chooses synthesis |
+| Save final spec | Write to `specs/active/YYYY-MM-DD-<slug>.md` |
+
+## Workflow
+
+1. Run `/rfspec <user's prompt>` -- fires parallel model calls, returns labeled options (A, B, C).
+2. Evaluate the results -- see [references/evaluation-guide.md](references/evaluation-guide.md).
+3. Present the choice to the user via AskUser.
+4. Present the selected or synthesized spec via ExitSpecMode for user review.
+5. Save to `specs/active/` only after the user approves in spec mode.
+
+## Saving
+
+**Do not save immediately.** After the user picks or synthesis is complete, present the
+final spec via ExitSpecMode for review. Only after approval, save to:
+
+```
+specs/active/YYYY-MM-DD-<slug>.md
+```
+
+Where `<slug>` is a short kebab-case name derived from the topic.
+
+## Pitfalls
+
+- Don't summarize each option individually -- compare them against each other.
+- Don't concatenate when synthesizing -- resolve contradictions and produce a coherent document.
+- If all options are rejected, gather feedback and re-run with a refined prompt.
+
+## Verification
+
+After saving a spec:
+
+1. Confirm the file exists at the expected path.
+2. Verify it contains the selected or synthesized content.
+3. Report the saved path to the user.
+
+## Examples
+
+Example 1: User wants competing specs
+User says: "Get me specs from multiple models for adding a dark mode toggle"
+Actions:
+
+1. Run `/rfspec add a dark mode toggle to the settings page with persistent user preference`
+2. Read Options A, B, C
+3. Compare: "Option A uses CSS variables with a React context, Option B uses Tailwind's dark class with localStorage, Option C uses a theme provider with system preference detection."
+4. Present choice via AskUser
+Result: User picks Option B, saved to `specs/active/2026-03-06-dark-mode-toggle.md`
+
+Example 2: User wants synthesis
+User says: "rfspec this: refactor the auth module to use JWT"
+Actions:
+
+1. Run `/rfspec refactor the auth module to use JWT`
+2. Compare results, noting Option A has better token rotation but Option C has cleaner middleware
+3. User selects "Synthesize"
+4. Combine Option A's rotation logic with Option C's middleware structure
+Result: Synthesized spec saved to `specs/active/2026-03-06-auth-jwt-refactor.md`
+
+Example 3: All options rejected
+User says: "None of these work, they all miss the caching layer"
+Actions:
+
+1. Ask what's missing -- user explains the Redis caching requirement
+2. Offer to re-run: `/rfspec refactor auth module to use JWT with Redis session caching`
+Result: New round of specs generated with caching addressed
+
+## References
+
+- [references/evaluation-guide.md](references/evaluation-guide.md) -- how to compare, synthesize, and handle rejection
+- [references/troubleshooting.md](references/troubleshooting.md) -- error codes and fixes

plugins/rfspec/skills/rfspec/references/evaluation-guide.md

@@ -0,0 +1,38 @@
+# Evaluation Guide
+
+How to compare and evaluate competing model responses.
+
+## Comparing Options
+
+When results come back from `/rfspec`:
+
+1. **Read all options** before responding. Understand each approach fully.
+2. **Identify meaningful differences** -- not cosmetic ones. Focus on:
+   - Architectural choices (patterns, libraries, data flow)
+   - Scope differences (what each included or excluded)
+   - Risk areas (where one flagged something the others missed)
+   - Concrete vs. vague (which named actual files, functions, steps)
+3. **Write a brief comparison** -- 2-4 sentences per option covering strengths and gaps. Compare, don't summarize.
+4. **Present the choice** using AskUser:
+   - Use Option A as-is
+   - Use Option B as-is
+   - Use Option C as-is
+   - Synthesize a refined version combining the best of all three
+   - None of these work
+
+## Synthesizing
+
+If the user picks synthesis:
+
+1. Start from the strongest option as the base.
+2. Pull in specific elements from the others -- name what you're taking and why.
+3. Resolve contradictions (don't concatenate).
+4. The final result should read as a single coherent document, not a patchwork.
+
+## Handling Rejection
+
+If the user rejects all options:
+
+1. Ask what's missing or wrong.
+2. Incorporate their feedback into a refined prompt.
+3. Offer to re-run `/rfspec` with the updated prompt.

plugins/rfspec/skills/rfspec/references/troubleshooting.md

@@ -0,0 +1,37 @@
+# Troubleshooting
+
+## All three models failed
+
+```
+Error: All three models failed. Check that your droid CLI is authenticated...
+```
+
+**Cause:** droid CLI not authenticated or models unavailable.
+**Solution:** Run `droid` interactively to verify auth, then retry.
+
+## jq not installed
+
+```
+Error: jq is required but not installed.
+```
+
+**Cause:** jq not on PATH.
+**Solution:** `brew install jq` (macOS) or `apt-get install jq` (Linux).
+
+## One or two models failed
+
+```
+Note: The following models encountered errors: Opus 4.6
+```
+
+**Cause:** Specific model unavailable or rate-limited.
+**Solution:** This is handled gracefully -- compare the options that did return. No action needed unless the failed model was critical.
+
+## Command not found
+
+```
+/rfspec: command not found
+```
+
+**Cause:** Plugin not installed.
+**Solution:** Install via `/plugins` UI or `droid plugin install rfspec@factory-plugins --scope user`.

plugins/rfspec/skills/rfspec/scripts/run.sh

@@ -0,0 +1,93 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# ── guard: dependencies ──────────────────────────────────────────────
+command -v jq  >/dev/null 2>&1 || { echo "Error: jq is required but not installed. Install it with: brew install jq"; exit 1; }
+command -v droid >/dev/null 2>&1 || { echo "Error: droid CLI is required but not found on PATH."; exit 1; }
+
+PROMPT="$*"
+
+if [ -z "$PROMPT" ]; then
+  echo "Usage: /rfspec <your prompt>"
+  echo ""
+  echo "Sends your prompt to three models in parallel (Opus, GPT, Gemini),"
+  echo "then lets you pick the best spec or synthesize a combination."
+  exit 1
+fi
+
+# ── prompt ────────────────────────────────────────────────────────────
+TMPDIR=$(mktemp -d)
+trap 'rm -rf "$TMPDIR"' EXIT
+
+echo "$PROMPT" > "$TMPDIR/prompt.md"
+
+# ── models (id, label, max reasoning) ────────────────────────────────
+MODEL_A="claude-opus-4-6";  LABEL_A="Opus 4.6";       RE_A="max"
+MODEL_B="gpt-5.4";          LABEL_B="GPT-5.4";        RE_B="xhigh"
+MODEL_C="gemini-3.1-pro-preview"; LABEL_C="Gemini 3.1 Pro"; RE_C="high"
+
+# ── fire all three in parallel ───────────────────────────────────────
+droid exec -m "$MODEL_A" -r "$RE_A" --auto medium -f "$TMPDIR/prompt.md" -o json 2>/dev/null > "$TMPDIR/a.json" &
+PID_A=$!
+droid exec -m "$MODEL_B" -r "$RE_B" --auto medium -f "$TMPDIR/prompt.md" -o json 2>/dev/null > "$TMPDIR/b.json" &
+PID_B=$!
+droid exec -m "$MODEL_C" -r "$RE_C" --auto medium -f "$TMPDIR/prompt.md" -o json 2>/dev/null > "$TMPDIR/c.json" &
+PID_C=$!
+
+FAIL=""
+wait $PID_A 2>/dev/null || FAIL="${FAIL}${LABEL_A} "
+wait $PID_B 2>/dev/null || FAIL="${FAIL}${LABEL_B} "
+wait $PID_C 2>/dev/null || FAIL="${FAIL}${LABEL_C} "
+
+# ── extract results ──────────────────────────────────────────────────
+extract() {
+  local file="$1"
+  if [ -s "$file" ]; then
+    jq -r '.result // empty' "$file" 2>/dev/null || cat "$file"
+  fi
+}
+
+RESULT_A=$(extract "$TMPDIR/a.json")
+RESULT_B=$(extract "$TMPDIR/b.json")
+RESULT_C=$(extract "$TMPDIR/c.json")
+
+# ── present results ──────────────────────────────────────────────────
+echo "=== RFSPEC RESULTS ==="
+echo ""
+echo "User request: ${PROMPT}"
+echo ""
+
+[ -n "$RESULT_A" ] && printf '### Option A -- %s\n\n%s\n\n' "$LABEL_A" "$RESULT_A"
+[ -n "$RESULT_B" ] && printf '### Option B -- %s\n\n%s\n\n' "$LABEL_B" "$RESULT_B"
+[ -n "$RESULT_C" ] && printf '### Option C -- %s\n\n%s\n\n' "$LABEL_C" "$RESULT_C"
+
+if [ -n "$FAIL" ]; then
+  echo "Note: The following models encountered errors: ${FAIL}"
+  echo ""
+fi
+
+SUCCESS=0
+[ -n "$RESULT_A" ] && SUCCESS=$((SUCCESS + 1))
+[ -n "$RESULT_B" ] && SUCCESS=$((SUCCESS + 1))
+[ -n "$RESULT_C" ] && SUCCESS=$((SUCCESS + 1))
+
+if [ "$SUCCESS" -eq 0 ]; then
+  echo "Error: All three models failed. Check that your droid CLI is authenticated"
+  echo "and the models (${MODEL_A}, ${MODEL_B}, ${MODEL_C}) are available."
+  exit 1
+fi
+
+echo "=== AGENT INSTRUCTIONS ==="
+echo "Analyze the specs above. Provide a brief comparison of each model's"
+echo "strengths and weaknesses. Then use the AskUser tool to offer:"
+echo "- Use Option A (${LABEL_A}) as-is"
+echo "- Use Option B (${LABEL_B}) as-is"
+echo "- Use Option C (${LABEL_C}) as-is"
+echo "- Synthesize a refined spec combining the best of all three"
+echo "- No -- none of these work (explain why)"
+echo ""
+echo "CRITICAL: Do NOT save the spec directly. After the user picks an option"
+echo "or requests synthesis, use the ExitSpecMode tool to present the final"
+echo "spec content for review. Only save to specs/active/YYYY-MM-DD-<slug>.md"
+echo "AFTER the user approves the spec in spec mode. If rejected, gather"
+echo "feedback and revise."