crewly 1.5.11 → 1.5.13

package/config/skills/agent/core/pipe-to-sink/execute.sh

@@ -0,0 +1,41 @@
+#!/usr/bin/env bash
+# pipe-to-sink: Route structured data to a registered sink via the Data API.
+#
+# Input (JSON):
+#   {
+#     "sinkId": "steve-inputs",
+#     "data": { "title": "...", "source": "slack", ... },
+#     "projectPath": "/path/to/project"    (optional — falls back to CREWLY_PROJECT_PATH)
+#   }
+#
+# Calls: POST /api/v2/data/sinks/:sinkId
+# Returns: JSON with the created DataObject ID on success, or error details.
+set -euo pipefail
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+source "${SCRIPT_DIR}/../../_common/lib.sh"
+
+INPUT=$(read_json_input "${1:-}")
+[ -z "$INPUT" ] && error_exit "Usage: execute.sh '{\"sinkId\":\"...\",\"data\":{...}}' or echo '{...}' | execute.sh"
+
+SINK_ID=$(printf '%s' "$INPUT" | jq -r '.sinkId // empty')
+require_param "sinkId" "$SINK_ID"
+
+DATA=$(printf '%s' "$INPUT" | jq '.data // empty')
+if [ "$DATA" = "null" ] || [ "$DATA" = "" ] || [ "$DATA" = "empty" ]; then
+  error_exit "Missing required parameter: data"
+fi
+
+# Resolve projectPath: explicit > env var > omit
+PROJECT_PATH=$(printf '%s' "$INPUT" | jq -r '.projectPath // empty')
+if [ -z "$PROJECT_PATH" ] && [ -n "${CREWLY_PROJECT_PATH:-}" ]; then
+  PROJECT_PATH="$CREWLY_PROJECT_PATH"
+fi
+
+# Build request body
+BODY=$(jq -n \
+  --argjson data "$DATA" \
+  --arg projectPath "$PROJECT_PATH" \
+  '{data: $data} + (if $projectPath != "" then {projectPath: $projectPath} else {} end)')
+
+# POST to the data API
+api_call POST "/v2/data/sinks/${SINK_ID}" "$BODY"

package/config/skills/agent/core/read-task/execute.sh

@@ -10,6 +10,8 @@ INPUT=$(read_json_input "${1:-}")
 ABSOLUTE_TASK_PATH=$(printf '%s' "$INPUT" | jq -r '.absoluteTaskPath // empty')
 require_param "absoluteTaskPath" "$ABSOLUTE_TASK_PATH"
 
-BODY=$(jq -n --arg absoluteTaskPath "$ABSOLUTE_TASK_PATH" '{absoluteTaskPath: $absoluteTaskPath}')
+BODY=$(jq -n --arg absoluteTaskPath "$ABSOLUTE_TASK_PATH" \
+  --arg taskPath "$ABSOLUTE_TASK_PATH" \
+  '{absoluteTaskPath: $absoluteTaskPath, taskPath: $taskPath}')
 
 api_call POST "/task-management/read-task" "$BODY"

package/config/skills/agent/core/report-progress/execute.sh

@@ -5,7 +5,7 @@ SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 source "${SCRIPT_DIR}/../../_common/lib.sh"
 
 INPUT=$(read_json_input "${1:-}")
-[ -z "$INPUT" ] && error_exit "Usage: execute.sh '{\"sessionName\":\"dev-1\",\"progress\":50,\"current\":\"Implementing tests\"}'"
+[ -z "$INPUT" ] && error_exit "Usage: execute.sh '{\"sessionName\":\"dev-1\",\"progress\":50,\"current\":\"Implementing tests\",\"taskGroup\":\"delegated\"}'"
 
 SESSION_NAME=$(printf '%s' "$INPUT" | jq -r '.sessionName // empty')
 PROGRESS=$(printf '%s' "$INPUT" | jq -r '.progress // empty')
@@ -20,6 +20,8 @@ BODY=$(printf '%s' "$INPUT" | jq '{
   progress: (.progress | tonumber),
   current: .current
 } +
+  (if .projectPath then {projectPath: .projectPath} else {} end) +
+  (if .taskGroup then {taskGroup: .taskGroup} else {} end) +
   (if .completed then {completed: .completed} else {} end) +
   (if .nextSteps then {nextSteps: .nextSteps} else {} end) +
   (if .blockers then {blockers: .blockers} else {} end) +

package/config/skills/agent/screenshot-compare/SKILL.md

@@ -0,0 +1,75 @@
+---
+name: screenshot-compare
+description: Compare two screenshots (e.g., iOS reference vs Web implementation) using Gemini Vision API. Returns a structured diff report with categorized issues, severity levels, and CSS fix suggestions. Use when verifying UI parity, checking design implementation accuracy, or auditing visual consistency across platforms.
+category: qa
+assignableRoles:
+  - "*"
+version: "1.0.0"
+tags:
+  - screenshot
+  - visual-qa
+  - comparison
+  - gemini
+  - parity
+---
+
+# Screenshot Compare
+
+Compare two UI screenshots using Gemini Vision API and get a structured diff report.
+
+## Actions
+
+| Parameter | Required | Description |
+|-----------|----------|-------------|
+| `reference` | Yes | Path to the reference screenshot (source of truth, e.g., iOS app) |
+| `target` | Yes | Path to the target screenshot (implementation to verify, e.g., web app) |
+| `focus` | No | Comma-separated focus areas: `icons,layout,colors,text,images,spacing` (default: all) |
+| `context` | No | Additional context (e.g., "This is the settings page", "Dark mode") |
+
+## Usage
+
+```bash
+# Basic comparison
+bash execute.sh '{"reference":"/path/to/ios-screenshot.png","target":"/path/to/web-screenshot.png"}'
+
+# Focused comparison (only icons and colors)
+bash execute.sh '{"reference":"ref.png","target":"web.png","focus":"icons,colors"}'
+
+# With context
+bash execute.sh '{"reference":"ios-home.png","target":"web-home.png","context":"Home screen, light mode"}'
+```
+
+## Output Format
+
+Returns JSON with:
+- `matchScore` — 0-100 overall similarity score
+- `totalIssues` — count of differences found
+- `issues[]` — array of categorized differences:
+  - `type` — icon_missing, layout_shift, color_mismatch, text_mismatch, font_mismatch, spacing, etc.
+  - `severity` — critical, major, minor
+  - `element` — which UI element is affected
+  - `suggestion` — specific CSS/code fix
+
+## Issue Types
+
+| Type | Description |
+|------|-------------|
+| `icon_missing` | Icon present in reference but missing in target |
+| `icon_wrong` | Icon exists but is the wrong icon |
+| `layout_shift` | Elements positioned differently |
+| `spacing` | Padding/margin differences |
+| `color_mismatch` | Colors don't match between reference and target |
+| `text_mismatch` | Text content differs |
+| `font_mismatch` | Font family, size, or weight differs |
+| `image_missing` | Image present in reference but missing/broken in target |
+| `image_wrong` | Image exists but is different |
+| `border_radius` | Rounded corners differ |
+| `shadow` | Box shadow differences |
+| `alignment` | Vertical/horizontal alignment issues |
+| `responsive` | Layout doesn't adapt correctly |
+
+## Prerequisites
+
+- `GEMINI_API_KEY` environment variable or configured in Settings > API Keys
+- Both image files must exist and be PNG, JPG, GIF, or WebP
+- Images should be under 4MB each

package/config/skills/agent/screenshot-compare/execute.sh

@@ -0,0 +1,182 @@
+#!/bin/bash
+# Screenshot Compare — Gemini Vision API dual-image comparison
+#
+# Sends two screenshots (e.g., iOS reference + Web implementation) to
+# Gemini Vision and returns a structured diff report.
+#
+# Usage:
+#   bash execute.sh '{"reference":"/path/to/ios-screenshot.png","target":"/path/to/web-screenshot.png"}'
+#   bash execute.sh '{"reference":"ref.png","target":"web.png","focus":"icons,layout,colors"}'
+#
+# Requires: GEMINI_API_KEY environment variable
+#
+# Output: JSON with differences categorized by type (icon, layout, color, text, image)
+
+set -euo pipefail
+
+# ── Configuration ──────────────────────────────────────────────────────────────
+MODEL="${GEMINI_MODEL:-gemini-2.5-flash-preview-05-20}"
+GEMINI_API_BASE="https://generativelanguage.googleapis.com"
+GEMINI_CONTENT_URL="${GEMINI_API_BASE}/v1beta/models/${MODEL}:generateContent"
+MAX_IMAGE_SIZE_MB=4
+
+# ── Input parsing ──────────────────────────────────────────────────────────────
+INPUT="${1:-}"
+if [ -z "$INPUT" ]; then
+  echo '{"success":false,"error":"Usage: execute.sh \u0027{\"reference\":\"/path/to/ref.png\",\"target\":\"/path/to/target.png\"}\u0027"}'
+  exit 1
+fi
+
+REFERENCE=$(echo "$INPUT" | jq -r '.reference // empty')
+TARGET=$(echo "$INPUT" | jq -r '.target // empty')
+FOCUS=$(echo "$INPUT" | jq -r '.focus // "all"')
+CONTEXT=$(echo "$INPUT" | jq -r '.context // ""')
+
+if [ -z "$REFERENCE" ] || [ -z "$TARGET" ]; then
+  echo '{"success":false,"error":"Both reference and target image paths are required"}'
+  exit 1
+fi
+
+if [ ! -f "$REFERENCE" ]; then
+  echo "{\"success\":false,\"error\":\"Reference image not found: $REFERENCE\"}"
+  exit 1
+fi
+
+if [ ! -f "$TARGET" ]; then
+  echo "{\"success\":false,\"error\":\"Target image not found: $TARGET\"}"
+  exit 1
+fi
+
+# ── API key resolution ─────────────────────────────────────────────────────────
+if [ -z "${GEMINI_API_KEY:-}" ]; then
+  # Try loading from settings via Crewly API
+  GEMINI_API_KEY=$(curl -sf "http://localhost:8787/api/settings" 2>/dev/null | jq -r '.data.apiKeys.global.gemini // empty' 2>/dev/null || true)
+fi
+
+if [ -z "${GEMINI_API_KEY:-}" ]; then
+  echo '{"success":false,"error":"GEMINI_API_KEY not set. Set via environment or Settings > API Keys."}'
+  exit 1
+fi
+
+# ── Image encoding ─────────────────────────────────────────────────────────────
+get_mime_type() {
+  local file="$1"
+  local ext="${file##*.}"
+  case "$ext" in
+    png)  echo "image/png" ;;
+    jpg|jpeg) echo "image/jpeg" ;;
+    gif)  echo "image/gif" ;;
+    webp) echo "image/webp" ;;
+    *)    echo "image/png" ;;  # default
+  esac
+}
+
+REF_MIME=$(get_mime_type "$REFERENCE")
+TGT_MIME=$(get_mime_type "$TARGET")
+REF_B64=$(base64 < "$REFERENCE" | tr -d '\n')
+TGT_B64=$(base64 < "$TARGET" | tr -d '\n')
+
+# ── Build prompt ───────────────────────────────────────────────────────────────
+FOCUS_INSTRUCTION=""
+if [ "$FOCUS" != "all" ]; then
+  FOCUS_INSTRUCTION="Focus specifically on these areas: ${FOCUS}."
+fi
+
+CONTEXT_INSTRUCTION=""
+if [ -n "$CONTEXT" ]; then
+  CONTEXT_INSTRUCTION="Additional context: ${CONTEXT}"
+fi
+
+PROMPT="You are a pixel-perfect UI comparison expert. Compare these two screenshots:
+
+IMAGE 1 (Reference — the source of truth, e.g., iOS app or design mockup)
+IMAGE 2 (Target — the implementation to verify, e.g., web app)
+
+${FOCUS_INSTRUCTION}
+${CONTEXT_INSTRUCTION}
+
+Analyze every visible difference and return a JSON array of issues found. Each issue must have:
+- \"type\": one of \"icon_missing\", \"icon_wrong\", \"layout_shift\", \"spacing\", \"color_mismatch\", \"text_mismatch\", \"font_mismatch\", \"image_missing\", \"image_wrong\", \"border_radius\", \"shadow\", \"alignment\", \"responsive\", \"other\"
+- \"severity\": \"critical\" (functionality broken), \"major\" (clearly visible), \"minor\" (subtle)
+- \"element\": which UI element is affected (e.g., \"header logo\", \"submit button\", \"nav bar\")
+- \"reference\": what it looks like in Image 1
+- \"target\": what it looks like in Image 2
+- \"suggestion\": specific CSS/code fix suggestion
+
+Return ONLY valid JSON in this format:
+{
+  \"summary\": \"Brief overall assessment\",
+  \"matchScore\": 85,
+  \"totalIssues\": 5,
+  \"issues\": [
+    {
+      \"type\": \"...\",
+      \"severity\": \"...\",
+      \"element\": \"...\",
+      \"reference\": \"...\",
+      \"target\": \"...\",
+      \"suggestion\": \"...\"
+    }
+  ]
+}"
+
+# ── API call ───────────────────────────────────────────────────────────────────
+REQUEST_BODY=$(cat <<ENDJSON
+{
+  "contents": [{
+    "parts": [
+      {"text": $(echo "$PROMPT" | jq -Rs .)},
+      {
+        "inline_data": {
+          "mime_type": "${REF_MIME}",
+          "data": "${REF_B64}"
+        }
+      },
+      {
+        "inline_data": {
+          "mime_type": "${TGT_MIME}",
+          "data": "${TGT_B64}"
+        }
+      }
+    ]
+  }],
+  "generationConfig": {
+    "temperature": 0.1,
+    "maxOutputTokens": 4096,
+    "responseMimeType": "application/json"
+  }
+}
+ENDJSON
+)
+
+TMPFILE=$(mktemp /tmp/gemini-compare-XXXXXX.json)
+echo "$REQUEST_BODY" > "$TMPFILE"
+RESPONSE=$(curl -sf -X POST \
+  "${GEMINI_CONTENT_URL}?key=${GEMINI_API_KEY}" \
+  -H "Content-Type: application/json" \
+  -d "@${TMPFILE}" 2>&1)
+rm -f "$TMPFILE"
+
+HTTP_CODE=$?
+if [ $HTTP_CODE -ne 0 ]; then
+  echo "{\"success\":false,\"error\":\"Gemini API request failed (curl exit $HTTP_CODE)\"}"
+  exit 1
+fi
+
+# ── Parse response ─────────────────────────────────────────────────────────────
+ERROR_MSG=$(echo "$RESPONSE" | jq -r '.error.message // empty' 2>/dev/null)
+if [ -n "$ERROR_MSG" ]; then
+  echo "{\"success\":false,\"error\":\"Gemini API error: $ERROR_MSG\"}"
+  exit 1
+fi
+
+# Extract the text content from Gemini response
+RESULT_TEXT=$(echo "$RESPONSE" | jq -r '.candidates[0].content.parts[0].text // empty' 2>/dev/null)
+
+if [ -z "$RESULT_TEXT" ]; then
+  echo '{"success":false,"error":"Empty response from Gemini API"}'
+  exit 1
+fi
+
+# Output: wrap the Gemini JSON result in a success envelope
+echo "{\"success\":true,\"model\":\"${MODEL}\",\"reference\":\"${REFERENCE}\",\"target\":\"${TARGET}\",\"comparison\":${RESULT_TEXT}}"

package/config/skills/agent/screenshot-compare/skill.json

@@ -0,0 +1,10 @@
+{
+  "name": "screenshot-compare",
+  "displayName": "Screenshot Compare (Gemini Vision)",
+  "description": "Compare two UI screenshots using Gemini Vision API. Returns categorized diffs with severity and fix suggestions.",
+  "category": "qa",
+  "assignableRoles": ["*"],
+  "version": "1.0.0",
+  "author": "Crewly Team",
+  "requires": ["GEMINI_API_KEY"]
+}

package/config/skills/agent/xiaoyuzhoufm-transcript/SKILL.md

@@ -0,0 +1,85 @@
+---
+name: xiaoyuzhoufm-transcript
+description: Extract and transcribe 小宇宙 (Xiaoyuzhou FM) podcast episodes. Downloads audio from episode URL and uses Gemini Audio API for transcription with speaker identification and timestamps.
+category: content
+assignableRoles:
+  - "*"
+version: "1.0.0"
+tags:
+  - podcast
+  - transcript
+  - audio
+  - gemini
+  - xiaoyuzhou
+  - chinese
+---
+
+# 小宇宙 Podcast Transcript
+
+Extract and transcribe podcast episodes from 小宇宙 (Xiaoyuzhou FM) using Gemini Audio API.
+
+## Pipeline
+
+```
+Episode URL → Fetch HTML → Extract audio URL → Download m4a → Upload to Gemini → Transcribe → Output
+```
+
+## Usage
+
+```bash
+# Transcribe from URL
+bash execute.sh '{"url":"https://www.xiaoyuzhoufm.com/episode/69bbc8ea3c625cc5ae21b461"}'
+
+# Save transcript to file
+bash execute.sh '{"url":"https://www.xiaoyuzhoufm.com/episode/...","outputFile":"./transcripts/episode.md"}'
+
+# Transcribe a local audio file (skip download)
+bash execute.sh '{"audioFile":"/path/to/podcast.m4a"}'
+
+# Specify language hint
+bash execute.sh '{"url":"...","language":"Chinese"}'
+```
+
+## Parameters
+
+| Parameter | Required | Description |
+|-----------|----------|-------------|
+| `url` | Yes* | 小宇宙 episode URL |
+| `audioFile` | Yes* | Path to local audio file (alternative to url) |
+| `outputFile` | No | Save transcript as markdown to this path |
+| `language` | No | Language hint for Gemini (default: auto-detect) |
+
+*Either `url` or `audioFile` is required.
+
+## Output Format
+
+```json
+{
+  "success": true,
+  "title": "Episode Title",
+  "url": "https://www.xiaoyuzhoufm.com/episode/...",
+  "audioUrl": "https://media.xyzcdn.net/.../audio.m4a",
+  "model": "gemini-2.5-flash-preview-05-20",
+  "transcriptLength": 12345,
+  "transcript": "**Speaker 1:** [00:00:00] Welcome to the show..."
+}
+```
+
+## Transcript Format
+
+- Speaker turns identified with `**Speaker Name:** text`
+- Timestamps at segment/topic changes: `[HH:MM:SS]`
+- Preserves original language (Chinese/English/mixed)
+
+## Prerequisites
+
+- `GEMINI_API_KEY` environment variable or configured in Settings > API Keys
+- `curl` and `jq` available in PATH
+- Internet access to xiaoyuzhoufm.com and Gemini API
+
+## Notes
+
+- Audio files are typically 30-90 minutes (20-80 MB)
+- Gemini processing takes 30-120 seconds depending on audio length
+- Maximum wait time: 5 minutes for Gemini processing
+- Temp files are auto-cleaned on exit