forge-workflow 0.0.3 → 0.0.5

package/scripts/validate.sh

@@ -0,0 +1,94 @@
+#!/usr/bin/env bash
+# Unified validation script for Forge project
+# Runs all quality checks in sequence
+# Exits on first failure
+
+set -e  # Exit on first error
+set -o pipefail  # Catch errors in pipes
+
+# Colors for output
+if [ -t 1 ]; then
+  RED='\033[0;31m'
+  GREEN='\033[0;32m'
+  YELLOW='\033[1;33m'
+  BLUE='\033[0;34m'
+  NC='\033[0m' # No Color
+else
+  RED=''
+  GREEN=''
+  YELLOW=''
+  BLUE=''
+  NC=''
+fi
+
+# Print section header
+print_header() {
+  echo ""
+  echo -e "${BLUE}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}"
+  echo -e "${BLUE}▶ $1${NC}"
+  echo -e "${BLUE}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}"
+}
+
+# Print success message
+print_success() {
+  echo -e "${GREEN}✓ $1${NC}"
+}
+
+# Print error message
+print_error() {
+  echo -e "${RED}✗ $1${NC}"
+}
+
+# Print warning message
+print_warning() {
+  echo -e "${YELLOW}⚠ $1${NC}"
+}
+
+echo ""
+echo -e "${BLUE}╔═══════════════════════════════════════════╗${NC}"
+echo -e "${BLUE}║   Forge Quality Gate - Running Checks    ║${NC}"
+echo -e "${BLUE}╚═══════════════════════════════════════════╝${NC}"
+
+# Step 1: Type Check
+print_header "1/4: Type Check"
+print_warning "SKIPPED (no TypeScript in project)"
+
+# Step 2: Lint
+print_header "2/4: Lint"
+if bun run lint; then
+  print_success "Lint passed"
+else
+  print_error "Lint failed"
+  exit 1
+fi
+
+# Step 3: Security Audit
+print_header "3/4: Security Audit"
+AUDIT_OUTPUT=$(bun audit 2>&1 || true)
+if echo "$AUDIT_OUTPUT" | grep -qiE 'critical|high'; then
+  print_error "Security audit found critical/high vulnerabilities"
+  echo "$AUDIT_OUTPUT"
+  exit 1
+fi
+if bun audit; then
+  print_success "Security audit passed"
+else
+  print_warning "Security audit found issues (moderate/low — non-blocking)"
+fi
+
+# Step 4: Tests
+print_header "4/4: Tests"
+if bun test; then
+  print_success "All tests passed"
+else
+  print_error "Tests failed"
+  exit 1
+fi
+
+echo ""
+echo -e "${GREEN}╔═══════════════════════════════════════════╗${NC}"
+echo -e "${GREEN}║     ✓ All Checks Passed Successfully     ║${NC}"
+echo -e "${GREEN}╚═══════════════════════════════════════════╝${NC}"
+echo ""
+
+exit 0

package/skills/parallel-deep-research/SKILL.md

@@ -1,108 +1,108 @@
----
-name: parallel-deep-research
-description: >
-  Produces comprehensive research reports that go far beyond what built-in web
-  search can achieve. Sends research tasks to Parallel AI's pro/ultra processors
-  which spend 3-25 minutes autonomously crawling, reading, and synthesizing dozens
-  of sources — returning structured reports with citations. Built-in WebSearch
-  can only run a few queries; this skill runs an entire research pipeline externally.
-  No binary install — requires PARALLEL_API_KEY in .env.local. ALWAYS use this
-  skill instead of doing multiple WebSearch calls when the user needs a comprehensive
-  report, market analysis, competitive landscape, industry deep-dive, strategic
-  recommendations, or multi-source synthesis. This is the RIGHT tool for any
-  research task that would require more than 3-4 web searches to answer properly.
-  Also trigger during /plan Phase 2 research and /research workflows.
-compatibility: Requires PARALLEL_API_KEY in .env.local. Uses curl. Takes 3-25 minutes.
-metadata:
-  author: harshanandak
-  version: "1.0.0"
----
-
-# Parallel Deep Research
-
-Comprehensive research reports with multi-source synthesis. Use `pro` (3-9 min, $0.10) or `ultra` (5-25 min, $0.30) for deep analysis.
-
-> **CLI alternative (recommended)**: Install `parallel-cli` for official skill:
-> `npx skills add parallel-web/parallel-agent-skills --skill parallel-deep-research`
-
-## Setup
-
-```bash
-API_KEY=$(grep "^PARALLEL_API_KEY=" .env.local | cut -d= -f2)
-```
-
-## Create Research Task
-
-```bash
-curl -s -X POST "https://api.parallel.ai/v1/tasks/runs" \
-  -H "x-api-key: $API_KEY" \
-  -H "Content-Type: application/json" \
-  -d '{
-    "input": "Analyze the AI chatbot market. Include: size, growth, key players, trends, competitive threats",
-    "processor": "pro"
-  }'
-```
-
-Response: `{"run_id": "trun_abc123...", "status": "queued"}`
-
-## Get Result (polling)
-
-The result endpoint returns both status and output in one call. Poll until `status` is `completed`.
-
-```bash
-RUN_ID="trun_abc123..."
-MAX_POLLS=180  # 30 min max (180 × 10s)
-
-for i in $(seq 1 $MAX_POLLS); do
-  RESULT=$(curl -s "https://api.parallel.ai/v1/tasks/runs/$RUN_ID/result" \
-    -H "x-api-key: $API_KEY")
-
-  STATUS=$(echo "$RESULT" | grep -o '"status":"[^"]*"' | head -1 | cut -d'"' -f4)
-
-  if [ "$STATUS" = "completed" ]; then
-    echo "$RESULT"
-    break
-  elif [ "$STATUS" = "failed" ]; then
-    echo "Task failed: $RESULT"
-    break
-  fi
-
-  echo "Poll $i/$MAX_POLLS — Status: $STATUS"
-  sleep 10
-done
-
-if [ "$i" = "$MAX_POLLS" ] && [ "$STATUS" != "completed" ] && [ "$STATUS" != "failed" ]; then
-  echo "Timeout: task did not complete within 30 minutes"
-fi
-```
-
-## Processors
-
-| Processor | Speed | Cost | Use For |
-|-----------|-------|------|---------|
-| pro | 3-9 min | $0.10/task | Market analysis, strategic reports |
-| ultra | 5-25 min | $0.30/task | Comprehensive deep research |
-
-## Example: Market Analysis
-
-```json
-{
-  "input": "Analyze the AI chip market in 2024. Include market size, growth rate, key players (NVIDIA, AMD, Intel), emerging competitors, and 2025 outlook.",
-  "processor": "pro"
-}
-```
-
-Result: Markdown report with citations.
-
-## When to Use
-
-- Market research and competitive analysis
-- Strategic reports requiring multiple sources
-- Research that needs synthesis across many documents
-- Any task that would need more than 3-4 web searches to answer properly
-
-For quick facts or single-source lookups, use built-in WebSearch instead.
-
-## Timeout
-
-Set polling timeout to 1800s (30 min) for ultra tasks. Pro tasks typically complete in 3-9 min.
+---
+name: parallel-deep-research
+description: >
+  Produces comprehensive research reports that go far beyond what built-in web
+  search can achieve. Sends research tasks to Parallel AI's pro/ultra processors
+  which spend 3-25 minutes autonomously crawling, reading, and synthesizing dozens
+  of sources — returning structured reports with citations. Built-in WebSearch
+  can only run a few queries; this skill runs an entire research pipeline externally.
+  No binary install — requires PARALLEL_API_KEY in .env.local. ALWAYS use this
+  skill instead of doing multiple WebSearch calls when the user needs a comprehensive
+  report, market analysis, competitive landscape, industry deep-dive, strategic
+  recommendations, or multi-source synthesis. This is the RIGHT tool for any
+  research task that would require more than 3-4 web searches to answer properly.
+  Also trigger during /plan Phase 2 research and /research workflows.
+compatibility: Requires PARALLEL_API_KEY in .env.local. Uses curl. Takes 3-25 minutes.
+metadata:
+  author: harshanandak
+  version: "1.0.0"
+---
+
+# Parallel Deep Research
+
+Comprehensive research reports with multi-source synthesis. Use `pro` (3-9 min, $0.10) or `ultra` (5-25 min, $0.30) for deep analysis.
+
+> **CLI alternative (recommended)**: Install `parallel-cli` for official skill:
+> `npx skills add parallel-web/parallel-agent-skills --skill parallel-deep-research`
+
+## Setup
+
+```bash
+API_KEY=$(grep "^PARALLEL_API_KEY=" .env.local | cut -d= -f2)
+```
+
+## Create Research Task
+
+```bash
+curl -s -X POST "https://api.parallel.ai/v1/tasks/runs" \
+  -H "x-api-key: $API_KEY" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "input": "Analyze the AI chatbot market. Include: size, growth, key players, trends, competitive threats",
+    "processor": "pro"
+  }'
+```
+
+Response: `{"run_id": "trun_abc123...", "status": "queued"}`
+
+## Get Result (polling)
+
+The result endpoint returns both status and output in one call. Poll until `status` is `completed`.
+
+```bash
+RUN_ID="trun_abc123..."
+MAX_POLLS=180  # 30 min max (180 × 10s)
+
+for i in $(seq 1 $MAX_POLLS); do
+  RESULT=$(curl -s "https://api.parallel.ai/v1/tasks/runs/$RUN_ID/result" \
+    -H "x-api-key: $API_KEY")
+
+  STATUS=$(echo "$RESULT" | grep -o '"status":"[^"]*"' | head -1 | cut -d'"' -f4)
+
+  if [ "$STATUS" = "completed" ]; then
+    echo "$RESULT"
+    break
+  elif [ "$STATUS" = "failed" ]; then
+    echo "Task failed: $RESULT"
+    break
+  fi
+
+  echo "Poll $i/$MAX_POLLS — Status: $STATUS"
+  sleep 10
+done
+
+if [ "$i" = "$MAX_POLLS" ] && [ "$STATUS" != "completed" ] && [ "$STATUS" != "failed" ]; then
+  echo "Timeout: task did not complete within 30 minutes"
+fi
+```
+
+## Processors
+
+| Processor | Speed | Cost | Use For |
+|-----------|-------|------|---------|
+| pro | 3-9 min | $0.10/task | Market analysis, strategic reports |
+| ultra | 5-25 min | $0.30/task | Comprehensive deep research |
+
+## Example: Market Analysis
+
+```json
+{
+  "input": "Analyze the AI chip market in 2024. Include market size, growth rate, key players (NVIDIA, AMD, Intel), emerging competitors, and 2025 outlook.",
+  "processor": "pro"
+}
+```
+
+Result: Markdown report with citations.
+
+## When to Use
+
+- Market research and competitive analysis
+- Strategic reports requiring multiple sources
+- Research that needs synthesis across many documents
+- Any task that would need more than 3-4 web searches to answer properly
+
+For quick facts or single-source lookups, use built-in WebSearch instead.
+
+## Timeout
+
+Set polling timeout to 1800s (30 min) for ultra tasks. Pro tasks typically complete in 3-9 min.

package/skills/parallel-deep-research/evals/README.md

@@ -1,27 +1,27 @@
-# Eval Sets
-
-These eval files use a flat JSON array format targeting `scripts/eval_win.py`:
-
-```json
-[{"query": "...", "should_trigger": true}]
-```
-
-This is **not** compatible with the skill-creator plugin's `run_loop.py` which expects:
-
-```json
-{"skill_name": "...", "evals": [{"id": "...", "prompt": "...", "should_trigger": true}]}
-```
-
-To convert for `run_loop.py`:
-
-```bash
-python3 -c "
-import json, pathlib, uuid
-data = json.loads(pathlib.Path('evals.json').read_text())
-out = {'skill_name': 'SKILL-NAME-HERE', 'evals': [
-    {'id': str(uuid.uuid4()), 'prompt': item['query'], 'should_trigger': item['should_trigger']}
-    for item in data
-]}
-print(json.dumps(out, indent=2))
-" > evals_skill_creator.json
-```
+# Eval Sets
+
+These eval files use a flat JSON array format targeting `scripts/eval_win.py`:
+
+```json
+[{"query": "...", "should_trigger": true}]
+```
+
+This is **not** compatible with the skill-creator plugin's `run_loop.py` which expects:
+
+```json
+{"skill_name": "...", "evals": [{"id": "...", "prompt": "...", "should_trigger": true}]}
+```
+
+To convert for `run_loop.py`:
+
+```bash
+python3 -c "
+import json, pathlib, uuid
+data = json.loads(pathlib.Path('evals.json').read_text())
+out = {'skill_name': 'SKILL-NAME-HERE', 'evals': [
+    {'id': str(uuid.uuid4()), 'prompt': item['query'], 'should_trigger': item['should_trigger']}
+    for item in data
+]}
+print(json.dumps(out, indent=2))
+" > evals_skill_creator.json
+```

package/skills/parallel-deep-research/evals/evals.json

@@ -1,62 +1,62 @@
-[
-  {
-    "query": "I need a comprehensive market analysis of the developer tools space — cover the top 20 players, their funding, market positioning, and where the industry is heading over the next 3-5 years. Include data from Gartner, Forrester, and any recent VC investment reports",
-    "should_trigger": true
-  },
-  {
-    "query": "Write a deep research report on the state of WebAssembly adoption in production — synthesize case studies from companies using WASM, performance benchmarks vs native code, ecosystem maturity analysis, and strategic recommendations for when to adopt it",
-    "should_trigger": true
-  },
-  {
-    "query": "Our CTO wants a competitive landscape analysis comparing Convex, Supabase, Firebase, and PlanetScale for our backend rewrite. Need comprehensive feature comparison, pricing analysis at our scale (50K DAU), community health metrics, and risk assessment for each",
-    "should_trigger": true
-  },
-  {
-    "query": "Create a strategic report on the AI code generation market — analyze GitHub Copilot, Cursor, Claude Code, and emerging competitors. Cover adoption rates, developer satisfaction surveys, enterprise pricing trends, and predictions for 2027",
-    "should_trigger": true
-  },
-  {
-    "query": "I'm doing /plan Phase 2 research — produce a comprehensive analysis of event-driven architecture patterns in microservices, covering Kafka vs RabbitMQ vs NATS, with production case studies, failure mode analysis, and recommendations for our 100K events/sec throughput requirement",
-    "should_trigger": true
-  },
-  {
-    "query": "Write an industry deep-dive into the observability market — compare Datadog, Grafana Cloud, and New Relic across features, pricing, scalability, and OpenTelemetry support. Include customer migration stories and TCO analysis for a 500-node cluster",
-    "should_trigger": true
-  },
-  {
-    "query": "Research and synthesize the current state of edge computing for real-time AI inference — cover hardware options, cloud provider edge offerings, latency benchmarks, and case studies from autonomous vehicles and IoT deployments",
-    "should_trigger": true
-  },
-  {
-    "query": "Quick search: what's the current price of Bitcoin and what were Anthropic's latest announcements?",
-    "should_trigger": false
-  },
-  {
-    "query": "Find the official migration guide URL for ESLint's new flat config format",
-    "should_trigger": false
-  },
-  {
-    "query": "Search for recent blog posts about Bun 2.0 features and release date",
-    "should_trigger": false
-  },
-  {
-    "query": "Go to https://stripe.com/docs/api and extract the authentication section with all the code examples",
-    "should_trigger": false
-  },
-  {
-    "query": "Scrape https://openai.com/pricing and extract the per-token costs for each model tier",
-    "should_trigger": false
-  },
-  {
-    "query": "Build a structured company profile for Databricks — return JSON with founding year, funding rounds, valuation, employee count, and tech stack",
-    "should_trigger": false
-  },
-  {
-    "query": "Fix the TypeScript compilation error in src/services/auth.ts — it's complaining about missing type for the session token",
-    "should_trigger": false
-  },
-  {
-    "query": "Add unit tests for the rate limiter middleware in src/middleware/rateLimit.ts",
-    "should_trigger": false
-  }
-]
+[
+  {
+    "query": "I need a comprehensive market analysis of the developer tools space — cover the top 20 players, their funding, market positioning, and where the industry is heading over the next 3-5 years. Include data from Gartner, Forrester, and any recent VC investment reports",
+    "should_trigger": true
+  },
+  {
+    "query": "Write a deep research report on the state of WebAssembly adoption in production — synthesize case studies from companies using WASM, performance benchmarks vs native code, ecosystem maturity analysis, and strategic recommendations for when to adopt it",
+    "should_trigger": true
+  },
+  {
+    "query": "Our CTO wants a competitive landscape analysis comparing Convex, Supabase, Firebase, and PlanetScale for our backend rewrite. Need comprehensive feature comparison, pricing analysis at our scale (50K DAU), community health metrics, and risk assessment for each",
+    "should_trigger": true
+  },
+  {
+    "query": "Create a strategic report on the AI code generation market — analyze GitHub Copilot, Cursor, Claude Code, and emerging competitors. Cover adoption rates, developer satisfaction surveys, enterprise pricing trends, and predictions for 2027",
+    "should_trigger": true
+  },
+  {
+    "query": "I'm doing /plan Phase 2 research — produce a comprehensive analysis of event-driven architecture patterns in microservices, covering Kafka vs RabbitMQ vs NATS, with production case studies, failure mode analysis, and recommendations for our 100K events/sec throughput requirement",
+    "should_trigger": true
+  },
+  {
+    "query": "Write an industry deep-dive into the observability market — compare Datadog, Grafana Cloud, and New Relic across features, pricing, scalability, and OpenTelemetry support. Include customer migration stories and TCO analysis for a 500-node cluster",
+    "should_trigger": true
+  },
+  {
+    "query": "Research and synthesize the current state of edge computing for real-time AI inference — cover hardware options, cloud provider edge offerings, latency benchmarks, and case studies from autonomous vehicles and IoT deployments",
+    "should_trigger": true
+  },
+  {
+    "query": "Quick search: what's the current price of Bitcoin and what were Anthropic's latest announcements?",
+    "should_trigger": false
+  },
+  {
+    "query": "Find the official migration guide URL for ESLint's new flat config format",
+    "should_trigger": false
+  },
+  {
+    "query": "Search for recent blog posts about Bun 2.0 features and release date",
+    "should_trigger": false
+  },
+  {
+    "query": "Go to https://stripe.com/docs/api and extract the authentication section with all the code examples",
+    "should_trigger": false
+  },
+  {
+    "query": "Scrape https://openai.com/pricing and extract the per-token costs for each model tier",
+    "should_trigger": false
+  },
+  {
+    "query": "Build a structured company profile for Databricks — return JSON with founding year, funding rounds, valuation, employee count, and tech stack",
+    "should_trigger": false
+  },
+  {
+    "query": "Fix the TypeScript compilation error in src/services/auth.ts — it's complaining about missing type for the session token",
+    "should_trigger": false
+  },
+  {
+    "query": "Add unit tests for the rate limiter middleware in src/middleware/rateLimit.ts",
+    "should_trigger": false
+  }
+]