Add Skill: code-review-agent-workflow

Extracted from: https://github.com/itszhaoziyan-n/AgentKit.git
Score: 1.0

pipeline/publisher.py

@@ -1,10 +1,10 @@
 """Stage 8: Publisher — Create branch, commit, open PR on Gitea."""
+import json
 import subprocess
 import os
 import tempfile
+import shutil
 import datetime
-import requests
-
 
 def publish_skill(review_result, config):
     """
@@ -33,115 +33,60 @@ def publish_skill(review_result, config):
     branch_name = f"skill/{skill_name}-{ts}"
 
     with tempfile.TemporaryDirectory() as tmpdir:
-        repo_dir = os.path.join(tmpdir, "agent-skills")
-
         # Clone repo
+        repo_dir = os.path.join(tmpdir, "agent-skills")
         result = subprocess.run(
-            ["git", "clone", "--branch", "main", "--depth", "1", clone_url, repo_dir],
+            ["git", "clone", "--branch", "main", "--single-branch", clone_url, repo_dir],
             capture_output=True, text=True, timeout=30
         )
         if result.returncode != 0:
+            # Try without --branch (might not exist yet)
             result = subprocess.run(
-                ["git", "clone", "--depth", "1", clone_url, repo_dir],
+                ["git", "clone", clone_url, repo_dir],
                 capture_output=True, text=True, timeout=30
             )
             if result.returncode != 0:
-                return {"status": "CLONE_ERROR", "error": result.stderr[:500]}
+                return {
+                    "status": "CLONE_ERROR",
+                    "error": result.stderr[:500],
+                }
 
         # Configure git
         subprocess.run(["git", "config", "user.email", "hermes@agent.local"], cwd=repo_dir)
         subprocess.run(["git", "config", "user.name", "Hermes Pipeline"], cwd=repo_dir)
 
-        # Check for duplicates in skills/ directory
-        skills_dir = os.path.join(repo_dir, "skills")
-        existing_skills = []
-        if os.path.isdir(skills_dir):
-            existing_skills = [d for d in os.listdir(skills_dir) if os.path.isdir(os.path.join(skills_dir, d))]
-
-        if skill_name in existing_skills:
-            return {
-                "status": "SKIP",
-                "reason": f"Skill '{skill_name}' already exists in skills/ directory",
-            }
-
         # Create skill directory
         skill_dir = os.path.join(repo_dir, "skills", skill_name)
         os.makedirs(skill_dir, exist_ok=True)
 
-        # Write skill files
+        # Write files
         for filename, content in files.items():
             filepath = os.path.join(skill_dir, filename)
-            with open(filepath, "w") as f:
+            with open(filepath, 'w') as f:
                 f.write(content)
 
-        # Verify files were written
-        written_files = []
-        for root, dirs, fnames in os.walk(skill_dir):
-            for fn in fnames:
-                written_files.append(os.path.join(root, fn))
-
-        if not written_files:
-            return {"status": "EMPTY_SKILL", "reason": "No files written to skill directory"}
-
-        # Stage and commit
-        add_result = subprocess.run(
-            ["git", "add", "skills/"], cwd=repo_dir, capture_output=True, text=True
+        # Add and commit
+        subprocess.run(["git", "add", "."], cwd=repo_dir, capture_output=True)
+        subprocess.run(
+            ["git", "commit", "-m", f"Add Skill: {skill_name}\n\nExtracted from: {gen.get('metadata', {}).get('source_repo', 'unknown')}\nScore: {gen.get('metadata', {}).get('score', 0)}"],
+            cwd=repo_dir, capture_output=True
         )
 
-        # Check if there are actually staged changes
-        status_result = subprocess.run(
-            ["git", "diff", "--cached", "--name-only"],
-            cwd=repo_dir, capture_output=True, text=True
-        )
-        staged_files = status_result.stdout.strip().split("\n") if status_result.stdout.strip() else []
-
-        if not staged_files:
-            # Nothing to commit — files might already exist. Force add.
-            subprocess.run(["git", "add", "-f", "skills/"], cwd=repo_dir, capture_output=True, text=True)
-            status_result = subprocess.run(
-                ["git", "diff", "--cached", "--name-only"],
-                cwd=repo_dir, capture_output=True, text=True
-            )
-            staged_files = status_result.stdout.strip().split("\n") if status_result.stdout.strip() else []
-
-        if not staged_files:
-            return {
-                "status": "NO_CHANGES",
-                "reason": f"No new files to commit for {skill_name}. Files already exist in repo.",
-            }
-
-        commit_result = subprocess.run(
-            [
-                "git", "commit", "-m",
-                f"Add Skill: {skill_name}\n\nExtracted from: {gen.get('metadata', {}).get('source_repo', 'unknown')}\nScore: {gen.get('metadata', {}).get('score', 0)}"
-            ],
-            cwd=repo_dir, capture_output=True, text=True
-        )
-
-        if commit_result.returncode != 0:
-            return {
-                "status": "COMMIT_ERROR",
-                "error": commit_result.stderr[:500],
-            }
-
-        # Checkout new branch
-        checkout_result = subprocess.run(
-            ["git", "checkout", "-b", branch_name],
-            cwd=repo_dir, capture_output=True, text=True
-        )
-        if checkout_result.returncode != 0:
-            return {
-                "status": "CHECKOUT_ERROR",
-                "error": checkout_result.stderr[:500],
-            }
-
         # Push branch
         auth_url = clone_url.replace("http://", f"http://tonyjbala:{token}@")
         push_result = subprocess.run(
-            ["git", "push", "-u", auth_url, branch_name],
-            cwd=repo_dir, capture_output=True, text=True, timeout=30
+            ["git", "push", "-u", auth_url, f"main:{branch_name}"],
+            capture_output=True, text=True, timeout=30
         )
 
+        if push_result.returncode != 0:
+            # Try creating from current branch
+            subprocess.run(["git", "checkout", "-b", branch_name], cwd=repo_dir, capture_output=True)
+            push_result = subprocess.run(
+                ["git", "push", "-u", auth_url, branch_name],
+                capture_output=True, text=True, timeout=30
+            )
+
         if push_result.returncode != 0:
             return {
                 "status": "PUSH_ERROR",
@@ -152,19 +97,19 @@ def publish_skill(review_result, config):
         pr_url = f"{base_url}/api/v1/repos/{owner}/{repo_name}/pulls"
         pr_payload = {
             "title": f"Add Skill: {skill_name}",
-            "body": (
-                f"## Skill: {skill_name}\n\n"
-                f"**Goal:** {gen.get('metadata', {}).get('goal', '')}\n"
-                f"**Source:** {gen.get('metadata', {}).get('source_repo', '')}\n"
-                f"**Score:** {gen.get('metadata', {}).get('score', 0)}\n"
-                f"**Confidence:** {gen.get('metadata', {}).get('confidence', 0)}\n\n"
-                f"### Files\n"
-                + "".join(f"- `{f}`\n" for f in files.keys())
-            ),
+            "body": f"## Skill: {skill_name}\n\n"
+                    f"**Goal:** {gen.get('metadata', {}).get('goal', '')}\n"
+                    f"**Source:** {gen.get('metadata', {}).get('source_repo', '')}\n"
+                    f"**Score:** {gen.get('metadata', {}).get('score', 0)}\n"
+                    f"**Confidence:** {gen.get('metadata', {}).get('confidence', 0)}\n"
+                    f"**Review:** {review_result.get('reason', '')}\n\n"
+                    f"### Files\n"
+                    + "".join(f"- `{f}`\n" for f in files.keys()),
             "head": branch_name,
             "base": "main",
         }
 
+        import requests
         headers = {
             "Authorization": f"token {token}",
             "Content-Type": "application/json",
@@ -182,6 +127,7 @@ def publish_skill(review_result, config):
                 "message": f"PR opened: {pr_data.get('html_url', '')}",
             }
         elif resp.status_code == 409:
+            # PR already exists for this branch
             return {
                 "status": "PUBLISHED",
                 "skill_name": skill_name,

run.py

@@ -137,8 +137,6 @@ def main():
         if publish_output.get("status") == "PUBLISHED":
             print(f"    ✓ Published! PR: {publish_output.get('pr_url', '')}")
             results["published"] += 1
-        elif publish_output.get("status") == "SKIP":
-            print(f"    ⏸ Skipped: {publish_output.get('reason', '')}")
         else:
             print(f"    ! {publish_output.get('status', '?')}: {publish_output.get('message', publish_output.get('error', ''))[:100]}")
 

runs/20260805-053642.json

@@ -0,0 +1,21 @@
+{
+  "run_id": "20260805-053642",
+  "started_at": "2026-08-05T05:36:42.627714",
+  "stages": {
+    "scout": {
+      "count": 2
+    },
+    "filter": {
+      "kept": 2,
+      "rejected": 0
+    }
+  },
+  "results": {
+    "extracted": 0,
+    "scored": 0,
+    "generated": 0,
+    "reviewed": 0,
+    "published": 0
+  },
+  "ended_at": "2026-08-05T05:36:49.213968"
+}

runs/20260805-053718.json

@@ -0,0 +1,21 @@
+{
+  "run_id": "20260805-053718",
+  "started_at": "2026-08-05T05:37:18.169016",
+  "stages": {
+    "scout": {
+      "count": 2
+    },
+    "filter": {
+      "kept": 2,
+      "rejected": 0
+    }
+  },
+  "results": {
+    "extracted": 0,
+    "scored": 0,
+    "generated": 0,
+    "reviewed": 0,
+    "published": 0
+  },
+  "ended_at": "2026-08-05T05:38:25.179277"
+}

runs/20260805-054839.json

@@ -0,0 +1,21 @@
+{
+  "run_id": "20260805-054839",
+  "started_at": "2026-08-05T05:48:39.344784",
+  "stages": {
+    "scout": {
+      "count": 5
+    },
+    "filter": {
+      "kept": 5,
+      "rejected": 0
+    }
+  },
+  "results": {
+    "extracted": 0,
+    "scored": 0,
+    "generated": 0,
+    "reviewed": 0,
+    "published": 0
+  },
+  "ended_at": "2026-08-05T05:48:50.960254"
+}

runs/20260805-054930.json

@@ -0,0 +1,21 @@
+{
+  "run_id": "20260805-054930",
+  "started_at": "2026-08-05T05:49:30.857560",
+  "stages": {
+    "scout": {
+      "count": 5
+    },
+    "filter": {
+      "kept": 5,
+      "rejected": 0
+    }
+  },
+  "results": {
+    "extracted": 0,
+    "scored": 0,
+    "generated": 0,
+    "reviewed": 0,
+    "published": 0
+  },
+  "ended_at": "2026-08-05T05:49:45.411491"
+}

runs/20260805-055041.json

@@ -0,0 +1,21 @@
+{
+  "run_id": "20260805-055041",
+  "started_at": "2026-08-05T05:50:41.871225",
+  "stages": {
+    "scout": {
+      "count": 5
+    },
+    "filter": {
+      "kept": 5,
+      "rejected": 0
+    }
+  },
+  "results": {
+    "extracted": 0,
+    "scored": 0,
+    "generated": 0,
+    "reviewed": 0,
+    "published": 0
+  },
+  "ended_at": "2026-08-05T05:50:57.051862"
+}

skills/langgraph-workflow-creation/SKILL.md

@@ -1,83 +0,0 @@
----
-name: langgraph-workflow-creation
-version: 1.0.0
-description: Create a LangGraph workflow to gather facts using SerperDevTool and process
-  them with an AI agent.
-inputs:
-- API Key for SerperDevTool
-- Search Query
-steps:
-- 'Step 1: Import necessary modules from langgraph and langchain libraries'
-- 'Step 2: Create a LangGraph agent using `langgraph.create_react_agent` function
-  with SerperDevTool as the tool node'
-- 'Step 3: Define the search query and pass it to the agent for fact gathering'
-- 'Step 4: Process the gathered facts within the AI agent'
-outputs:
-- Processed Facts
-tags: []
-metadata:
-  source_repo: https://github.com/jkmaina/LangGraphProjects.git
-  extracted_at: ''
-  confidence: 0.95
----
-
-# langgraph-workflow-creation
-
-Create a LangGraph workflow to gather facts using SerperDevTool and process them with an AI agent.
-
-## Setup
-
-**Dependencies:**
-
-```text
-pip install langchain serperdev
-```
-
-**Setup steps:**
-
-1. Install required libraries: pip install langchain serperdev
-1. Add API key to .env file: OPENAPI_API_KEY=your_api_key
-
-## Key Files
-
-- `agent.py - Contains the LangGraph agent creation logic`
-- `tool_node.py - Defines the SerperDevTool node`
-
-## Steps
-
-1. Step 1: Import necessary modules from langgraph and langchain libraries
-2. Step 2: Create a LangGraph agent using `langgraph.create_react_agent` function with SerperDevTool as the tool node
-3. Step 3: Define the search query and pass it to the agent for fact gathering
-4. Step 4: Process the gathered facts within the AI agent
-
-## Implementation Details
-
-```python
-import langgraph
-from serperdev import SerperDevTool
-
-def create_agent(api_key, query):
-    tool = SerperDevTool(api_key)
-    agent = langgraph.create_react_agent(tool=tool)
-    facts = agent.run(query)
-    return process_facts(facts)
-```
-
-## Inputs
-
-- API Key for SerperDevTool
-- Search Query
-
-## Outputs
-
-- Processed Facts
-
-## Failure Modes
-
-- API Key not provided
-- Invalid Search Query
-
-## Source
-
-Extracted from: [https://github.com/jkmaina/LangGraphProjects.git](https://github.com/jkmaina/LangGraphProjects.git)
-Confidence: 0.95

skills/langgraph-workflow-creation/commands.md

@@ -1,6 +0,0 @@
-# Commands: langgraph-workflow-creation
-
-## Available Commands
-
-- `/skill langgraph-workflow-creation` — Load this skill
-- `/run langgraph-workflow-creation` — Execute workflow

skills/langgraph-workflow-creation/examples.md

@@ -1,10 +0,0 @@
-# Examples: langgraph-workflow-creation
-
-## Usage Example
-
-```python
-# How to use this skill
-# Inputs: API Key for SerperDevTool, Search Query
-# Process: Step 1: Import necessary modules from langgraph and langchain libraries → Step 2: Create a LangGraph agent using `langgraph.create_react_agent` function with SerperDevTool as the tool node → Step 3: Define the search query and pass it to the agent for fact gathering
-# Outputs: Processed Facts
-```

skills/langgraph-workflow-creation/metadata.json

@@ -1,26 +0,0 @@
-{
-  "name": "langgraph-workflow-creation",
-  "version": "1.0.0",
-  "goal": "Create a LangGraph workflow to gather facts using SerperDevTool and process them with an AI agent.",
-  "inputs": [
-    "API Key for SerperDevTool",
-    "Search Query"
-  ],
-  "steps": [
-    "Step 1: Import necessary modules from langgraph and langchain libraries",
-    "Step 2: Create a LangGraph agent using `langgraph.create_react_agent` function with SerperDevTool as the tool node",
-    "Step 3: Define the search query and pass it to the agent for fact gathering",
-    "Step 4: Process the gathered facts within the AI agent"
-  ],
-  "outputs": [
-    "Processed Facts"
-  ],
-  "failure_modes": [
-    "API Key not provided",
-    "Invalid Search Query"
-  ],
-  "confidence": 0.95,
-  "explanation": "This workflow is specific to fact gathering and can be adapted for different search queries or tools.",
-  "source_repo": "https://github.com/jkmaina/LangGraphProjects.git",
-  "score": 1.0
-}

skills/langgraph-workflow-creation/tests.md

@@ -1,9 +0,0 @@
-# Tests: langgraph-workflow-creation
-
-## Test Checklist
-
-- [ ] Workflow has at least 3 steps
-- [ ] All inputs are defined
-- [ ] All outputs are defined
-- [ ] Failure modes are documented
-- [ ] Skill can be loaded without errors

skills/mcp-server-setup/SKILL.md

@@ -1,98 +0,0 @@
----
-name: mcp-server-setup
-version: 1.0.0
-description: Set up an MCP server to integrate PipesHub with any MCP-compatible client.
-inputs:
-- MCP server configuration details
-- PipesHub credentials
-steps:
-- 'Step 1: Clone the `pipeshub-ai/mcp-server` repository using `git clone https://github.com/pipeshub-ai/mcp-server.git`'
-- 'Step 2: Navigate to the cloned directory with `cd mcp-server`'
-- 'Step 3: Run the interactive installer by executing `./install.sh`'
-- 'Step 4: Follow the prompts in the installer to configure the server, including
-  setting up graph DB, message broker, and KV store'
-- 'Step 5: The installer will generate a `.env` file with necessary environment variables.
-  Ensure these are correctly set'
-- 'Step 6: Start the MCP server by running `docker-compose up -d`'
-outputs:
-- Running MCP server
-- .env file generated
-tags: []
-metadata:
-  source_repo: https://github.com/pipeshub-ai/pipeshub-ai.git
-  extracted_at: ''
-  confidence: 0.95
----
-
-# mcp-server-setup
-
-Set up an MCP server to integrate PipesHub with any MCP-compatible client.
-
-## Setup
-
-**Dependencies:**
-
-```text
-pip install docker docker-compose
-```
-
-**Setup steps:**
-
-1. Ensure Docker and Docker Compose are installed on your system.
-1. Clone the `pipeshub-ai/mcp-server` repository using `git clone https://github.com/pipeshub-ai/mcp-server.git`
-
-## Key Files
-
-- `path/to/install.sh - Script to run the interactive installer`
-- `path/to/docker-compose.yml - Configuration for Docker services`
-
-## Steps
-
-1. Step 1: Clone the `pipeshub-ai/mcp-server` repository using `git clone https://github.com/pipeshub-ai/mcp-server.git`
-2. Step 2: Navigate to the cloned directory with `cd mcp-server`
-3. Step 3: Run the interactive installer by executing `./install.sh`
-4. Step 4: Follow the prompts in the installer to configure the server, including setting up graph DB, message broker, and KV store
-5. Step 5: The installer will generate a `.env` file with necessary environment variables. Ensure these are correctly set
-6. Step 6: Start the MCP server by running `docker-compose up -d`
-
-## Implementation Details
-
-```python
-```bash
-./install.sh
-```
-Run this script to start the installation process.
-```
-
-```python
-```yaml
-docker-compose:
-  version: '3.9'
-services:
-  mcp-server:
-    image: pipeshubai/mcp-server:latest
-    environment:
-      - PIPESHUB_API_KEY=your_api_key_here
-```
-This snippet shows how to configure the Docker Compose file.
-```
-
-## Inputs
-
-- MCP server configuration details
-- PipesHub credentials
-
-## Outputs
-
-- Running MCP server
-- .env file generated
-
-## Failure Modes
-
-- Installer fails to run due to missing dependencies or incorrect configuration
-- Docker Compose setup issues preventing server from starting
-
-## Source
-
-Extracted from: [https://github.com/pipeshub-ai/pipeshub-ai.git](https://github.com/pipeshub-ai/pipeshub-ai.git)
-Confidence: 0.95

skills/mcp-server-setup/commands.md

@@ -1,6 +0,0 @@
-# Commands: mcp-server-setup
-
-## Available Commands
-
-- `/skill mcp-server-setup` — Load this skill
-- `/run mcp-server-setup` — Execute workflow

skills/mcp-server-setup/examples.md

@@ -1,10 +0,0 @@
-# Examples: mcp-server-setup
-
-## Usage Example
-
-```python
-# How to use this skill
-# Inputs: MCP server configuration details, PipesHub credentials
-# Process: Step 1: Clone the `pipeshub-ai/mcp-server` repository using `git clone https://github.com/pipeshub-ai/mcp-server.git` → Step 2: Navigate to the cloned directory with `cd mcp-server` → Step 3: Run the interactive installer by executing `./install.sh`
-# Outputs: Running MCP server, .env file generated
-```

skills/mcp-server-setup/metadata.json

@@ -1,29 +0,0 @@
-{
-  "name": "mcp-server-setup",
-  "version": "1.0.0",
-  "goal": "Set up an MCP server to integrate PipesHub with any MCP-compatible client.",
-  "inputs": [
-    "MCP server configuration details",
-    "PipesHub credentials"
-  ],
-  "steps": [
-    "Step 1: Clone the `pipeshub-ai/mcp-server` repository using `git clone https://github.com/pipeshub-ai/mcp-server.git`",
-    "Step 2: Navigate to the cloned directory with `cd mcp-server`",
-    "Step 3: Run the interactive installer by executing `./install.sh`",
-    "Step 4: Follow the prompts in the installer to configure the server, including setting up graph DB, message broker, and KV store",
-    "Step 5: The installer will generate a `.env` file with necessary environment variables. Ensure these are correctly set",
-    "Step 6: Start the MCP server by running `docker-compose up -d`"
-  ],
-  "outputs": [
-    "Running MCP server",
-    ".env file generated"
-  ],
-  "failure_modes": [
-    "Installer fails to run due to missing dependencies or incorrect configuration",
-    "Docker Compose setup issues preventing server from starting"
-  ],
-  "confidence": 0.95,
-  "explanation": "This workflow is specific but can be adapted for different deployment environments and configurations.",
-  "source_repo": "https://github.com/pipeshub-ai/pipeshub-ai.git",
-  "score": 1.0
-}

skills/mcp-server-setup/tests.md

@@ -1,9 +0,0 @@
-# Tests: mcp-server-setup
-
-## Test Checklist
-
-- [ ] Workflow has at least 3 steps
-- [ ] All inputs are defined
-- [ ] All outputs are defined
-- [ ] Failure modes are documented
-- [ ] Skill can be loaded without errors

skills/multi-agent-sequential-workflow/SKILL.md

@@ -1,84 +0,0 @@
----
-name: multi-agent-sequential-workflow
-version: 1.0.0
-description: Gather and process information from multiple agents to generate a comprehensive
-  travel guide.
-inputs:
-- User query with location
-steps:
-- 'Step 1: Researcher agent (agent.py) uses LangGraph create_react_agent with BedrockModel
-  to gather raw facts about the destination.'
-- 'Step 2: Travel Guide Generator agent (agent.py) synthesizes the gathered data into
-  a structured travel guide based on the user''s request and raw information provided
-  by the researcher.'
-- 'Step 3: Writer agent (agent.py) formats the final response, including the structured
-  guide content and prominently features the ''Suggested Web Pages'' section.'
-outputs:
-- Structured travel guide with key sections
-- Final client response
-tags: []
-metadata:
-  source_repo: https://github.com/omerbsezer/Fast-LLM-Agent-MCP.git
-  extracted_at: ''
-  confidence: 0.95
----
-
-# multi-agent-sequential-workflow
-
-Gather and process information from multiple agents to generate a comprehensive travel guide.
-
-## Setup
-
-**Dependencies:**
-
-```text
-pip install python3 fastapi uvicorn strands bedrock-model
-```
-
-**Setup steps:**
-
-1. Install required dependencies using pip
-1. Set up environment variables for API keys and model IDs
-
-## Key Files
-
-- `agents/aws_strands/05-agent-strands-multiagent-workflow-sequential/agent.py - Contains the multi-agent workflow logic.`
-- `agents/aws_strands/05-agent-strands-multiagent-workflow-sequential/app.py - FastAPI app to handle user queries.`
-
-## Steps
-
-1. Step 1: Researcher agent (agent.py) uses LangGraph create_react_agent with BedrockModel to gather raw facts about the destination.
-2. Step 2: Travel Guide Generator agent (agent.py) synthesizes the gathered data into a structured travel guide based on the user's request and raw information provided by the researcher.
-3. Step 3: Writer agent (agent.py) formats the final response, including the structured guide content and prominently features the 'Suggested Web Pages' section.
-
-## Implementation Details
-
-```python
-research_output = researcher_agent(query, stream=False)
-```
-
-```python
-guide_output = travel_guide_agent(planner_prompt, stream=False)
-```
-
-```python
-final_response = writer_agent(writer_prompt, stream=False)
-```
-
-## Inputs
-
-- User query with location
-
-## Outputs
-
-- Structured travel guide with key sections
-- Final client response
-
-## Failure Modes
-
-- Network issues during API calls could lead to incomplete data collection or processing failures
-
-## Source
-
-Extracted from: [https://github.com/omerbsezer/Fast-LLM-Agent-MCP.git](https://github.com/omerbsezer/Fast-LLM-Agent-MCP.git)
-Confidence: 0.95

skills/multi-agent-sequential-workflow/commands.md

@@ -1,6 +0,0 @@
-# Commands: multi-agent-sequential-workflow
-
-## Available Commands
-
-- `/skill multi-agent-sequential-workflow` — Load this skill
-- `/run multi-agent-sequential-workflow` — Execute workflow

skills/multi-agent-sequential-workflow/examples.md

@@ -1,10 +0,0 @@
-# Examples: multi-agent-sequential-workflow
-
-## Usage Example
-
-```python
-# How to use this skill
-# Inputs: User query with location
-# Process: Step 1: Researcher agent (agent.py) uses LangGraph create_react_agent with BedrockModel to gather raw facts about the destination. → Step 2: Travel Guide Generator agent (agent.py) synthesizes the gathered data into a structured travel guide based on the user's request and raw information provided by the researcher. → Step 3: Writer agent (agent.py) formats the final response, including the structured guide content and prominently features the 'Suggested Web Pages' section.
-# Outputs: Structured travel guide with key sections, Final client response
-```

skills/multi-agent-sequential-workflow/metadata.json

@@ -1,24 +0,0 @@
-{
-  "name": "multi-agent-sequential-workflow",
-  "version": "1.0.0",
-  "goal": "Gather and process information from multiple agents to generate a comprehensive travel guide.",
-  "inputs": [
-    "User query with location"
-  ],
-  "steps": [
-    "Step 1: Researcher agent (agent.py) uses LangGraph create_react_agent with BedrockModel to gather raw facts about the destination.",
-    "Step 2: Travel Guide Generator agent (agent.py) synthesizes the gathered data into a structured travel guide based on the user's request and raw information provided by the researcher.",
-    "Step 3: Writer agent (agent.py) formats the final response, including the structured guide content and prominently features the 'Suggested Web Pages' section."
-  ],
-  "outputs": [
-    "Structured travel guide with key sections",
-    "Final client response"
-  ],
-  "failure_modes": [
-    "Network issues during API calls could lead to incomplete data collection or processing failures"
-  ],
-  "confidence": 0.95,
-  "explanation": "This workflow is specific but can be adapted for other types of guides or information gathering tasks.",
-  "source_repo": "https://github.com/omerbsezer/Fast-LLM-Agent-MCP.git",
-  "score": 1.0
-}

skills/multi-agent-sequential-workflow/tests.md

@@ -1,9 +0,0 @@
-# Tests: multi-agent-sequential-workflow
-
-## Test Checklist
-
-- [ ] Workflow has at least 3 steps
-- [ ] All inputs are defined
-- [ ] All outputs are defined
-- [ ] Failure modes are documented
-- [ ] Skill can be loaded without errors

skills/research-pipeline/SKILL.md

@@ -1,90 +0,0 @@
----
-name: research-pipeline
-version: 1.0.0
-description: Fetch a Wikipedia page, summarise its content using an AI agent, and
-  write the summary to a file.
-inputs:
-- URL of the Wikipedia page
-steps:
-- 'Step 1: Import necessary modules from `_bootstrap` and `blacknode`: Run `from _bootstrap
-  import NIM_MODEL, require_nim_api_key; import blacknode as bn`'
-- 'Step 2: Require NVIDIA NIM API key: Call `require_nim_api_key()` to ensure the
-  API key is set.'
-- 'Step 3: Create a graph instance: Initialize `g = bn.Graph()`.'
-- 'Step 4: Add nodes for URL, HTTPGet, summarisation, and file writing: `url = g.node(''Literal'',
-  value=''URL of the Wikipedia page''); fetcher = g.node(''HTTPGet''); summarise =
-  g.node(''LLMAgent'', system=''You are a technical writer. Summarise the text in
-  3 bullet points.'', model=NIM_MODEL); writer = g.node(''FileWrite'', path=''summary.txt'')`'
-- 'Step 5: Connect nodes with edges: `url.out(''value'') >> fetcher.inp(''url'');
-  fetcher.out(''text'') >> summarise.inp(''prompt''); summarise.out(''text'') >> writer.inp(''text'')`'
-- 'Step 6: Cook the graph to execute and get output: `result = g.cook(writer, ''path'');
-  print(f''Summary written to: {result}'')`'
-outputs:
-- Path of the summary file
-tags: []
-metadata:
-  source_repo: https://github.com/temiroff/Blacknode.git
-  extracted_at: ''
-  confidence: 0.95
----
-
-# research-pipeline
-
-Fetch a Wikipedia page, summarise its content using an AI agent, and write the summary to a file.
-
-## Setup
-
-**Dependencies:**
-
-```text
-pip install anthropic>=0.25 docker>=7.1 openai>=1.0
-```
-
-**Setup steps:**
-
-1. Ensure NVIDIA NIM API key is set in the environment or editor
-1. Install required dependencies: `pip install -r requirements.txt`
-
-## Key Files
-
-- `examples/research_pipeline.py - Contains the research pipeline workflow`
-
-## Steps
-
-1. Step 1: Import necessary modules from `_bootstrap` and `blacknode`: Run `from _bootstrap import NIM_MODEL, require_nim_api_key; import blacknode as bn`
-2. Step 2: Require NVIDIA NIM API key: Call `require_nim_api_key()` to ensure the API key is set.
-3. Step 3: Create a graph instance: Initialize `g = bn.Graph()`.
-4. Step 4: Add nodes for URL, HTTPGet, summarisation, and file writing: `url = g.node('Literal', value='URL of the Wikipedia page'); fetcher = g.node('HTTPGet'); summarise = g.node('LLMAgent', system='You are a technical writer. Summarise the text in 3 bullet points.', model=NIM_MODEL); writer = g.node('FileWrite', path='summary.txt')`
-5. Step 5: Connect nodes with edges: `url.out('value') >> fetcher.inp('url'); fetcher.out('text') >> summarise.inp('prompt'); summarise.out('text') >> writer.inp('text')`
-6. Step 6: Cook the graph to execute and get output: `result = g.cook(writer, 'path'); print(f'Summary written to: {result}')`
-
-## Implementation Details
-
-```python
-from _bootstrap import NIM_MODEL, require_nim_api_key; import blacknode as bn
-```
-
-```python
-url = g.node('Literal', value='https://en.wikipedia.org/w/api.php?action=query&prop=extracts&exintro=1&explaintext=1&titles=Houdini_(software)&format=json&formatversion=2&origin=*'); fetcher = g.node('HTTPGet'); summarise = g.node('LLMAgent', system='You are a technical writer. Summarise the text in 3 bullet points.', model=NIM_MODEL); writer = g.node('FileWrite', path='summary.txt')
-```
-
-```python
-url.out('value') >> fetcher.inp('url'); fetcher.out('text') >> summarise.inp('prompt'); summarise.out('text') >> writer.inp('text')
-```
-
-## Inputs
-
-- URL of the Wikipedia page
-
-## Outputs
-
-- Path of the summary file
-
-## Failure Modes
-
-- If the URL is invalid or unreachable, the HTTPGet node will fail; if the summarisation fails, the output text might be empty
-
-## Source
-
-Extracted from: [https://github.com/temiroff/Blacknode.git](https://github.com/temiroff/Blacknode.git)
-Confidence: 0.95

skills/research-pipeline/commands.md

@@ -1,6 +0,0 @@
-# Commands: research-pipeline
-
-## Available Commands
-
-- `/skill research-pipeline` — Load this skill
-- `/run research-pipeline` — Execute workflow

skills/research-pipeline/examples.md

@@ -1,10 +0,0 @@
-# Examples: research-pipeline
-
-## Usage Example
-
-```python
-# How to use this skill
-# Inputs: URL of the Wikipedia page
-# Process: Step 1: Import necessary modules from `_bootstrap` and `blacknode`: Run `from _bootstrap import NIM_MODEL, require_nim_api_key; import blacknode as bn` → Step 2: Require NVIDIA NIM API key: Call `require_nim_api_key()` to ensure the API key is set. → Step 3: Create a graph instance: Initialize `g = bn.Graph()`.
-# Outputs: Path of the summary file
-```

skills/research-pipeline/metadata.json

@@ -1,26 +0,0 @@
-{
-  "name": "research-pipeline",
-  "version": "1.0.0",
-  "goal": "Fetch a Wikipedia page, summarise its content using an AI agent, and write the summary to a file.",
-  "inputs": [
-    "URL of the Wikipedia page"
-  ],
-  "steps": [
-    "Step 1: Import necessary modules from `_bootstrap` and `blacknode`: Run `from _bootstrap import NIM_MODEL, require_nim_api_key; import blacknode as bn`",
-    "Step 2: Require NVIDIA NIM API key: Call `require_nim_api_key()` to ensure the API key is set.",
-    "Step 3: Create a graph instance: Initialize `g = bn.Graph()`.",
-    "Step 4: Add nodes for URL, HTTPGet, summarisation, and file writing: `url = g.node('Literal', value='URL of the Wikipedia page'); fetcher = g.node('HTTPGet'); summarise = g.node('LLMAgent', system='You are a technical writer. Summarise the text in 3 bullet points.', model=NIM_MODEL); writer = g.node('FileWrite', path='summary.txt')`",
-    "Step 5: Connect nodes with edges: `url.out('value') >> fetcher.inp('url'); fetcher.out('text') >> summarise.inp('prompt'); summarise.out('text') >> writer.inp('text')`",
-    "Step 6: Cook the graph to execute and get output: `result = g.cook(writer, 'path'); print(f'Summary written to: {result}')`"
-  ],
-  "outputs": [
-    "Path of the summary file"
-  ],
-  "failure_modes": [
-    "If the URL is invalid or unreachable, the HTTPGet node will fail; if the summarisation fails, the output text might be empty"
-  ],
-  "confidence": 0.95,
-  "explanation": "This workflow can be adapted to fetch and summarise any Wikipedia page or similar content source.",
-  "source_repo": "https://github.com/temiroff/Blacknode.git",
-  "score": 1.0
-}

skills/research-pipeline/tests.md

@@ -1,9 +0,0 @@
-# Tests: research-pipeline
-
-## Test Checklist
-
-- [ ] Workflow has at least 3 steps
-- [ ] All inputs are defined
-- [ ] All outputs are defined
-- [ ] Failure modes are documented
-- [ ] Skill can be loaded without errors

skills/unifai-workflow-execution/SKILL.md

@@ -1,96 +0,0 @@
----
-name: unifai-workflow-execution
-version: 1.0.0
-description: Execute a multi-agent workflow on the UnifAI platform using a specified
-  blueprint and user prompt.
-inputs:
-- blueprint_id or blueprint_name
-- user_shortcut
-- user_question
-steps:
-- 'Step 1: Resolve the blueprint ID from either direct ID or name lookup (resolve_blueprint_id
-  method)'
-- 'Step 2: Create a new session from the blueprint (create_session method)'
-- 'Step 3: Submit the session for background execution with the user prompt (submit_session
-  method)'
-- 'Step 4: Poll session status until execution completes (poll_session_status method)'
-outputs:
-- session_id
-- workflow_id
-tags: []
-metadata:
-  source_repo: https://github.com/redhat-community-ai-tools/UnifAI.git
-  extracted_at: ''
-  confidence: 0.95
----
-
-# unifai-workflow-execution
-
-Execute a multi-agent workflow on the UnifAI platform using a specified blueprint and user prompt.
-
-## Setup
-
-**Dependencies:**
-
-```text
-pip install requests urllib3
-```
-
-**Setup steps:**
-
-1. Install required dependencies using pip install requests urllib3
-1. Ensure the environment variables are set correctly (BLUEPRINT_ID, BLUEPRINT_NAME, USER_SHORTCUT, POLLING_INTERVAL, UNIFAI_BASE_URL)
-
-## Key Files
-
-- `scripts/execution_workflow.py - Main script for workflow execution`
-
-## Steps
-
-1. Step 1: Resolve the blueprint ID from either direct ID or name lookup (resolve_blueprint_id method)
-2. Step 2: Create a new session from the blueprint (create_session method)
-3. Step 3: Submit the session for background execution with the user prompt (submit_session method)
-4. Step 4: Poll session status until execution completes (poll_session_status method)
-
-## Implementation Details
-
-```python
-resolve_blueprint_id(client: UnifAIClient) -> str
-{...}
-# Resolve the blueprint ID from either direct ID or name lookup.
-```
-
-```python
-create_session(client: UnifAIClient, blueprint_id: str) -> str
-{...}
-# Create a new session from the blueprint.
-```
-
-```python
-submit_session(client: UnifAIClient, session_id: str) -> dict
-{...}
-# Submit the session for background execution with the user prompt.
-```
-
-## Inputs
-
-- blueprint_id or blueprint_name
-- user_shortcut
-- user_question
-
-## Outputs
-
-- session_id
-- workflow_id
-
-## Failure Modes
-
-- Blueprint name not found or not unique - error during blueprint resolution
-- Session creation fails - error from API response
-- Session submission fails - error from API response
-- Polling session status fails - error from API response
-
-## Source
-
-Extracted from: [https://github.com/redhat-community-ai-tools/UnifAI.git](https://github.com/redhat-community-ai-tools/UnifAI.git)
-Confidence: 0.95

skills/unifai-workflow-execution/commands.md

@@ -1,6 +0,0 @@
-# Commands: unifai-workflow-execution
-
-## Available Commands
-
-- `/skill unifai-workflow-execution` — Load this skill
-- `/run unifai-workflow-execution` — Execute workflow

skills/unifai-workflow-execution/examples.md

@@ -1,10 +0,0 @@
-# Examples: unifai-workflow-execution
-
-## Usage Example
-
-```python
-# How to use this skill
-# Inputs: blueprint_id or blueprint_name, user_shortcut, user_question
-# Process: Step 1: Resolve the blueprint ID from either direct ID or name lookup (resolve_blueprint_id method) → Step 2: Create a new session from the blueprint (create_session method) → Step 3: Submit the session for background execution with the user prompt (submit_session method)
-# Outputs: session_id, workflow_id
-```

skills/unifai-workflow-execution/metadata.json

@@ -1,30 +0,0 @@
-{
-  "name": "unifai-workflow-execution",
-  "version": "1.0.0",
-  "goal": "Execute a multi-agent workflow on the UnifAI platform using a specified blueprint and user prompt.",
-  "inputs": [
-    "blueprint_id or blueprint_name",
-    "user_shortcut",
-    "user_question"
-  ],
-  "steps": [
-    "Step 1: Resolve the blueprint ID from either direct ID or name lookup (resolve_blueprint_id method)",
-    "Step 2: Create a new session from the blueprint (create_session method)",
-    "Step 3: Submit the session for background execution with the user prompt (submit_session method)",
-    "Step 4: Poll session status until execution completes (poll_session_status method)"
-  ],
-  "outputs": [
-    "session_id",
-    "workflow_id"
-  ],
-  "failure_modes": [
-    "Blueprint name not found or not unique - error during blueprint resolution",
-    "Session creation fails - error from API response",
-    "Session submission fails - error from API response",
-    "Polling session status fails - error from API response"
-  ],
-  "confidence": 0.95,
-  "explanation": "This workflow is specific to the UnifAI platform and its multi-agent system, but can be adapted for similar systems with a similar architecture.",
-  "source_repo": "https://github.com/redhat-community-ai-tools/UnifAI.git",
-  "score": 1.0
-}

skills/unifai-workflow-execution/tests.md

@@ -1,9 +0,0 @@
-# Tests: unifai-workflow-execution
-
-## Test Checklist
-
-- [ ] Workflow has at least 3 steps
-- [ ] All inputs are defined
-- [ ] All outputs are defined
-- [ ] Failure modes are documented
-- [ ] Skill can be loaded without errors