Add Skill: literature-review-with-traceable-ai-evidence

Extracted from: https://github.com/0verL1nk/PaperSage.git
Score: 1.0

skills/graph-based-node-orchestration/SKILL.md

@@ -1,108 +0,0 @@
----
-name: graph-based-node-orchestration
-version: 1.0.0
-description: Build a typed node graph that processes data through a sequence of operations
-  and produces a final result
-inputs:
-- NIM_MODEL constant (e.g., 'nim:meta/llama-3.1-8b-instruct') for the LLM model
-- blacknode package with Graph, Node, and cook functionality
-- Python script defining node types with inputs/outputs and connecting them via edges
-steps:
-- Import required modules (blacknode as bn, NIM_MODEL) and ensure API keys are available
-  via require_nim_api_key()
-- Create a bn.Graph() instance to hold all nodes and their connections
-- Define individual nodes with specific input/output parameters (e.g., Text node with
-  'value' input, LLMAgent node with model parameter, Output node with 'value' output)
-- Connect nodes together using edge definitions (from_port -> to_port) to establish
-  data flow
-- Execute the graph using g.cook() to run the pipeline and process data through the
-  node chain
-- Extract the final result from the output node to complete the workflow
-outputs:
-- A fully constructed graph with typed nodes and defined connections
-- Executed result (e.g., processed text, summary, or other output) from the final
-  node
-- A reusable pattern that can be adapted to different models, hardware, or task types
-tags: []
-metadata:
-  source_repo: https://github.com/temiroff/Blacknode.git
-  extracted_at: ''
-  confidence: 0.95
----
-
-# graph-based-node-orchestration
-
-Build a typed node graph that processes data through a sequence of operations and produces a final result
-
-## Setup
-
-**Dependencies:**
-
-```text
-pip install blacknode >= 0.3.0 Python >= 3.11 NVIDIA NIM API key (optional but recommended) Anthropic, OpenAI, or other LLM models
-```
-
-**Setup steps:**
-
-1. Clone the repository and install dependencies: pip install -e .
-1. Set NVIDIA_API_KEY or other required API keys in .env
-1. Run the example script: python examples/hello_agent.py
-1. For production, configure hardware pairing and deploy via the blacknode CLI
-
-## Key Files
-
-- `examples/converted_nvidia_nim.py - Full graph with Model, Text, LLMAgent, Output nodes`
-- `examples/hello_agent.py - Minimal agent example connecting Literal → LLMAgent → Print`
-- `blacknode/core - Graph and node implementation (internal)`
-
-## Steps
-
-1. Import required modules (blacknode as bn, NIM_MODEL) and ensure API keys are available via require_nim_api_key()
-2. Create a bn.Graph() instance to hold all nodes and their connections
-3. Define individual nodes with specific input/output parameters (e.g., Text node with 'value' input, LLMAgent node with model parameter, Output node with 'value' output)
-4. Connect nodes together using edge definitions (from_port -> to_port) to establish data flow
-5. Execute the graph using g.cook() to run the pipeline and process data through the node chain
-6. Extract the final result from the output node to complete the workflow
-
-## Implementation Details
-
-```python
-g = bn.Graph()
-```
-
-```python
-model = g.node('Model', **{'value': 'nim:meta/llama-3.1-8b-instruct'})
-```
-
-```python
-agent = g.node('LLMAgent', **{model})
-```
-
-```python
-result = g.cook(output, 'value')
-```
-
-## Inputs
-
-- NIM_MODEL constant (e.g., 'nim:meta/llama-3.1-8b-instruct') for the LLM model
-- blacknode package with Graph, Node, and cook functionality
-- Python script defining node types with inputs/outputs and connecting them via edges
-
-## Outputs
-
-- A fully constructed graph with typed nodes and defined connections
-- Executed result (e.g., processed text, summary, or other output) from the final node
-- A reusable pattern that can be adapted to different models, hardware, or task types
-
-## Failure Modes
-
-- Missing or invalid API key (NIM_API_KEY, OPENAI_API_KEY) causing require_nim_api_key() to fail
-- Type mismatch in node connections (e.g., expecting 'value' but receiving 'text') breaking the data flow
-- Model not available or unreachable (NIM_MODEL not found) causing the LLMAgent node to fail
-- Graph execution error due to incorrect edge configuration or circular dependencies
-- Resource exhaustion (e.g., GPU memory) when processing large inputs in the pipeline
-
-## Source
-
-Extracted from: [https://github.com/temiroff/Blacknode.git](https://github.com/temiroff/Blacknode.git)
-Confidence: 0.95

skills/graph-based-node-orchestration/commands.md

@@ -1,6 +0,0 @@
-# Commands: graph-based-node-orchestration
-
-## Available Commands
-
-- `/skill graph-based-node-orchestration` — Load this skill
-- `/run graph-based-node-orchestration` — Execute workflow

skills/graph-based-node-orchestration/examples.md

@@ -1,10 +0,0 @@
-# Examples: graph-based-node-orchestration
-
-## Usage Example
-
-```python
-# How to use this skill
-# Inputs: NIM_MODEL constant (e.g., 'nim:meta/llama-3.1-8b-instruct') for the LLM model, blacknode package with Graph, Node, and cook functionality, Python script defining node types with inputs/outputs and connecting them via edges
-# Process: Import required modules (blacknode as bn, NIM_MODEL) and ensure API keys are available via require_nim_api_key() → Create a bn.Graph() instance to hold all nodes and their connections → Define individual nodes with specific input/output parameters (e.g., Text node with 'value' input, LLMAgent node with model parameter, Output node with 'value' output)
-# Outputs: A fully constructed graph with typed nodes and defined connections, Executed result (e.g., processed text, summary, or other output) from the final node, A reusable pattern that can be adapted to different models, hardware, or task types
-```

skills/graph-based-node-orchestration/metadata.json

@@ -1,34 +0,0 @@
-{
-  "name": "graph-based-node-orchestration",
-  "version": "1.0.0",
-  "goal": "Build a typed node graph that processes data through a sequence of operations and produces a final result",
-  "inputs": [
-    "NIM_MODEL constant (e.g., 'nim:meta/llama-3.1-8b-instruct') for the LLM model",
-    "blacknode package with Graph, Node, and cook functionality",
-    "Python script defining node types with inputs/outputs and connecting them via edges"
-  ],
-  "steps": [
-    "Import required modules (blacknode as bn, NIM_MODEL) and ensure API keys are available via require_nim_api_key()",
-    "Create a bn.Graph() instance to hold all nodes and their connections",
-    "Define individual nodes with specific input/output parameters (e.g., Text node with 'value' input, LLMAgent node with model parameter, Output node with 'value' output)",
-    "Connect nodes together using edge definitions (from_port -> to_port) to establish data flow",
-    "Execute the graph using g.cook() to run the pipeline and process data through the node chain",
-    "Extract the final result from the output node to complete the workflow"
-  ],
-  "outputs": [
-    "A fully constructed graph with typed nodes and defined connections",
-    "Executed result (e.g., processed text, summary, or other output) from the final node",
-    "A reusable pattern that can be adapted to different models, hardware, or task types"
-  ],
-  "failure_modes": [
-    "Missing or invalid API key (NIM_API_KEY, OPENAI_API_KEY) causing require_nim_api_key() to fail",
-    "Type mismatch in node connections (e.g., expecting 'value' but receiving 'text') breaking the data flow",
-    "Model not available or unreachable (NIM_MODEL not found) causing the LLMAgent node to fail",
-    "Graph execution error due to incorrect edge configuration or circular dependencies",
-    "Resource exhaustion (e.g., GPU memory) when processing large inputs in the pipeline"
-  ],
-  "confidence": 0.95,
-  "explanation": "This workflow demonstrates a declarative graph-based orchestration pattern where nodes are connected via explicit ports and data flows through the graph. The pattern is highly reusable across different domains (robotics, research, data processing) because it separates graph structure from execution logic. The same graph construction and cook pattern can be adapted to different models (NIM, Anthropic, OpenAI), hardware targets (CPU, GPU, Jetson), and task types (LLM reasoning, file I/O, sensor processing).",
-  "source_repo": "https://github.com/temiroff/Blacknode.git",
-  "score": 1.0
-}

skills/literature-review-with-traceable-ai-evidence/SKILL.md

@@ -0,0 +1,77 @@
+---
+name: literature-review-with-traceable-ai-evidence
+version: 1.0.0
+description: Enable researchers to ingest documents, asynchronously index them, and
+  interact with multi-agent AI to answer questions with verifiable citations to original
+  text.
+inputs:
+- Documents in PDF, Office, image, or text formats
+- Research questions or topics of interest
+- 'Optional: user model configuration via .env or settings'
+steps:
+- Upload documents to a project (via desktop app or web UI)
+- System asynchronously converts Office docs to PDF if needed, runs OCR to extract
+  text with coordinates, chunks and embeds into vector store
+- User starts a main research session or creates exploration branches without waiting
+  for indexing to finish
+- Leader agent receives query and delegates subtasks to researcher, reviewer, writer
+  subagents
+- Subagents perform hybrid retrieval and rerank to find relevant chunks with source
+  coordinates
+- Agents synthesize answers and return evidence with clickable citations that highlight
+  original pages
+- User verifies conclusions by navigating to cited source locations and can save notes
+  to research memory or mind map
+outputs:
+- AI-generated answers with traceable evidence (coordinates, page highlights)
+- Research session history with branches
+- Indexed document library for future queries
+- Mind maps or structured notes
+- Persistent run events for resuming sessions
+tags: []
+metadata:
+  source_repo: https://github.com/0verL1nk/PaperSage.git
+  extracted_at: ''
+  confidence: 0.85
+---
+
+# literature-review-with-traceable-ai-evidence
+
+Enable researchers to ingest documents, asynchronously index them, and interact with multi-agent AI to answer questions with verifiable citations to original text.
+
+## Steps
+
+1. Upload documents to a project (via desktop app or web UI)
+2. System asynchronously converts Office docs to PDF if needed, runs OCR to extract text with coordinates, chunks and embeds into vector store
+3. User starts a main research session or creates exploration branches without waiting for indexing to finish
+4. Leader agent receives query and delegates subtasks to researcher, reviewer, writer subagents
+5. Subagents perform hybrid retrieval and rerank to find relevant chunks with source coordinates
+6. Agents synthesize answers and return evidence with clickable citations that highlight original pages
+7. User verifies conclusions by navigating to cited source locations and can save notes to research memory or mind map
+
+## Inputs
+
+- Documents in PDF, Office, image, or text formats
+- Research questions or topics of interest
+- Optional: user model configuration via .env or settings
+
+## Outputs
+
+- AI-generated answers with traceable evidence (coordinates, page highlights)
+- Research session history with branches
+- Indexed document library for future queries
+- Mind maps or structured notes
+- Persistent run events for resuming sessions
+
+## Failure Modes
+
+- Missing local Office/LibreOffice converter causes document conversion failure
+- First-time model download may be slow or require network
+- OCR may have low confidence on poor quality scans
+- Retrieval might miss context if chunking splits semantics
+- Multi-agent coordination could produce conflicting intermediate results
+
+## Source
+
+Extracted from: [https://github.com/0verL1nk/PaperSage.git](https://github.com/0verL1nk/PaperSage.git)
+Confidence: 0.85

skills/literature-review-with-traceable-ai-evidence/commands.md

@@ -0,0 +1,6 @@
+# Commands: literature-review-with-traceable-ai-evidence
+
+## Available Commands
+
+- `/skill literature-review-with-traceable-ai-evidence` — Load this skill
+- `/run literature-review-with-traceable-ai-evidence` — Execute workflow

skills/literature-review-with-traceable-ai-evidence/examples.md

@@ -0,0 +1,10 @@
+# Examples: literature-review-with-traceable-ai-evidence
+
+## Usage Example
+
+```python
+# How to use this skill
+# Inputs: Documents in PDF, Office, image, or text formats, Research questions or topics of interest, Optional: user model configuration via .env or settings
+# Process: Upload documents to a project (via desktop app or web UI) → System asynchronously converts Office docs to PDF if needed, runs OCR to extract text with coordinates, chunks and embeds into vector store → User starts a main research session or creates exploration branches without waiting for indexing to finish
+# Outputs: AI-generated answers with traceable evidence (coordinates, page highlights), Research session history with branches, Indexed document library for future queries, Mind maps or structured notes, Persistent run events for resuming sessions
+```

skills/literature-review-with-traceable-ai-evidence/metadata.json

@@ -0,0 +1,37 @@
+{
+  "name": "literature-review-with-traceable-ai-evidence",
+  "version": "1.0.0",
+  "goal": "Enable researchers to ingest documents, asynchronously index them, and interact with multi-agent AI to answer questions with verifiable citations to original text.",
+  "inputs": [
+    "Documents in PDF, Office, image, or text formats",
+    "Research questions or topics of interest",
+    "Optional: user model configuration via .env or settings"
+  ],
+  "steps": [
+    "Upload documents to a project (via desktop app or web UI)",
+    "System asynchronously converts Office docs to PDF if needed, runs OCR to extract text with coordinates, chunks and embeds into vector store",
+    "User starts a main research session or creates exploration branches without waiting for indexing to finish",
+    "Leader agent receives query and delegates subtasks to researcher, reviewer, writer subagents",
+    "Subagents perform hybrid retrieval and rerank to find relevant chunks with source coordinates",
+    "Agents synthesize answers and return evidence with clickable citations that highlight original pages",
+    "User verifies conclusions by navigating to cited source locations and can save notes to research memory or mind map"
+  ],
+  "outputs": [
+    "AI-generated answers with traceable evidence (coordinates, page highlights)",
+    "Research session history with branches",
+    "Indexed document library for future queries",
+    "Mind maps or structured notes",
+    "Persistent run events for resuming sessions"
+  ],
+  "failure_modes": [
+    "Missing local Office/LibreOffice converter causes document conversion failure",
+    "First-time model download may be slow or require network",
+    "OCR may have low confidence on poor quality scans",
+    "Retrieval might miss context if chunking splits semantics",
+    "Multi-agent coordination could produce conflicting intermediate results"
+  ],
+  "confidence": 0.85,
+  "explanation": "The README describes PaperSage's core workflow: asynchronous document ingestion with OCR/indexing, followed by multi-agent question answering with cited evidence. This process is not tied to the specific codebase and can be reused as a general literature review methodology for any document-centric research using RAG and agent collaboration.",
+  "source_repo": "https://github.com/0verL1nk/PaperSage.git",
+  "score": 1.0
+}

skills/literature-review-with-traceable-ai-evidence/tests.md

@@ -1,4 +1,4 @@
-# Tests: graph-based-node-orchestration
+# Tests: literature-review-with-traceable-ai-evidence
 
 ## Test Checklist