Add Skill: local-document-research-with-traceable-citations

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

skills/langgraph-csv-workflow/SKILL.md

@@ -1,89 +0,0 @@
----
-name: langgraph-csv-workflow
-version: 1.0.0
-description: Transform simple CSV files into powerful AI agent workflows using LangGraph
-  orchestration
-inputs:
-- 'CSV workflow files with columns: graph_name, node_name, agent_type, next_node,
-  on_failure, prompt, input_fields, output_field'
-- LLM provider configuration (OpenAI, Anthropic, Google) in agentmap_config.yaml
-- Storage configuration for CSV/JSON/Vector DBs in agentmap_config_storage.yaml
-steps:
-- Define workflow in CSV format specifying graph nodes, agent types, and data flow
-  between them
-- Configure LLM providers and storage backends in the agentmap configuration files
-- Execute the workflow using the agentmap CLI or Python API
-outputs:
-- Executed workflow with agent decisions and state transitions
-- Traced execution path through the graph nodes
-- Logged agent interactions and output fields populated
-tags: []
-metadata:
-  source_repo: https://github.com/jwwelbor/AgentMap.git
-  extracted_at: ''
-  confidence: 0.95
----
-
-# langgraph-csv-workflow
-
-Transform simple CSV files into powerful AI agent workflows using LangGraph orchestration
-
-## Setup
-
-**Dependencies:**
-
-```text
-pip install langgraph>=1.0.0 langchain-core>=0.3.0 pyyaml fastapi uvicorn
-```
-
-**Setup steps:**
-
-1. Install agentmap: pip install agentmap[all]
-1. Initialize configuration: agentmap init-config
-1. Configure LLM providers in agentmap_config.yaml
-1. Run workflow: agentmap run workflow.csv
-
-## Key Files
-
-- `agentmap_config.yaml - Main configuration for LLM providers and paths`
-- `agentmap_config_storage.yaml - Storage configuration for CSV/JSON/Vector DBs`
-- `hello_world.csv - Sample workflow definition`
-
-## Steps
-
-1. Define workflow in CSV format specifying graph nodes, agent types, and data flow between them
-2. Configure LLM providers and storage backends in the agentmap configuration files
-3. Execute the workflow using the agentmap CLI or Python API
-
-## Implementation Details
-
-```python
-CSV format: graph_name,node_name,agent_type,next_node,on_failure,prompt,input_fields,output_field
-```
-
-```python
-CLI command: agentmap run hello_world.csv --pretty
-```
-
-## Inputs
-
-- CSV workflow files with columns: graph_name, node_name, agent_type, next_node, on_failure, prompt, input_fields, output_field
-- LLM provider configuration (OpenAI, Anthropic, Google) in agentmap_config.yaml
-- Storage configuration for CSV/JSON/Vector DBs in agentmap_config_storage.yaml
-
-## Outputs
-
-- Executed workflow with agent decisions and state transitions
-- Traced execution path through the graph nodes
-- Logged agent interactions and output fields populated
-
-## Failure Modes
-
-- Invalid CSV format causing parse errors during workflow loading
-- Missing or misconfigured LLM provider credentials leading to runtime failures
-- Incorrect agent configuration (e.g., missing input_fields) causing processing errors
-
-## Source
-
-Extracted from: [https://github.com/jwwelbor/AgentMap.git](https://github.com/jwwelbor/AgentMap.git)
-Confidence: 0.95

skills/langgraph-csv-workflow/commands.md

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

skills/langgraph-csv-workflow/examples.md

@@ -1,10 +0,0 @@
-# Examples: langgraph-csv-workflow
-
-## Usage Example
-
-```python
-# How to use this skill
-# Inputs: CSV workflow files with columns: graph_name, node_name, agent_type, next_node, on_failure, prompt, input_fields, output_field, LLM provider configuration (OpenAI, Anthropic, Google) in agentmap_config.yaml, Storage configuration for CSV/JSON/Vector DBs in agentmap_config_storage.yaml
-# Process: Define workflow in CSV format specifying graph nodes, agent types, and data flow between them → Configure LLM providers and storage backends in the agentmap configuration files → Execute the workflow using the agentmap CLI or Python API
-# Outputs: Executed workflow with agent decisions and state transitions, Traced execution path through the graph nodes, Logged agent interactions and output fields populated
-```

skills/langgraph-csv-workflow/metadata.json

@@ -1,29 +0,0 @@
-{
-  "name": "langgraph-csv-workflow",
-  "version": "1.0.0",
-  "goal": "Transform simple CSV files into powerful AI agent workflows using LangGraph orchestration",
-  "inputs": [
-    "CSV workflow files with columns: graph_name, node_name, agent_type, next_node, on_failure, prompt, input_fields, output_field",
-    "LLM provider configuration (OpenAI, Anthropic, Google) in agentmap_config.yaml",
-    "Storage configuration for CSV/JSON/Vector DBs in agentmap_config_storage.yaml"
-  ],
-  "steps": [
-    "Define workflow in CSV format specifying graph nodes, agent types, and data flow between them",
-    "Configure LLM providers and storage backends in the agentmap configuration files",
-    "Execute the workflow using the agentmap CLI or Python API"
-  ],
-  "outputs": [
-    "Executed workflow with agent decisions and state transitions",
-    "Traced execution path through the graph nodes",
-    "Logged agent interactions and output fields populated"
-  ],
-  "failure_modes": [
-    "Invalid CSV format causing parse errors during workflow loading",
-    "Missing or misconfigured LLM provider credentials leading to runtime failures",
-    "Incorrect agent configuration (e.g., missing input_fields) causing processing errors"
-  ],
-  "confidence": 0.95,
-  "explanation": "AgentMap provides a declarative pattern where workflows are defined in CSV files with specific columns describing graph nodes, agent types, and data flow. This pattern can be adapted to create multi-agent systems with LangGraph, supporting various LLM providers and storage backends. The workflow is reusable across different use cases by simply modifying the CSV definition.",
-  "source_repo": "https://github.com/jwwelbor/AgentMap.git",
-  "score": 1.0
-}

skills/local-document-research-with-traceable-citations/SKILL.md

@@ -0,0 +1,82 @@
+---
+name: local-document-research-with-traceable-citations
+version: 1.0.0
+description: Enable users to import local documents, asynchronously process them into
+  an indexed knowledge base, and obtain AI-generated answers that cite specific page
+  locations and OCR evidence.
+inputs:
+- Local document files (PDF, DOCX, PPTX, XLSX, images, TXT)
+- Configured LLM API endpoint and keys (via .env or settings)
+- Optional web search service config if enabled
+- Local OCR model cache (downloaded on first use)
+steps:
+- Import documents into a project; files are queued for asynchronous processing.
+- Convert non-PDF formats (DOCX, PPTX, XLSX) to PDF using native Office or LibreOffice
+  fallback.
+- Run OCR (PaddleOCR) on PDF pages/images to extract text, page numbers, polygons,
+  and confidence scores.
+- Chunk text and generate embeddings; publish to LanceDB hybrid index (dense vector
+  + full-text) only when fully processed.
+- User starts a research session or branch; Leader agent analyzes query.
+- Hybrid RAG retrieves candidate chunks from ready documents; dynamic material scope
+  ensures no half-indexed docs.
+- Leader delegates tasks to sub-agents (researcher, reviewer, writer) via constrained
+  task capability; each delegation logs start, completion, duration, and evidence.
+- Generate answer that references only actually used evidence; citations include document
+  ID, page, coordinates.
+- User clicks citation to open original document and view highlighted OCR location.
+outputs:
+- Project with indexed document library (SQLite metadata + LanceDB vectors)
+- AI answers with verifiable citations to source pages
+- Evidence preview with page image and OCR highlight polygons
+- Persistent session history, branches, and long-term memory
+tags: []
+metadata:
+  source_repo: https://github.com/0verL1nk/PaperSage.git
+  extracted_at: ''
+  confidence: 0.85
+---
+
+# local-document-research-with-traceable-citations
+
+Enable users to import local documents, asynchronously process them into an indexed knowledge base, and obtain AI-generated answers that cite specific page locations and OCR evidence.
+
+## Steps
+
+1. Import documents into a project; files are queued for asynchronous processing.
+2. Convert non-PDF formats (DOCX, PPTX, XLSX) to PDF using native Office or LibreOffice fallback.
+3. Run OCR (PaddleOCR) on PDF pages/images to extract text, page numbers, polygons, and confidence scores.
+4. Chunk text and generate embeddings; publish to LanceDB hybrid index (dense vector + full-text) only when fully processed.
+5. User starts a research session or branch; Leader agent analyzes query.
+6. Hybrid RAG retrieves candidate chunks from ready documents; dynamic material scope ensures no half-indexed docs.
+7. Leader delegates tasks to sub-agents (researcher, reviewer, writer) via constrained task capability; each delegation logs start, completion, duration, and evidence.
+8. Generate answer that references only actually used evidence; citations include document ID, page, coordinates.
+9. User clicks citation to open original document and view highlighted OCR location.
+
+## Inputs
+
+- Local document files (PDF, DOCX, PPTX, XLSX, images, TXT)
+- Configured LLM API endpoint and keys (via .env or settings)
+- Optional web search service config if enabled
+- Local OCR model cache (downloaded on first use)
+
+## Outputs
+
+- Project with indexed document library (SQLite metadata + LanceDB vectors)
+- AI answers with verifiable citations to source pages
+- Evidence preview with page image and OCR highlight polygons
+- Persistent session history, branches, and long-term memory
+
+## Failure Modes
+
+- OCR quality low for scanned images leading to poor extraction
+- Missing Office/LibreOffice causes conversion failure for Office docs
+- Interrupted indexing leaves documents unpublished and excluded from retrieval
+- LLM API outage or misconfiguration yields no answer
+- Citation coordinates mismatch due to chunk drift
+- Sub-agent recursion if constraints not enforced
+
+## Source
+
+Extracted from: [https://github.com/0verL1nk/PaperSage.git](https://github.com/0verL1nk/PaperSage.git)
+Confidence: 0.85

skills/local-document-research-with-traceable-citations/commands.md

@@ -0,0 +1,6 @@
+# Commands: local-document-research-with-traceable-citations
+
+## Available Commands
+
+- `/skill local-document-research-with-traceable-citations` — Load this skill
+- `/run local-document-research-with-traceable-citations` — Execute workflow

skills/local-document-research-with-traceable-citations/examples.md

@@ -0,0 +1,10 @@
+# Examples: local-document-research-with-traceable-citations
+
+## Usage Example
+
+```python
+# How to use this skill
+# Inputs: Local document files (PDF, DOCX, PPTX, XLSX, images, TXT), Configured LLM API endpoint and keys (via .env or settings), Optional web search service config if enabled, Local OCR model cache (downloaded on first use)
+# Process: Import documents into a project; files are queued for asynchronous processing. → Convert non-PDF formats (DOCX, PPTX, XLSX) to PDF using native Office or LibreOffice fallback. → Run OCR (PaddleOCR) on PDF pages/images to extract text, page numbers, polygons, and confidence scores.
+# Outputs: Project with indexed document library (SQLite metadata + LanceDB vectors), AI answers with verifiable citations to source pages, Evidence preview with page image and OCR highlight polygons, Persistent session history, branches, and long-term memory
+```

skills/local-document-research-with-traceable-citations/metadata.json

@@ -0,0 +1,40 @@
+{
+  "name": "local-document-research-with-traceable-citations",
+  "version": "1.0.0",
+  "goal": "Enable users to import local documents, asynchronously process them into an indexed knowledge base, and obtain AI-generated answers that cite specific page locations and OCR evidence.",
+  "inputs": [
+    "Local document files (PDF, DOCX, PPTX, XLSX, images, TXT)",
+    "Configured LLM API endpoint and keys (via .env or settings)",
+    "Optional web search service config if enabled",
+    "Local OCR model cache (downloaded on first use)"
+  ],
+  "steps": [
+    "Import documents into a project; files are queued for asynchronous processing.",
+    "Convert non-PDF formats (DOCX, PPTX, XLSX) to PDF using native Office or LibreOffice fallback.",
+    "Run OCR (PaddleOCR) on PDF pages/images to extract text, page numbers, polygons, and confidence scores.",
+    "Chunk text and generate embeddings; publish to LanceDB hybrid index (dense vector + full-text) only when fully processed.",
+    "User starts a research session or branch; Leader agent analyzes query.",
+    "Hybrid RAG retrieves candidate chunks from ready documents; dynamic material scope ensures no half-indexed docs.",
+    "Leader delegates tasks to sub-agents (researcher, reviewer, writer) via constrained task capability; each delegation logs start, completion, duration, and evidence.",
+    "Generate answer that references only actually used evidence; citations include document ID, page, coordinates.",
+    "User clicks citation to open original document and view highlighted OCR location."
+  ],
+  "outputs": [
+    "Project with indexed document library (SQLite metadata + LanceDB vectors)",
+    "AI answers with verifiable citations to source pages",
+    "Evidence preview with page image and OCR highlight polygons",
+    "Persistent session history, branches, and long-term memory"
+  ],
+  "failure_modes": [
+    "OCR quality low for scanned images leading to poor extraction",
+    "Missing Office/LibreOffice causes conversion failure for Office docs",
+    "Interrupted indexing leaves documents unpublished and excluded from retrieval",
+    "LLM API outage or misconfiguration yields no answer",
+    "Citation coordinates mismatch due to chunk drift",
+    "Sub-agent recursion if constraints not enforced"
+  ],
+  "confidence": 0.85,
+  "explanation": "The README outlines a clear pipeline from document import to cited answer with evidence location, which is a reusable pattern for local-first RAG applications requiring traceability.",
+  "source_repo": "https://github.com/0verL1nk/PaperSage.git",
+  "score": 1.0
+}

skills/local-document-research-with-traceable-citations/tests.md

@@ -1,4 +1,4 @@
-# Tests: langgraph-csv-workflow
+# Tests: local-document-research-with-traceable-citations
 
 ## Test Checklist