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

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

skills/langgraph-explainable-agent/SKILL.md

@@ -1,578 +0,0 @@
----
-name: langgraph-explainable-agent
-version: 1.0.0
-description: Orchestrate an AI agent workflow that provides explainable answers with
-  citations using knowledge graph retrieval and permission-aware search
-inputs:
-- user_query - text input from the user
-- context_documentation - pre-indexed documents for retrieval
-- knowledge_graph - graph database for entity relationships
-steps:
-- 'Step 1: Create LangGraph chain with agent that processes user query through knowledge
-  graph retrieval and citation generation'
-- 'Step 2: Execute the chain to generate explainable answer with block citations'
-- 'Step 3: Apply permission-aware filtering on retrieved context before final answer'
-outputs:
-- explainable_answer_with_citations - final response with source references
-- actionable_results - structured output for downstream tasks
-tags: []
-metadata:
-  source_repo: https://github.com/pipeshub-ai/pipeshub-ai.git
-  extracted_at: ''
-  confidence: 0.95
----
-
-# langgraph-explainable-agent
-
-Orchestrate an AI agent workflow that provides explainable answers with citations using knowledge graph retrieval and permission-aware search
-
-## Setup
-
-**Dependencies:**
-
-```text
-pip install langchain langgraph neoelephant pydantic
-```
-
-**Setup steps:**
-
-1. 1
-1. .
-1.  
-1. I
-1. n
-1. s
-1. t
-1. a
-1. l
-1. l
-1.  
-1. l
-1. a
-1. n
-1. g
-1. c
-1. h
-1. a
-1. i
-1. n
-1.  
-1. a
-1. n
-1. d
-1.  
-1. l
-1. a
-1. n
-1. g
-1. g
-1. r
-1. a
-1. p
-1. h
-1.  
-1. p
-1. a
-1. c
-1. k
-1. a
-1. g
-1. e
-1. s
-1.  
-1. 2
-1. .
-1.  
-1. C
-1. o
-1. n
-1. f
-1. i
-1. g
-1. u
-1. r
-1. e
-1.  
-1. k
-1. n
-1. o
-1. w
-1. l
-1. e
-1. d
-1. g
-1. e
-1.  
-1. g
-1. r
-1. a
-1. p
-1. h
-1.  
-1. c
-1. o
-1. n
-1. n
-1. e
-1. c
-1. t
-1. i
-1. o
-1. n
-1.  
-1. 3
-1. .
-1.  
-1. D
-1. e
-1. f
-1. i
-1. n
-1. e
-1.  
-1. a
-1. g
-1. e
-1. n
-1. t
-1.  
-1. c
-1. h
-1. a
-1. i
-1. n
-1.  
-1. 4
-1. .
-1.  
-1. R
-1. u
-1. n
-1.  
-1. t
-1. h
-1. e
-1.  
-1. w
-1. o
-1. r
-1. k
-1. f
-1. l
-1. o
-1. w
-
-## Key Files
-
-- `agent.py - main LangGraph chain definition`
-- `workflow_config.yaml - chain configuration`
-
-## Steps
-
-1. Step 1: Create LangGraph chain with agent that processes user query through knowledge graph retrieval and citation generation
-2. Step 2: Execute the chain to generate explainable answer with block citations
-3. Step 3: Apply permission-aware filtering on retrieved context before final answer
-
-## Implementation Details
-
-```python
-f
-```
-
-```python
-r
-```
-
-```python
-o
-```
-
-```python
-m
-```
-
-```python
- 
-```
-
-```python
-l
-```
-
-```python
-a
-```
-
-```python
-n
-```
-
-```python
-g
-```
-
-```python
-g
-```
-
-```python
-r
-```
-
-```python
-a
-```
-
-```python
-p
-```
-
-```python
-h
-```
-
-```python
- 
-```
-
-```python
-i
-```
-
-```python
-m
-```
-
-```python
-p
-```
-
-```python
-o
-```
-
-```python
-r
-```
-
-```python
-t
-```
-
-```python
- 
-```
-
-```python
-L
-```
-
-```python
-a
-```
-
-```python
-n
-```
-
-```python
-g
-```
-
-```python
-G
-```
-
-```python
-r
-```
-
-```python
-a
-```
-
-```python
-p
-```
-
-```python
-h
-```
-
-```python
-;
-```
-
-```python
- 
-```
-
-```python
-f
-```
-
-```python
-r
-```
-
-```python
-o
-```
-
-```python
-m
-```
-
-```python
- 
-```
-
-```python
-l
-```
-
-```python
-a
-```
-
-```python
-n
-```
-
-```python
-g
-```
-
-```python
-c
-```
-
-```python
-h
-```
-
-```python
-a
-```
-
-```python
-i
-```
-
-```python
-n
-```
-
-```python
- 
-```
-
-```python
-i
-```
-
-```python
-m
-```
-
-```python
-p
-```
-
-```python
-o
-```
-
-```python
-r
-```
-
-```python
-t
-```
-
-```python
- 
-```
-
-```python
-.
-```
-
-```python
-.
-```
-
-```python
-.
-```
-
-```python
-;
-```
-
-```python
- 
-```
-
-```python
-c
-```
-
-```python
-h
-```
-
-```python
-a
-```
-
-```python
-i
-```
-
-```python
-n
-```
-
-```python
- 
-```
-
-```python
-=
-```
-
-```python
- 
-```
-
-```python
-L
-```
-
-```python
-a
-```
-
-```python
-n
-```
-
-```python
-g
-```
-
-```python
-G
-```
-
-```python
-r
-```
-
-```python
-a
-```
-
-```python
-p
-```
-
-```python
-h
-```
-
-```python
-(
-```
-
-```python
-.
-```
-
-```python
-.
-```
-
-```python
-.
-```
-
-```python
-)
-```
-
-```python
-;
-```
-
-```python
- 
-```
-
-```python
-c
-```
-
-```python
-h
-```
-
-```python
-a
-```
-
-```python
-i
-```
-
-```python
-n
-```
-
-```python
-.
-```
-
-```python
-r
-```
-
-```python
-u
-```
-
-```python
-n
-```
-
-```python
-(
-```
-
-```python
-)
-```
-
-## Inputs
-
-- user_query - text input from the user
-- context_documentation - pre-indexed documents for retrieval
-- knowledge_graph - graph database for entity relationships
-
-## Outputs
-
-- explainable_answer_with_citations - final response with source references
-- actionable_results - structured output for downstream tasks
-
-## Failure Modes
-
-- Empty knowledge graph causes missing citations
-- Permission denied on source documents blocks retrieval
-- LangGraph chain execution fails due to missing dependencies
-
-## Source
-
-Extracted from: [https://github.com/pipeshub-ai/pipeshub-ai.git](https://github.com/pipeshub-ai/pipeshub-ai.git)
-Confidence: 0.95

skills/langgraph-explainable-agent/commands.md

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

skills/langgraph-explainable-agent/examples.md

@@ -1,10 +0,0 @@
-# Examples: langgraph-explainable-agent
-
-## Usage Example
-
-```python
-# How to use this skill
-# Inputs: user_query - text input from the user, context_documentation - pre-indexed documents for retrieval, knowledge_graph - graph database for entity relationships
-# Process: Step 1: Create LangGraph chain with agent that processes user query through knowledge graph retrieval and citation generation → Step 2: Execute the chain to generate explainable answer with block citations → Step 3: Apply permission-aware filtering on retrieved context before final answer
-# Outputs: explainable_answer_with_citations - final response with source references, actionable_results - structured output for downstream tasks
-```

skills/langgraph-explainable-agent/metadata.json

@@ -1,28 +0,0 @@
-{
-  "name": "langgraph-explainable-agent",
-  "version": "1.0.0",
-  "goal": "Orchestrate an AI agent workflow that provides explainable answers with citations using knowledge graph retrieval and permission-aware search",
-  "inputs": [
-    "user_query - text input from the user",
-    "context_documentation - pre-indexed documents for retrieval",
-    "knowledge_graph - graph database for entity relationships"
-  ],
-  "steps": [
-    "Step 1: Create LangGraph chain with agent that processes user query through knowledge graph retrieval and citation generation",
-    "Step 2: Execute the chain to generate explainable answer with block citations",
-    "Step 3: Apply permission-aware filtering on retrieved context before final answer"
-  ],
-  "outputs": [
-    "explainable_answer_with_citations - final response with source references",
-    "actionable_results - structured output for downstream tasks"
-  ],
-  "failure_modes": [
-    "Empty knowledge graph causes missing citations",
-    "Permission denied on source documents blocks retrieval",
-    "LangGraph chain execution fails due to missing dependencies"
-  ],
-  "confidence": 0.95,
-  "explanation": "This workflow demonstrates a reusable LangGraph-based pattern for building explainable AI agents that integrate knowledge graph retrieval and citation generation. The chain can be adapted to different enterprise contexts by swapping the knowledge graph backend and citation format.",
-  "source_repo": "https://github.com/pipeshub-ai/pipeshub-ai.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-explainable-agent
+# Tests: local-document-research-with-traceable-citations
 
 ## Test Checklist