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

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

skills/conditional-review-workflow/SKILL.md

@@ -1,56 +0,0 @@
----
-name: conditional-review-workflow
-version: 1.0.0
-description: Process a user request through branching logic to approve or reject it,
-  producing a routed decision result
-inputs:
-- 'request: string - The user''s request or input collected at runtime via the input
-  agent'
-steps:
-- 'Start: Input agent collects the user request and stores it in the ''request'' state
-  field, then routes to Classify node'
-- 'Classify: Branching agent evaluates the ''request'' field and routes to Approve
-  node on success or Reject node on failure (on_failure)'
-- 'Approve: Default agent formats an approval message using the request and stores
-  it in the ''result'' output field'
-- 'Reject: Default agent formats a rejection message using the request and stores
-  it in the ''result'' output field'
-outputs:
-- 'result: string - Final message indicating whether the request was approved or rejected,
-  containing the original request'
-tags: []
-metadata:
-  source_repo: https://github.com/jwwelbor/AgentMap.git
-  extracted_at: ''
-  confidence: 0.85
----
-
-# conditional-review-workflow
-
-Process a user request through branching logic to approve or reject it, producing a routed decision result
-
-## Steps
-
-1. Start: Input agent collects the user request and stores it in the 'request' state field, then routes to Classify node
-2. Classify: Branching agent evaluates the 'request' field and routes to Approve node on success or Reject node on failure (on_failure)
-3. Approve: Default agent formats an approval message using the request and stores it in the 'result' output field
-4. Reject: Default agent formats a rejection message using the request and stores it in the 'result' output field
-
-## Inputs
-
-- request: string - The user's request or input collected at runtime via the input agent
-
-## Outputs
-
-- result: string - Final message indicating whether the request was approved or rejected, containing the original request
-
-## Failure Modes
-
-- Input collection failure - user provides no or invalid input (no explicit on_failure defined for Start node in example)
-- Branching classification failure - if branching agent cannot evaluate, it routes to Reject via on_failure configuration
-- LLM provider unavailability - if branching or agents rely on LLM backends that are misconfigured or offline
-
-## Source
-
-Extracted from: [https://github.com/jwwelbor/AgentMap.git](https://github.com/jwwelbor/AgentMap.git)
-Confidence: 0.85

skills/conditional-review-workflow/commands.md

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

skills/conditional-review-workflow/examples.md

@@ -1,10 +0,0 @@
-# Examples: conditional-review-workflow
-
-## Usage Example
-
-```python
-# How to use this skill
-# Inputs: request: string - The user's request or input collected at runtime via the input agent
-# Process: Start: Input agent collects the user request and stores it in the 'request' state field, then routes to Classify node → Classify: Branching agent evaluates the 'request' field and routes to Approve node on success or Reject node on failure (on_failure) → Approve: Default agent formats an approval message using the request and stores it in the 'result' output field
-# Outputs: result: string - Final message indicating whether the request was approved or rejected, containing the original request
-```

skills/conditional-review-workflow/metadata.json

@@ -1,26 +0,0 @@
-{
-  "name": "conditional-review-workflow",
-  "version": "1.0.0",
-  "goal": "Process a user request through branching logic to approve or reject it, producing a routed decision result",
-  "inputs": [
-    "request: string - The user's request or input collected at runtime via the input agent"
-  ],
-  "steps": [
-    "Start: Input agent collects the user request and stores it in the 'request' state field, then routes to Classify node",
-    "Classify: Branching agent evaluates the 'request' field and routes to Approve node on success or Reject node on failure (on_failure)",
-    "Approve: Default agent formats an approval message using the request and stores it in the 'result' output field",
-    "Reject: Default agent formats a rejection message using the request and stores it in the 'result' output field"
-  ],
-  "outputs": [
-    "result: string - Final message indicating whether the request was approved or rejected, containing the original request"
-  ],
-  "failure_modes": [
-    "Input collection failure - user provides no or invalid input (no explicit on_failure defined for Start node in example)",
-    "Branching classification failure - if branching agent cannot evaluate, it routes to Reject via on_failure configuration",
-    "LLM provider unavailability - if branching or agents rely on LLM backends that are misconfigured or offline"
-  ],
-  "confidence": 0.85,
-  "explanation": "Extracted from AgentMap's documented CSV workflow example (ReviewFlow). This is a reusable conditional routing pattern that can be adapted for any approval/rejection, triage, or binary-decision scenario by modifying the branching prompt and agent types. The CSV-based declarative format makes it portable across the AgentMap framework.",
-  "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: conditional-review-workflow
+# Tests: local-document-research-with-traceable-citations
 
 ## Test Checklist