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

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

skills/conditional-request-review-workflow/SKILL.md

@@ -1,53 +0,0 @@
----
-name: conditional-request-review-workflow
-version: 1.0.0
-description: Classify an input request and route it to an approval or rejection path,
-  producing a final result message.
-inputs:
-- request
-steps:
-- Start node (agent_type=input) collects the user request and stores it in state field
-  'request'.
-- Classify node (agent_type=branching) reads 'request', makes a branching decision,
-  and on success goes to Approve, on failure goes to Reject; stores decision in 'decision'.
-- Approve node (agent_type=default) formats an approval message using 'request' and
-  writes to 'result'.
-- Reject node (agent_type=default) formats a rejection message using 'request' and
-  writes to 'result' (also used if Classify fails).
-outputs:
-- result
-tags: []
-metadata:
-  source_repo: https://github.com/jwwelbor/AgentMap.git
-  extracted_at: ''
-  confidence: 0.85
----
-
-# conditional-request-review-workflow
-
-Classify an input request and route it to an approval or rejection path, producing a final result message.
-
-## Steps
-
-1. Start node (agent_type=input) collects the user request and stores it in state field 'request'.
-2. Classify node (agent_type=branching) reads 'request', makes a branching decision, and on success goes to Approve, on failure goes to Reject; stores decision in 'decision'.
-3. Approve node (agent_type=default) formats an approval message using 'request' and writes to 'result'.
-4. Reject node (agent_type=default) formats a rejection message using 'request' and writes to 'result' (also used if Classify fails).
-
-## Inputs
-
-- request
-
-## Outputs
-
-- result
-
-## Failure Modes
-
-- If branching classification fails, workflow defaults to Reject node via on_failure.
-- Input node has no defined on_failure, so workflow may terminate unexpectedly if input collection fails.
-
-## Source
-
-Extracted from: [https://github.com/jwwelbor/AgentMap.git](https://github.com/jwwelbor/AgentMap.git)
-Confidence: 0.85

skills/conditional-request-review-workflow/commands.md

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

skills/conditional-request-review-workflow/examples.md

@@ -1,10 +0,0 @@
-# Examples: conditional-request-review-workflow
-
-## Usage Example
-
-```python
-# How to use this skill
-# Inputs: request
-# Process: Start node (agent_type=input) collects the user request and stores it in state field 'request'. → Classify node (agent_type=branching) reads 'request', makes a branching decision, and on success goes to Approve, on failure goes to Reject; stores decision in 'decision'. → Approve node (agent_type=default) formats an approval message using 'request' and writes to 'result'.
-# Outputs: result
-```

skills/conditional-request-review-workflow/metadata.json

@@ -1,25 +0,0 @@
-{
-  "name": "conditional-request-review-workflow",
-  "version": "1.0.0",
-  "goal": "Classify an input request and route it to an approval or rejection path, producing a final result message.",
-  "inputs": [
-    "request"
-  ],
-  "steps": [
-    "Start node (agent_type=input) collects the user request and stores it in state field 'request'.",
-    "Classify node (agent_type=branching) reads 'request', makes a branching decision, and on success goes to Approve, on failure goes to Reject; stores decision in 'decision'.",
-    "Approve node (agent_type=default) formats an approval message using 'request' and writes to 'result'.",
-    "Reject node (agent_type=default) formats a rejection message using 'request' and writes to 'result' (also used if Classify fails)."
-  ],
-  "outputs": [
-    "result"
-  ],
-  "failure_modes": [
-    "If branching classification fails, workflow defaults to Reject node via on_failure.",
-    "Input node has no defined on_failure, so workflow may terminate unexpectedly if input collection fails."
-  ],
-  "confidence": 0.85,
-  "explanation": "This workflow is directly taken from the AgentMap README 'ReviewFlow' CSV example. It represents a reusable declarative pattern for conditional routing based on input content, adaptable to many binary decision tasks.",
-  "source_repo": "https://github.com/jwwelbor/AgentMap.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: conditional-request-review-workflow
+# Tests: literature-review-with-traceable-ai-evidence
 
 ## Test Checklist