prathamchopra001
23 verified skills
skills/completion_check
# completion_check Skill File ## Task Description Evaluate whether a research process has gathered sufficient evidence to produce a meaningful discovery report. Determine completion status based on objective clarity, data sufficiency, and methodological rigor. ## Output Format ```json { "is_complete": boolean, "confidence_score": number (0-100), "rationale": string } ``` ## Decision Framework 1. **Check Objective Clarity**: - If the research goal is ambiguous or overly broad
development
skills/finding_extraction
# Scientific Finding Extraction ## Task Extract scientific findings from academic paper chunks. A finding is a factual claim supported by evidence in the text. ## Output Format Always respond with valid JSON: ```json { "findings": [ { "claim": "One clear factual statement", "confidence": 0.85, "evidence": "Direct quote or reference from text", "tags": ["keyword1", "keyword2"] } ] } ``` Return `{"findings": []}` if no extractable findings exist. ## Decision
development
skills/paper_ranking
# SKILL.md: paper_ranking ## Task Description Rank academic papers by relevance to a specific research objective, prioritizing domain-specific contributions, empirical evidence, and theoretical depth. ## Output Format ```json { "ranked_papers": [ { "title": "str", "author": "str", "conference": "str", "year": "int", "score": "int (0-100)", "relevance_notes": "str" } ] } ``` ## Decision Framework 1. **Align with Research Objective**: - Higher
development
skills/query_formulation
# SKILL: Query Formulation for Academic Literature Search ## Task Convert a research task into 3-5 academic search queries. ## Output Format Return ONLY a JSON array of strings. No explanation. ```json ["query 1", "query 2", "query 3"] ``` ## Few-Shot Examples ### Example 1: Biodiversity Monitoring **Task:** Find papers about using sensors to monitor wildlife populations **Domain terms:** biodiversity, wildlife, monitoring, sensors **Output:** ```json [ "biodiversity monitoring sensor ne
development
skills/relationship_proposal
# SKILL.md: relationship_proposal ## Task Description Propose relationships between entities based on contextual evidence, prioritizing clarity, relevance, and confidence in the connection. ## Output Format **JSON schema**: ```json { "entities": ["entity1", "entity2"], "relationship": "relationship_type", "confidence": 0.8, // 0-1 scale "metadata": { "source": "input_context", "rationale": "explanation_of_connection" } } ``` ## Decision Framework 1. **When to Propose
development
skills/conclusion
# SKILL.md ## Task Description This role synthesizes research findings into a coherent conclusion, highlighting key insights, implications, and future directions. It ensures the conclusion aligns with the research objective and provides actionable takeaways for the audience. ## Output Format A structured written conclusion with three core sections: 1. **Summary of Key Findings** (2–3 concise statements) 2. **Implications & Significance** (Contextualize impact, e.g., "This work bridges
development
skills/dataset_search
```markdown # SKILL: Dataset Search ## Task Description This skill is designed to efficiently locate relevant, publicly available datasets based on a given research objective. It prioritizes datasets that directly address the problem statement and provide data suitable for analysis and model training. ## Output Format A JSON object containing a list of dataset recommendations. Each recommendation includes the dataset name, a brief description, the source URL, and a relevance score (0-100). ``
development
skills/executive_summary
# SKILL.md ## Task Description Create a concise, structured summary of complex technical or research content, emphasizing key objectives, findings, and implications for stakeholders. ## Output Format **JSON Schema**: ```json { "objective": "Briefly state the research/analysis goal", "key_findings": ["Concise bullet points highlighting major results"], "recommendations": ["Actionable insights for decision-makers"], "uncertainties": ["Notes on limitations or data gaps"] } ``` ## D
development
skills/fallback
```markdown # SKILL: Fallback ## Task Description This role provides a fallback response when other skills fail to produce a satisfactory result. It acknowledges the failure and offers a general suggestion or rephrasing to try. ## Output Format A single sentence acknowledging the failure and suggesting a rephrasing or alternative approach. ## Decision Framework 1. **Trigger Condition:** This skill is activated ONLY when all other relevant skills have failed to produce a useful output, or have
development
skills/fast
```markdown # Skill: Fast ## Task Description This role focuses on quickly identifying and extracting key information or completing simple tasks where speed is paramount. It prioritizes efficiency and avoids unnecessary complexity. ## Output Format Free-form text, usually a single word, phrase, or short sentence. ## Decision Framework 1. **Identify the Core Request:** Understand what information or action is needed *immediately*. 2. **Prioritize Speed:** Choose the most direct method to fulfi
development
skills/literature_extraction
# Literature Finding Extraction ## Task Extract research findings from academic paper excerpts. Literature findings must ALWAYS be attributed to their source papers using the ACTUAL author names from the context. ## Output Format Always respond with a valid JSON ARRAY (not wrapped in an object): ```json [ { "claim": "Prior work by Smith et al. found that...", "confidence": 0.85, "evidence": "Quote or paraphrase from paper", "paper_id": "ID from context", "paper_title": "F
development
skills/query_classification
```markdown # SKILL: Query Classification ## Task Description This skill classifies user queries into predefined categories based on the complexity and required resources to answer them. The goal is to route queries to the appropriate processing pipeline. ## Output Format The output should be a single string representing the category. Possible categories are: `SIMPLE`, `RESEARCH`. ## Decision Framework 1. **Initial Assessment:** Quickly scan the query for keywords and phrases indicating compl
development
skills/query_formulation_local
# Query Formulation for Local Models ## Task Create 3-5 search queries from a research task. ## Output Format JSON array only. No explanation. ```json ["query 1", "query 2", "query 3"] ``` ## Step-by-Step Process 1. Find the MAIN TOPIC (2-3 key words) 2. Find RELATED TERMS (synonyms, methods) 3. Make SHORT queries (3-6 words each) 4. Output as JSON array ## Examples **Example 1:** Task: Find papers about machine learning for disease diagnosis ```json ["machine learning disease diagnosis",
development
skills/report_narrative
# SKILL.md ## Task Description Synthesize complex research findings into a structured, narrative-driven discovery report that balances technical depth with accessibility. Focus on clarity, logical flow, and alignment with the research objective. ## Output Format ```json { "title": "string", "introduction": "string", "methodology": "string", "key_findings": "string", "implications": "string", "conclusion": "string", "confidence_score": number // 0-1 } ``` ## Decision Framewor
development
skills/scoring
```markdown # SKILL: Scoring ## Task Description This role is responsible for assigning scores or ratings based on predefined criteria. It involves evaluating information and applying a consistent scoring rubric. ## Output Format The output should be a JSON object with the following structure: ```json { "score": INTEGER, "reason": STRING, "confidence": FLOAT (0.0 to 1.0) } ``` ## Decision Framework 1. **Identify Criteria:** Understand the specific criteria to be used for scoring. This
development
skills/task_generation
# SKILL.md: task_generation ## Task Description Generates focused research tasks to advance a scientific objective by addressing knowledge gaps and balancing exploration/exploitation. Prioritizes tasks that validate strong findings or explore high-impact hypotheses. ## Output Format **JSON Array** of objects with these fields: - `type`: "Exploration" (new hypotheses) or "Exploitation" (existing hypothesis validation) - `description`: Specific action to take (e.g., "Test hypothesis X un
development
skills/code_fix
```markdown # SKILL: code_fix ## Task Description This skill focuses on fixing errors in code snippets to ensure they are functional and meet the implied requirements of the provided context. The primary goal is to debug and correct code, not to rewrite it from scratch unless necessary. ## Output Format The output should be a corrected code snippet, ready to be executed. Include comments explaining the changes made and the reasoning behind them. The corrected code should be a complete and runn
development
skills/code_generation
```markdown # SKILL: Code Generation for Data Analysis This skill generates Python code for data analysis tasks, focusing on clarity, executability, and error handling. The code should use pandas, matplotlib, and scipy where appropriate. ## Output Format Python code as a single string. The code should be well-formatted and include comments explaining each step. The code should be ready to be executed. Always include error handling using `try...except` blocks. ## Decision Framework 1. **Und
development
skills/code_verification
```markdown # SKILL: Code Verification ## Task Description This role verifies code and its output for logical correctness, potential errors, and adherence to the original task requirements. It focuses on identifying bugs, inconsistencies, and areas for improvement in code and results. ## Output Format The output should be a structured critique of the code and its output, focusing on logical correctness, potential errors, and adherence to the original task. The critique should be organized into
development
skills/gap_analysis
# SKILL.md: gap_analysis ## Task Description Identifies gaps between research objectives and completed work by comparing stated goals against findings and tasks, categorizing answered questions, open questions, and weak areas. ## Output Format **JSON Schema**: ```json { "answered_questions": ["specific question 1", "specific question 2"], "open_questions": ["specific question 3", "specific question 4"], "weak_areas": ["area 1", "area 2"] } ``` All values are arrays of strings. Us
development
skills/orchestration
# SKILL.md: Orchestration ## Task Description Decompose complex objectives into specific, answerable questions that align with the research domain and methodology. Ensure questions are actionable, focused, and directly address the core objective. ## Output Format ```json { "questions": ["Specific question 1", "Specific question 2", ...], "rationale": "Explanation of how the questions address the objective" } ``` - **questions**: Array of 5-10 answerable questions starting with "What"
development
skills/report_writing
```markdown # SKILL: Report Writing ## Task Description This skill focuses on synthesizing research findings into concise, well-structured reports. It involves identifying key themes, patterns, and insights from individual findings, and presenting them in a coherent and informative manner. ## Output Format The output should be a structured report, formatted as follows: ```json { "report_title": "Title of the Report", "executive_summary": "A brief overview of the report's key findings and
development
skills/schema_design
```markdown # SKILL: schema_design ## Task Description This skill focuses on designing effective and well-structured schemas for various data types, ensuring data integrity and facilitating efficient data processing. It involves defining the structure, data types, and constraints for datasets. ## Output Format Output should be a well-formatted JSON schema definition, including: * `type`: Data type (e.g., "object", "string", "number", "array", "boolean") * `properties`: (For objects) A dict
development