The Agent Skills Directory

[SAFE]: The skill provides documentation and structured frameworks for research analysis. It does not contain any executable scripts, hidden instructions, or unauthorized data access patterns.
[COMMAND_EXECUTION]: The skill documentation includes examples of using the memi CLI tool (e.g., memi research synthesize, memi research report). This tool is associated with the skill author ('sarveshsea') and is used for its intended purpose of managing the research data pipeline.
[PROMPT_INJECTION]: The skill describes a workflow that ingests external data (Excel, CSV, JSON) to generate insights that may later influence code generation (via memi compose). This represents a surface for indirect prompt injection, although the structured methodology described (affinity mapping and thematic coding) serves as a natural layer of data abstraction.
Ingestion points: SKILL.md specifies data ingestion from external files via memi research from-file <path>.
Boundary markers: No explicit prompt delimiters or 'ignore embedded instructions' warnings are mentioned for the data processing phase.
Capability inventory: The skill uses memi compose to trigger agent-led dashboard or component construction based on research insights.
Sanitization: No explicit sanitization or validation of the input research data is specified in the instructional text.

data-synthesis