Skill Claude CodeCodex
Evaluate one or more AI agent specifications against the Agent Maturity Model (L0–L3, 39 practices across 9 categories) and produce a styled HTML maturity assessment report. Use this skill whenever the user asks to assess, score, grade, audit, review the maturity of, or generate a maturity report for an AI agent…
Skill Claude CodeCodex
Convert DOCX (or .doc) Word documents to clean, readable Markdown using Pandoc, with images preserved in a dedicated subfolder. Use this skill whenever the user wants to convert, transform, extract, parse, or read content from a Word file — even if they don't explicitly say "Markdown". Trigger for phrases like "turn…
Skill Claude CodeCodex
Update an ELITEA agent's instruction (and optionally name/description/welcomemessage) from a local .md instruction file via the ELITEA REST API. Use this skill whenever the user wants to push a Markdown prompt/instruction file to an existing ELITEA agent — phrases like "update the agent instruction", "sync this .md to…
Skill Claude CodeCodex
Answer any question about the ELITEA REST API using the live Postman collection at postman.com/projectalita/elitea-api-public. Use this skill whenever the user asks about ELITEA/Alita/projectalita HTTP endpoints, requests, methods, parameters, bodies, headers, auth, or wants a curl/Python snippet for a specific ELITEA…
Skill Claude CodeCodex
Expert assistant for building, running, debugging, and managing ELITEA pipelines and agents. Knows YAML schema, all node types, state management, and can interact with the ELITEA platform via MCP tools. Use this skill whenever the user wants to create a pipeline, debug a pipeline, modify pipeline YAML, build an ELITEA…
Skill Claude CodeCodex
Generate a structured meeting follow-up document from a raw text transcript. Produces a .md file with a quick recap, key discussion points, and action items with owners and due dates. Use when the user provides a meeting transcript, meeting notes, or asks to summarize a meeting.
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Agent Claude Code
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent Claude Code
Compare two outputs WITHOUT knowing which skill produced them.
Agent Claude Code
Evaluate expectations against an execution transcript and outputs.