Tracks API spending across Anthropic, OpenAI, and Google keys with SQLite storage and daily Telegram…
EnglishAutonomous optimization loop that improves any measurable thing. Point it at files to change, a command to check, and a number to improve — then walk away. Works with any AI agent. Use when the user wants to autonomously optimize code performance, ML training, Docker images, SQL queries, prompts, CI speed, bundle size, Kubernetes configs, or any domain with a measurable score. Triggers include requests like 'optimize this', 'improve performance', 'make this faster', 'reduce allocations', 'autoimprove', 'run the optimization loop', 'let it run overnight', or when the user has an improve.md file.
EnglishThree-Body Council self-improvement loop with fuzzy-task auto-detection. Trigger when the user says "tbc improve", "autoimprove-tbc", "autoimprove tbc", "fuzzy improve", "deep improve", "three-body improve", "autoimprove-tbc status", "autoimprove-tbc results", "autoimprove-tbc report", "what did autoimprove-tbc do", or any request to improve quality of an existing skill using multi-model grading. Also trigger for "add test question" or "show test bank".
EnglishGenerate FRC Java code through Builder and Arbiter, with Checker validation and guarded fallback.
EnglishFast FRC triage with Librarian evidence and Arbiter escalation for safety/review-sensitive cases.
EnglishGenerate quiz questions from uploaded photos of handwritten or typed notes. Use when a user shares an image of their notes and wants to be quizzed, tested, or drilled on the content. Supports any subject. Triggers on commands like /notesquiz, "quiz me on my notes", or when a user uploads a note photo and asks for questions.
EnglishHybrid retrieval front door for FRC patterns: local team sources, curated docs, official examples, then remote fallback.
EnglishExplain Clawdia's repository structure, locate functionality, trace agent/skill wiring, and diagnose config issues.
English
AGENT SKILLS ATLASIncludes API Spend Tracker, Autoimprove, Autoimprove Tbc, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
API Spend Tracker
Tracks API spending across Anthropic, OpenAI, and Google keys with SQLite storage and daily Telegram digests
Autoimprove
Autonomous optimization loop that improves any measurable thing. Point it at files to change, a command to check, and a number to improve — then walk away. Works with any AI agent. Use when the user wants to autonomously optimize code performance, ML training, Docker images, SQL queries, prompts, CI speed, bundle size, Kubernetes configs, or any domain with a measurable score. Triggers include requests like 'optimize this', 'improve performance', 'make this faster', 'reduce allocations', 'autoimprove', 'run the optimization loop', 'let it run overnight', or when the user has an improve.md file.
Autoimprove Tbc
Three-Body Council self-improvement loop with fuzzy-task auto-detection. Trigger when the user says "tbc improve", "autoimprove-tbc", "autoimprove tbc", "fuzzy improve", "deep improve", "three-body improve", "autoimprove-tbc status", "autoimprove-tbc results", "autoimprove-tbc report", "what did autoimprove-tbc do", or any request to improve quality of an existing skill using multi-model grading. Also trigger for "add test question" or "show test bank".
Code Tutor
Programming tutor — explanations, debugging help, challenges, and guided practice.
Frc Codegen
Generate FRC Java code through Builder and Arbiter, with Checker validation and guarded fallback.
Frc Triage
Fast FRC triage with Librarian evidence and Arbiter escalation for safety/review-sensitive cases.
Notesquiz
Generate quiz questions from uploaded photos of handwritten or typed notes. Use when a user shares an image of their notes and wants to be quizzed, tested, or drilled on the content. Supports any subject. Triggers on commands like /notesquiz, "quiz me on my notes", or when a user uploads a note photo and asks for questions.
Patternscout
Hybrid retrieval front door for FRC patterns: local team sources, curated docs, official examples, then remote fallback.
Repo Brain
Explain Clawdia's repository structure, locate functionality, trace agent/skill wiring, and diagnose config issues.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the API Spend Tracker skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- License details are not provided in these listings. Check the author’s terms before using the skills.