#137137th of 193 in Skills, plugins and prompts
teaql-agent-kit
Agent skill that makes coding agents model, generate and verify TeaQL apps
Live demo ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 2.8k
- License
- MIT
- Last commit
- Sep 2026
- Last release
- Jul 2026
- Language
- Python
2,722 on 31 Mar 20262,818 on 20 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
An Agent Skill (build-teaql-app) that coding agents such as Claude Code, Codex, Cursor, Copilot or Gemini CLI follow to build apps model-first. The agent writes a domain model, has a TeaQL service evaluate and repair it, generates a typed library with Q query and E expression APIs, then implements and verifies the app. The README's example uses Rust and SQLite and ends with a work-complete.md evidence report.
Who it is for: Developers using coding agents who want model-first, auditable app generation
Strengths
- Works with several existing coding agents through one pasted prompt
- Deterministic model evaluation with repair guidance runs before application code is written
- Generated typed Q/E APIs; runtime logs SQL and audit context with query purpose and comment
- Requires a work-complete.md report citing build, test and runtime log evidence
Weaknesses
- Default workflow needs network access; model content is sent to TeaQL services
- Evaluation, generation and Assist use hosted services, so the workflow is not offline
- Ties the application to the TeaQL runtime and generated library
- README gives no measured token savings; the context benefit is stated as an aim
What it needs
- no GPU
- Needs TeaQL evaluation and generation services, Coding agent with file and terminal access, Language toolchain for the target app (e.g. Rust)
- Models: Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI
Also in Skills, plugins and prompts
See all 193| Rank | Project | Score |
|---|---|---|
| 1 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |
| 2 | impeccableDesign skill with 24 commands and a detector for AI-generated frontends | 95 out of 100 |
| 3 | skillsAgent skills for planning, TDD, debugging and code review | 94 out of 100 |
| #4 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 94 out of 100 |
| #5 | oh-my-claudecodeMulti-agent orchestration plugin and CLI for Claude Code | 93 out of 100 |