Ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Detects structural prompt weaknesses before they affect production outputs — improving the quality, consistency, and reliability of every future generation across the pipeline.
> **Partner-grade evaluation for LLM agents.** Score AI outputs against the verbatim BCG rubric used to promote analysts. Adversarial Skeptic Agent for sycophancy detection. 10-signal Novelty Stack. **Claude-native — no API keys.** [](LICENSE) [](https://docs.anthropic.com/en/docs/agents-and-tools/agent-skills) [](https://www.anthropic.com/) [](#install-one-command) [](#built-in-feedback-loop) In any Claude Code
git clone --depth 1 https://github.com/EvXata/deepeval-bcg.git ~/.claude/skills/deepeval-bcg
Restart Claude Code afterwards. See the README for skill-specific setup.
Using Codex CLI? Copy the same folder to ~/.codex/skills/deepeval-bcg instead.
No specific triggers listed.
> **Partner-grade evaluation for LLM agents.** Score AI outputs against the verbatim BCG rubric used to promote analysts. Adversarial Skeptic Agent for sycophancy detection. 10-signal Novelty Stack. **Claude-native — no API keys.** [](LICENSE) [](https://docs.anthropic.com/en/docs/agents-and-tools/agent-skills) [](https://www.anthropic.com/) [](#install-one-command) [](#built-in-feedback-loop) In any Claude Code
Clone it into your personal skills folder: git clone --depth 1 https://github.com/EvXata/deepeval-bcg.git ~/.claude/skills/deepeval-bcg — then restart Claude Code.
Deepeval Bcg is open source on GitHub (2 stars at last check) and published by EvXata.
Browse other meta skills in the Meta category of this directory.