Find agent skills by outcome

valet-wt Plugin

Laravel workspace scripts and git worktrees with Valet, databases, and Warp config.

Worktree

Manage git worktrees with symlinked .env files, playground, and simulations

Read documentation here

https://hot-labs.gitbook.io/hot-protocol/hot-kit

Follow the AI policy and context files for this repo.

- docs/ai/AI_POLICY.md

Please read and strictly follow the rules defined in ./AGENTS.md

generic skill

- Recommendations for iteration (A/B testing

feedback loops)

- Instead

suggest non-AI or hybrid alternatives (e.g.

- Key risks or dependencies to monitor (e.g.

bias checks)

- Keep it minimal and adaptable

including placeholders for iteration or error handling

- Lightweight/chat-only models (older 7B–13B models

mini variants) — usually lack depth/context/tool reliability

- Gemini 2.5 Pro / Flash (Google) — Outstanding multimodal (especially video/document understanding)

very large context windows

Data

- Llama 4 / Llama 405B variants (Meta) — Best open-source frontier performance

excellent for self-hosting

- Mistral Large 2 / Devstral — Very strong price/performance

fast

- Claude 4 Opus/Sonnet (Anthropic) — Exceptional long-form reasoning

writing quality

Data

- Grok 3 / Grok 4 (xAI) — Excellent reasoning

real-time knowledge via X

Current Best-in-Class Ranking (January 2026 – general guidance

always tailor to the process):

- Tool use

function calling

- Privacy

open behavior

If AI is viable

recommend which AI engines are best suited and why.

- Track KPIs (e.g.

20% time savings

- Call out misconceptions

dependencies

When scoring

evaluate these dimensions (suggested weights for averaging: e.g.

Summarize the overall feasibility score (weighted average)

then issue your verdict with clear reasoning.

Interpretation: Clear patterns exist

but context accuracy is critical. Recommend hybrid approach with AI drafts + human review.