Find agent skills by outcome

- Generate a simple

practical starter prompt

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

very large context windows

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

fast

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

writing quality

- Privacy

open behavior

- Tool use

function calling

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

always tailor to the process):

- Call out misconceptions

dependencies

If AI is viable

recommend which AI engines are best suited and why.

- Track KPIs (e.g.

20% time savings

Interpretation: Clear patterns exist

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

Summarize the overall feasibility score (weighted average)

then issue your verdict with clear reasoning.

When scoring

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

| 1 – Not Feasible | Process heavily dependent on expert judgment

implicit knowledge

Creative

Copilot 規範層（全タスク共通で短く強い指示）

- 仕様の入口は `.github/copilot/00-index.md`。参照順に従い、設計→実装の2段階ループを厳守する。

../claude.md

generic skill

リポジトリガイドライン

README.md を参照してください。

Repository Agent Instructions

- Always use Conventional Commits.

Guidelines for my dotfiles repo

Pi agent config is at `~/.config/pi/agent` (symlinked to dotfiles). Extensions go in `~/.config/pi/agent/extensions/`.

- How would you measure the success of AI support (e.g.

time saved

After the interview

provide a structured assessment.

- Are there legal

ethical

### 4. Frequency

Scale