Find agent skills by outcome

copilot instructions

after completing a task, you may want to run these quality checks. it may be easiest to run them all together from a

Local Notes

- Contracts: /Users/avral/projects/alcor/contracts/dex

Creative

这些指令适用于在此项目中工作的 AI 助手。

docs/ai-instructions.md

generic skill

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

writing quality

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

very large context windows

- Tool use

function calling

Productivity

- GPT-5 / o3 family (OpenAI) — Deepest reasoning on very complex structured tasks

best at following extremely long/complex instructions

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

always tailor to the process):

Design

Cog came from Andreas's experience at Spotify and Ben's experience at Docker.

- Track KPIs (e.g.

20% time savings

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.

- Call out misconceptions

dependencies

Productivity

| 3 – Moderate Feasibility | Certain tasks could be automated (e.g.

drafting

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

implicit knowledge

After the interview

provide a structured assessment.

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

time saved

- What is your budget or resource availability for AI implementation (e.g.

time

- Is correctness

creativity

- Are there legal

ethical

### 4. Frequency

Scale

Begin by asking the user the following questions

one section at a time. Do NOT skip ahead