Data
PromptBeginner5 minmarkdownQuality: 24
- Llama 4 / Llama 405B variants (Meta) — Best open-source frontier performance
excellent for self-hosting
0
Explore
Find agent skills by outcome
153,723 skills indexed with the new KISS metadata standard.
Showing 24 of 153,723
General
PromptBeginner5 minmarkdownQuality: 20
- Mistral Large 2 / Devstral — Very strong price/performance
fast
0
General
PromptBeginner5 minmarkdownQuality: 20
- Claude 4 Opus/Sonnet (Anthropic) — Exceptional long-form reasoning
writing quality
0
Productivity
PromptBeginner5 minmarkdownQuality: 24
- GPT-5 / o3 family (OpenAI) — Deepest reasoning on very complex structured tasks
best at following extremely long/complex instructions
0
Data
PromptBeginner5 minmarkdownQuality: 20
- Grok 3 / Grok 4 (xAI) — Excellent reasoning
real-time knowledge via X
0
General
PromptBeginner5 minmarkdownQuality: 20
- Tool use
function calling
0
General
PromptBeginner5 minmarkdownQuality: 20
Current Best-in-Class Ranking (January 2026 – general guidance
always tailor to the process):
0
General
PromptBeginner5 minmarkdownQuality: 20
- Privacy
open behavior
0
General
PromptBeginner5 minmarkdownQuality: 20
- Call out misconceptions
dependencies
0
General
PromptBeginner5 minmarkdownQuality: 20
If AI is viable
recommend which AI engines are best suited and why.
0
General
PromptBeginner5 minmarkdownQuality: 20
- Track KPIs (e.g.
20% time savings
0
General
PromptBeginner5 minmarkdownQuality: 24
Summarize the overall feasibility score (weighted average)
then issue your verdict with clear reasoning.
0
General
PromptBeginner5 minmarkdownQuality: 24
Interpretation: Clear patterns exist
but context accuracy is critical. Recommend hybrid approach with AI drafts + human review.
0
Data
PromptBeginner5 minmarkdownQuality: 25
| Data quality | 3 | Mostly clean
some inconsistency |
0
Data
PromptBeginner5 minmarkdownQuality: 25
| 5 – Excellent Feasibility | Predictable process
well-defined data
0
Data
PromptBeginner5 minmarkdownQuality: 25
| 4 – High Feasibility | Clear logic
consistent data
0
General
PromptBeginner5 minmarkdownQuality: 20
When scoring
evaluate these dimensions (suggested weights for averaging: e.g.
0
General
PromptBeginner5 minmarkdownQuality: 25
| 1 – Not Feasible | Process heavily dependent on expert judgment
implicit knowledge
0
Data
PromptBeginner5 minmarkdownQuality: 29
| 2 – Low Feasibility | Some structured elements exist
but goals or data are unclear. AI could assist with insights
0
Creative
PromptBeginner5 minmarkdownQuality: 32
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。
0
General
PromptBeginner5 minmarkdownQuality: 17
../claude.md
generic skill
0
Data
PromptBeginner5 minmarkdownQuality: 48
worklog
Update worklog files by moving tasks between todo/doing/done states. Use when recording task progress, starting new work, or marking tasks complete. Requires explicit arguments: worklog [done|doing|to...
0
Productivity
PromptBeginner5 minmarkdownQuality: 46
ship
|
0
Productivity
PromptBeginner5 minmarkdownQuality: 24
With Skill Evidence for google-flow--google-flow
Agent is prompted to [task description] with this skill loaded.
0