General
PromptBeginner5 minmarkdown
- Key risks or dependencies to monitor (e.g.
bias checks)
0
Explore
Find agent skills by outcome
115,682 skills indexed with the new KISS metadata standard.
Showing 24 of 115,682Categories: Data, Cursor-rules, Communication, General, Coding & Debugging
General
PromptBeginner5 minmarkdown
- Lightweight/chat-only models (older 7B–13B models
mini variants) — usually lack depth/context/tool reliability
0
Data
PromptBeginner5 minmarkdown
- **Llama 4 / Llama 405B variants (Meta)** — Best open-source frontier performance
excellent for self-hosting
0
General
PromptBeginner5 minmarkdown
- **Gemini 2.5 Pro / Flash (Google)** — Outstanding multimodal (especially video/document understanding)
very large context windows
0
General
PromptBeginner5 minmarkdown
- **Mistral Large 2 / Devstral** — Very strong price/performance
fast
0
Data
PromptBeginner5 minmarkdown
- **Grok 3 / Grok 4 (xAI)** — Excellent reasoning
real-time knowledge via X
0
General
PromptBeginner5 minmarkdown
- **Claude 4 Opus/Sonnet (Anthropic)** — Exceptional long-form reasoning
writing quality
0
General
PromptBeginner5 minmarkdown
- Privacy
open behavior
0
General
PromptBeginner5 minmarkdown
- Tool use
function calling
0
General
PromptBeginner5 minmarkdown
Current Best-in-Class Ranking (January 2026 – general guidance
always tailor to the process):
0
General
PromptBeginner5 minmarkdown
- Call out misconceptions
dependencies
0
General
PromptBeginner5 minmarkdown
If AI is viable
recommend which AI engines are best suited and why.
0
General
PromptBeginner5 minmarkdown
- Track KPIs (e.g.
20% time savings
0
General
PromptBeginner5 minmarkdown
Summarize the overall feasibility score (weighted average)
then issue your verdict with clear reasoning.
0
General
PromptBeginner5 minmarkdown
**Interpretation:** Clear patterns exist
but context accuracy is critical. Recommend hybrid approach with AI drafts + human review.
0
Data
PromptBeginner5 minmarkdown
| Data quality | 3 | Mostly clean
some inconsistency |
0
Data
PromptBeginner5 minmarkdown
| **4 – High Feasibility** | Clear logic
consistent data
0
General
PromptBeginner5 minmarkdown
When scoring
evaluate these dimensions (suggested weights for averaging: e.g.
0
Data
PromptBeginner5 minmarkdown
| **5 – Excellent Feasibility** | Predictable process
well-defined data
0
Data
PromptBeginner5 minmarkdown
| **2 – Low Feasibility** | Some structured elements exist
but goals or data are unclear. AI could assist with insights
0
General
PromptBeginner5 minmarkdown
| **1 – Not Feasible** | Process heavily dependent on expert judgment
implicit knowledge
0
General
PromptBeginner5 minmarkdown
../claude.md
generic skill
0
Data
PromptBeginner5 minmarkdown
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|todo] [description].
0
General
PromptBeginner5 minmarkdown
リポジトリガイドライン
README.md を参照してください。
0