FreeSkills
Commits, branches and sync with the but CLI
- 361361 downloads
- 198198 likes
- 103103 saves
Works with
- Claude Code
- Codex
- Cursor
- and 3 more
Designing and evaluating AI systems v1.0.0
Use this resource to design and evaluate an AI application
New
- 553 downloads
- 190 likes
- 183 saves
Free
Install with the CLI
In a terminal, from the folder you want:
npx --yes palatekit@latest install llm-application-evaluation-2With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.
First time: connect the CLI with
npx --yes palatekit@latest loginThe agent designs the architecture of an LLM application (prompts, RAG, agents, tools), sets up an evaluation suite and reviews safety, cost and deployment. You get a reasoned design and measurable evaluation criteria.
Mostly picked by
Updated November 2, 2026
Previews
Details
- Install guides
- Generates with
- Your agent's model
- Licence
- MIT
Similar resources
View all- Free
FreeSkills
Sentry CLI guide
- 525525 downloads
- 117117 likes
- 128128 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Drizzle ORM best practices with PostgreSQL
- 407407 downloads
- 194194 likes
- 151151 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
SLO design wizard
- 537537 downloads
- 105105 likes
- 242242 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
User stories and sprint fit
- 451451 downloads
- 150150 likes
- 132132 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Capacity-based sprint plan
- 423423 downloads
- 192192 likes
- 102102 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Startup CTO advisor
- 580580 downloads
- 201201 likes
- 242242 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Creating GitHub pull requests with quality checks
- 427427 downloads
- 230230 likes
- 196196 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
What you get
- SKILL.md: operating modes, decision rules and behavior contracts
- reference/: agent design, embedding strategy, evaluation and cost optimization
Good fit for
- You are building an assistant that answers from your documents
- You want to know whether a new prompt version is better
Not for
Tags
- llm
- rag
- evaluation
- agents
About
You say
“Design a RAG over our help center, with an evaluation suite and a cost estimate per request.”
Skill published by simota under the MIT license, delivered in its original version.
Show moreShow less
How to use it
- Install the skill in your agent's skills folder
- Ask your agent to design and evaluate an AI application
- Review and adjust the result
Content preview
Files
- LICENSE1 KB
- NOTICE-PALATEKIT.md0.4 KB
- reference/advanced-tool-use.md14.1 KB
- reference/agent-behavior-contract.md13.1 KB
- reference/agent-design.md12.4 KB
- reference/ai-safety-guardrails.md7.2 KB
- reference/architecture-review.md8.3 KB
- reference/cost-optimization.md18.3 KB
- reference/embedding-strategy.md7.6 KB
- reference/evaluation-observability.md18.8 KB
- reference/human-ai-trust.md16 KB
- reference/llm-application-patterns.md11.4 KB
- reference/llm-production-anti-patterns.md7 KB
- reference/prompt-engineering.md16.8 KB
- reference/rag-design-anti-patterns.md10.1 KB
- reference/recipes-index.md1.9 KB
- reference/reference-index.md2.7 KB
- SKILL.md23.7 KB
Origin and licence
Listed unmodified
- Author
- simota
- Source
- github.com/simota/agent-skills/tree/2e02cc9efb3852a45334495df3784d59b87b0e18/oracle
- Licence
- MIT
Notice
« oracle » (simota, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.
User reviews
–
No ratings yet
Loading reviews…