FreeSkills
Knowledge wiki setup
- 418418 downloads
- 129129 likes
- 161161 saves
Works with
- Claude Code
- Codex
- Cursor
- and 3 more
Evaluate AI answers and trajectories v1.0.0
Use this resource to score the quality of an AI answer and analyze its solution steps
New
- 441 downloads
- 175 likes
- 240 saves
Free
Install with the CLI
In a terminal, from the folder you want:
npx --yes palatekit@latest install ai-response-evaluation-promptsWith 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 applies meta-prompt templates: it critiques an answer, gives it a score from 0 to 10 and states whether the question is fully solved. It can also analyze a solution trajectory by action type. You get a structured evaluation with explicit criteria.
Mostly picked by
Updated November 2, 2026
Previews
Details
- Install guides
- Generates with
- Your agent's model
- Licence
- Apache-2.0
Similar resources
View all- Free
FreeSkills
Wiki health check
- 552552 downloads
- 202202 likes
- 127127 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Ask your wiki
- 374374 downloads
- 131131 likes
- 214214 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Wiki source ingestion
- 315315 downloads
- 230230 likes
- 246246 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Wiki auditor agent
- 556556 downloads
- 205205 likes
- 192192 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
UX research assistant
- 598598 downloads
- 142142 likes
- 236236 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Wiki ingestion agent
- 437437 downloads
- 162162 likes
- 191191 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Wiki librarian agent
- 304304 downloads
- 120120 likes
- 217217 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
What you get
- SKILL.md: response evaluator, evaluation fields and criteria
- SKILL.md: trajectory analysis, action types and prompt techniques
Good fit for
- You compare several model answers to the same questions
- You test a question-answering agent and look for where it fails
Not for
Tags
- meta-prompt
- evaluation
- ai
About
You say
“Score this answer out of 10 and say whether it fully solves the question.”
Skill published by mindrally under the Apache-2.0 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 score the quality of an AI answer and analyze its solution steps
- Review and adjust the result
Content preview
Files
- LICENSE11.3 KB
- NOTICE-PALATEKIT.md0.5 KB
- SKILL.md4.6 KB
Origin and licence
Listed unmodified
- Author
- mindrally
- Source
- github.com/mindrally/skills/tree/7682ca77710e0971eab4e0ae5dddfa281aea0ba5/meta-prompt
- Licence
- Apache-2.0
Notice
« meta-prompt » (mindrally, Apache-2.0) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.
User reviews
–
No ratings yet
Loading reviews…