FreeSkills
Commits, branches and sync with the but CLI
- 361361 downloads
- 198198 likes
- 103103 saves
- Claude Code
- Codex
- Cursor
- and 3 more
Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans
Use this resource to constrain an LLM's output to a valid format with Guidance
New
Free
In a terminal, from the folder you want:
npx --yes palatekit@latest install guidance-constrained-llm-outputWith 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 writes Guidance programs that enforce a syntax with regex or grammar, guarantee valid JSON, XML or code, and chain several steps in Python. It connects the chosen model: OpenAI, Transformers, llama.cpp or Claude. You get outputs that always follow the requested format.
Mostly picked by
Updated November 2, 2026
You say
“Force my model's answer into JSON with name, date and amount, and no surrounding text.”

Skill published by davila7 under the MIT license, delivered in its original version.
Listed unmodified
« prompt-engineering-guidance » (davila7, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.
–
No ratings yet
Loading reviews…