lingtai-recipe

lingtai-recipe is an Agent, team & workflow authoring skill for AI agents, published by Lingtai-AI in the lingtai repository on GitHub. Skillspace rates lingtai-recipe C (78/100) and it passed the safety scan; the rating is based on static analysis only.

Menu manual (not a tool) for everything recipe-related in LingTai. A **recipe** is the named payload that shapes an orchestrator's greeting, ongoing behaviour, and shipped library; every LingTai project uses one (selected at `/setup` time, inherited from a clone, or auto-discovered when a project already has `.recipe/` at its root). The skill body fans out into two substantive sub-guides so you load only what the task needs: `reference/recipe-format/SKILL.md` for the bundle format + `recipe.json` schema + library sibling rules + validator contract (read first when authoring or customising); and `reference/export-recipe/SKILL.md` for shipping the methodology / culture as a bundle others can use to seed *new* networks (no agents, no mailboxes). Body also warns about the three different recipe-shaped artifacts that can co-exist in one project (inner network, outer applied recipe, captured applied snapshot — easy to conflate). Read this skill when the human mentions recipes, wants to…

Grade
C
Quality
78 / 100
Safety
Passed
GitHub stars
701

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Our review

Architecture
84 / 100
Maturity
Structured: ships references or scripts
Security scan
No issues found
License
Apache-2.0
Adoption
Adopted by 0 other repositories, in 0 collections
Scope
Vendor-specific: built around one product. Documents LingTai product's recipe concept for its users

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.