bee-creator

bee-creator is an Agent, team & workflow authoring skill for AI agents, published by legioncodeinc in the that-git-life repository on GitHub. Skillspace rates bee-creator B (81/100) and it passed the safety scan; the rating is based on static analysis only.

Phase 3 of the Legion AI Tools Factory pipeline. Authors the Cursor IDE subagent (Bee) file from a completed Command Brief and forged Stinger. Writes the YAML frontmatter, composes the body with proper Read-references to every file in the paired Stinger folder, wires the Bee to its guardrails and escalation paths, and declares a proactive/on-demand trigger policy. Use this skill whenever the user asks to "create the Bee", "author the subagent", "build the subagent file", "wire up the Bee", "finish the Bee", or signals that the Stinger is forged and it is time to assemble the subagent. Also trigger when stinger-forge has just announced its handoff or when the user points to a ready-to-use stinger folder and asks for its Bee.

Grade
B
Quality
81 / 100
Safety
Passed
GitHub stars
72

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

Not launch-quality. It is graded B with a clean safety verdict, but our quality filters exclude it: a model that read it found it written only for the repository it lives in. So it is not in our launch-quality set, the skills our MCP server searches and recommends. How launch-quality is decided

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
100 / 100
Maturity
Packaged: licensed, with a version or references
Security scan
No issues found
License
Not declared. Check the repository before reusing it.
Adoption
Adopted by 1 other repositories, in 0 collections
Scope
Repo-internal: written for the repository it lives in. Phase of Legion AI Tools Factory with its own briefs and Stingers

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.