kkirikkiri
kkirikkiri is an Agent, team & workflow authoring skill for AI agents, published by fivetaku in the gptaku-plugins-codex repository on GitHub. Skillspace rates kkirikkiri C (79/100) and it passed the safety scan; the rating is based on static analysis only.
Assemble and run a Codex-native agent team from one plain-language request. Interviews the user with 2-3 questions, proposes specialized agents synthesized from 7 archetypes + domain detail, then executes with a local lead plus bounded sidecar agents and shared memory in `.kkirikkiri/`. Use when the user explicitly wants delegation, a research/development/analysis/content/product team, or parallel sub-agent work. Korean triggers — 팀 만들어줘, 리서치 팀, 끼리끼리, 팀 구성해줘. English — build a team, research team, agent team, kkirikkiri.
- Grade
- C
- Quality
- 79 / 100
- Safety
- Passed
- GitHub stars
- 109
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 97 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- No issues found
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- 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.