harness-lab

harness-lab is an Agent, team & workflow authoring skill for AI agents, published by jikime in the harness-lab repository on GitHub. Skillspace rates harness-lab C (71/100) and it passed the safety scan; the rating is based on static analysis only.

Codex용 하네스 엔지니어링 실습·설계·생성 스킬. 사용자가 일상 업무, 학습 과제, 문서 작업, 콘텐츠 제작, 리포트·계획서·체크리스트·HTML 시각 리포트 같은 결과물을 반복 가능하게 만들고 싶어 할 때, 그 일을 Agent, Skill, Orchestrator, Test, Evolution 구조로 바꿔준다. "하네스 만들어줘", "에이전트와 스킬 설계해줘", "내 업무를 멋진 산출물로 만들어줘", "Codex용 AGENTS.md와 .agents/skills, .codex/agents 구성해줘", "기존 하네스 점검/개선해줘", "하네스 성숙도 진단해줘", "내 업무를 하네스 설계 카드로 바꿔줘" 같은 요청에서 반드시 사용한다. 실행 하네스 생성 시에는 반드시 Codex의 AGENTS.md, AGENTS.override.md, .agents/skills, .codex/agents 경로를 기준으로 한다. 단순한 일반 설명, 하네스와 무관한 코딩 질문, Claude Code 전용 .claude 파일 생성에는 사용하지 않는다.

Grade
C
Quality
71 / 100
Safety
Passed
GitHub stars
55

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

Not launch-quality. It is graded C with a clean safety verdict, but our quality filters exclude it: it is a near-duplicate variant of another skill. 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.

View source on GitHubjikime/harness-lab

Our review

Architecture
94 / 100
Maturity
Structured: ships references or scripts
Security scan
No issues found
License
Not declared. Check the repository before reusing it.
Adoption
Adopted by 0 other repositories, in 0 collections

Not checked yet

  • Category is a classifier prediction; no model has read this skill 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

Better-rated skills in Agent, team & workflow authoring

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