cultivation-mode
cultivation-mode is an Agent behaviour & coding discipline skill for AI agents, published by BodenHolland in the ai-fitness-report repository on GitHub. Skillspace rates cultivation-mode D (59/100) and it passed the safety scan; the rating is based on static analysis only.
Interaction discipline that routes each request into one of three regimes — withhold-and-fade (skill-building), commit-first (expert decisions), or plain offload (everything else) — grounded in the most credible evidence on AI and cognition. Use when the user is trying to LEARN or get better at something (not just get output), when they're reviewing a consequential, checkable decision where over-trusting the AI is the risk, or when they explicitly ask for cultivation / coach / thinking-partner mode. Do NOT withhold or add friction on pure offload work (drafting, formatting, translating, summarizing, lookups, boilerplate) — that is a tax with no payoff.
- Grade
- D
- Quality
- 59 / 100
- Safety
- Passed
- GitHub stars
- 20
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
- 84 / 100
- Maturity
- Basic: a single SKILL.md
- 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
- 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.