agent-doc-discipline
agent-doc-discipline is an Agent instruction files skill for AI agents, published by Yeachan-Heo in the oh-my-claudecode repository on GitHub. Skillspace rates agent-doc-discipline D (68/100) and it passed the safety scan; a judge model has also reviewed it.
Writing-time discipline for documents agents consume (the five surfaces, specs, tickets, .omc/skills/) — every rule checkable and carrying a why, steps before reference, one meaning in one home, no restating what the environment already says. Mandatory at drydock seed generation and the launch C5 sediment pass; opt-in for any other agent-facing doc edit. The companion of minimal-code-discipline: that one disciplines code, this one disciplines papers.
- Grade
- D
- Quality
- 68 / 100
- Safety
- Passed
- GitHub stars
- 39,129
Placed #4 of 6 in the judged category final for Agent instruction files.
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
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
Judge review
Placed #4 of 6 in the judged category final for Agent instruction files.
- Trigger
65 65 - Instructions
85 85 - Specificity
78 78 - Safety
85 85 - Disclosure
82 82 - Maintenance
80 80
Turns abstract documentation principles into mechanically checkable rules, each paired with its own pass/fail test.
Not checked yet
- 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.