v4-best-practices
v4-best-practices is an Agent behaviour & coding discipline skill for AI agents, published by Hmbown in the CodeWhale repository on GitHub. Skillspace rates v4-best-practices D (68/100) and it passed the safety scan; the rating is based on static analysis only.
Use when working with deepseek-v4-pro or deepseek-v4-flash in thinking mode on multi-step or plan-driven tasks. Provides rules to prevent stale references, unverified plan assumptions, and vague plan output.
- Grade
- D
- Quality
- 68 / 100
- Safety
- Passed
- GitHub stars
- 39,823
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
- 100 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 1 collections
- Scope
- Vendor-specific: built around one product. Best practices for the public deepseek-v4 thinking-mode models
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.