talk-normal
talk-normal is a Writing style & humanising skill for AI agents, published by hexiecs in the talk-normal repository on GitHub. Skillspace rates talk-normal A (90/100) and it passed the safety scan; a judge model has also reviewed it.
Stop LLM slop. A curated system prompt that cuts verbose, corporate-sounding LLM output by 56-71% (measured) while preserving information. Works bilingually (English + Chinese). Installs into your AGENTS.md as an always-on behavior modifier.
- Grade
- A
- Quality
- 90 / 100
- Safety
- Passed
- GitHub stars
- 1,794
Placed #2 of 6 in the judged category final for Writing style & humanising.
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.
Our review
- Architecture
- 94 / 100
- Maturity
- Packaged: licensed, with a version or references
- Security scan
- No issues found
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
- Scope
- Portable: works in any project. generic LLM output style modifier installed into any AGENTS.md
Judge review
Placed #2 of 6 in the judged category final for Writing style & humanising.
- Trigger
82 82 - Instructions
80 80 - Specificity
85 85 - Safety
72 72 - Disclosure
90 90 - Maintenance
92 92
Well-measured, versioned, licensed installer, though it rewrites a persistent shared config file with no confirmation step mentioned.
Not checked yet
- 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.