terse-internal
terse-internal is a Context window & token budget skill for AI agents, published by nghiahsgs in the taw-kit repository on GitHub. Skillspace rates terse-internal D (59/100) and it passed the safety scan; the rating is based on static analysis only.
Caveman-style terse output rules for AGENT-INTERNAL work only (planner, researcher, fullstack-dev, tester, reviewer, debug). Cuts ~60-70% of output tokens by killing preamble, postamble, tool narration, and filler. Never activates for user-facing Vietnamese output (taw, taw-add, taw-new, approval-plan, vietnamese-copy, error-to-vi hints shown to user). Inspired by JuliusBrussee/caveman but scoped so non-dev VN users still get friendly hand-holding in their language.
- Grade
- D
- Quality
- 59 / 100
- Safety
- Passed
- GitHub stars
- 32
Unproven: rated by static analysis only, not yet compared head-to-head.
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
- 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.