sandeco-token-reduce

sandeco-token-reduce is a Context window & token budget skill for AI agents, published by sandeco in the prompts repository on GitHub. Skillspace rates sandeco-token-reduce F (45/100) and the safety scan rated it risky; the rating is based on static analysis only.

Comprime tokens de prompts usando LLMLingua-2 da Microsoft para reduzir custo e latencia. Use esta skill sempre que o usuario pedir para comprimir um prompt, reduzir tokens, economizar tokens, usar LLMLingua, ou quando um texto for longo demais para enviar a um LLM. Tambem use quando o usuario quiser pre-processar contexto antes de enviar ao Claude. Triggers: "comprimir", "reduzir tokens", "economizar tokens", "LLMLingua", "texto muito longo", "compressao de prompt", "token compression", "compress tokens", "inicializar compressao", "init token-reduce".

Grade
F
Quality
45 / 100
Safety
Risky
GitHub stars
863

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.

View source on GitHubsandeco/prompts

Our review

Architecture
84 / 100
Maturity
Structured: ships references or scripts
Security scan
High-risk patterns
License
Not declared. Check the repository before reusing it.
Adoption
Adopted by 0 other repositories, in 0 collections

What the scanner flagged

  • references sensitive credential env
  • mentions secrets in text

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

Better-rated skills in Context window & token budget

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.