Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

skill-slim

A tiny audit tool for Agent Skills. It measures the always-loaded token weight of a SKILL.md and flags what to defer to references/ or scripts/.

Why

A skill's SKILL.md is injected into context in every session where the skill is available. Detail that only matters after the skill fires still taxes every session. The fix is progressive disclosure: keep SKILL.md a thin trigger + pointers, and push heavy content into linked references/*.md and executable scripts/.

skill-slim just measures that weight so you can see which skills are heavy and where the movable bytes are. It doesn't rewrite anything — it points; you slim.

Install

Drop it into your skills directory, or clone and run the script directly. No dependencies beyond Python 3.

git clone https://github.com/llmer/skill-slim
python3 skill-slim/scripts/analyze.py path/to/SKILL.md [more.md ...]

Usage

python3 scripts/analyze.py path/to/SKILL.md [more.md ...]

Reports per file: estimated always-loaded tokens, budget overage, movable inline-code / long-prose weight, existing progressive-disclosure links, and a conservative post-slim estimate. Sorted worst-first. JSON on stdout, a summary table at the end.

Proof (reproducible)

Run the analyzer on a real Anthropic skill before and after slimming, plus this tool's own SKILL.md:

$ python3 scripts/analyze.py examples/frontend-design-before/SKILL.md examples/frontend-design-after/SKILL.md SKILL.md

=== summary (worst first) ===
[SLIM] frontend-design-before/SKILL.md  ~ 2062 tok  → ~1501 after  (27% off)
[ok  ] frontend-design-after/SKILL.md   ~  395 tok  → ~ 395 after  (0% off)
[ok  ] skill-slim/SKILL.md              ~  323 tok  → ~ 323 after  (0% off)
  • frontend-design before: ~2,062 always-loaded tokens, flagged over budget.
  • frontend-design after a hand-slim that moved the design + writing guidance into references/ (see examples/frontend-design-after/): 395 tokens — an actual 81% cut, well under budget.
  • skill-slim dogfoods: its own SKILL.md is 323 tokens, under budget.

Note the estimator's → after column is deliberately conservative (it only counts obviously-movable code/prose, so it predicted 27% for frontend-design). A real slim that also restructures the prose beat that estimate by a wide margin. Treat the estimate as a floor, not a ceiling.

The examples/ directory contains the exact before/after files, so the numbers above reproduce on a clean checkout.

What it flags

Metric Meaning
total_tokens_est chars/4 of the whole file (approximate, tokenizer-free)
inline_code_tokens fenced code blocks — examples the model can run from scripts/ instead of reading inline
long_prose_tokens paragraphs > 600 chars — often re-derivable guidance or reference material for references/
existing_ref_links links to *.md; zero + over budget = everything loads eagerly

Method, heuristics, and the budget rationale: references/method.md.

Caveats

Token counts are a chars/4 approximation, not a real tokenizer — use them for relative ranking and rough targets, not exact billing. The ~500-token budget is a guideline for a "thin" skill, not a hard failure line.

License

MIT

About

Audit a SKILL.md's always-loaded token weight and flag what to defer to references/ or scripts/. Reproducible 81% slim on Anthropic's frontend-design skill.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages