Auto Improve

What it does

When your agent uses it

• The user wants to autonomously improve the quality of a document
• Tasks that involve Quizzes and assessments
• Tasks that involve Git workflow

Example prompts

• “/auto-improve”

Requirements

• Python 3
• A credential in GEMINI_API_KEY

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1Mutate — best-of-N candidate edits, applied as surgical diffs (crash-proof).
2. 2Score — each candidate graded against the rubric by a separate model call.
3. 3Decide — the best candidate is pairwise-judged against the champion (both

What it can do on your machine

Read from SKILL.md and the folder at commit 03aa5a9. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • python3
  • git

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • aistudio.google.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • GEMINI_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Auto Improve loads about 651 tokens when it runs. Until then it costs about 97 tokens; SKILL.md has 246 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~97

When it runs · the whole SKILL.md, loaded when a task matches

~651

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from crimeacs/auto-improve at commit 03aa5a9, republished under its MIT licence (© crimeacs). 246 words, ~651 tokens.

name

auto-improve

description

GAN-style iterative improvement loop for any text artifact. Mutates a file, grades each change against a rubric with a SEPARATE model, keeps only verified wins (pairwise-judged), reverts the rest. The git history is the improvement log. Use when the user wants to autonomously improve the quality of a document, email, prompt, landing page, README, contract, or any text file.

user-invocable

true

export GEMINI_API_KEY=...        # https://aistudio.google.com/apikey
python3 improve.py \
  --artifact path/to/file.md \   # must be inside a git repo
  --tag v1 \                     # → branch improve/v1, results/v1.tsv
  --max-iterations 8 \
  --criteria path/to/rubric.md   # OPTIONAL — omit to auto-infer a rubric; or add
                                 # --goal "what good looks like" to steer the inferred one

© crimeacs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 56 other files (assets) in the repository root of crimeacs/auto-improve.

• SKILL.md
• .editorconfig
• .github/CODEOWNERS
• .github/CODE_OF_CONDUCT.md
• .github/CONTRIBUTING.md
• .github/ISSUE_TEMPLATE/bug_report.yml
• .github/ISSUE_TEMPLATE/config.yml
• .github/ISSUE_TEMPLATE/feature_request.yml
• .github/PULL_REQUEST_TEMPLATE.md
• .github/SECURITY.md
• .github/SUPPORT.md
• .github/dependabot.yml
• .github/workflows/ci.yml
• .gitignore
• .pre-commit-config.yaml
• CHANGELOG.md
• CITATION.cff
• LICENSE
• … and 39 more

Open the folder on GitHubat commit 03aa5a9