Index of every page on this site: llms.txt
All skills
a2ui-project avatar

/inference-format-optimizer

@6bf4cc2
by A2UIa2ui-project/a2ui18k stars
1,430
Run it yourself

Iterative benchmarking, evaluation, and algorithmic optimization of alternative A2UI inference formats (such as Express, Atom, and Elemental). Trigger when asked to: (1) Run optimization passes or loops on an inference format, (2) Evaluate or benchmark format accuracy, latency, or token efficiency, (3) Create parallel worktree subagents for format iteration, or (4) Benchmark format trade-offs against baselines.

  • 19 files
  • 207.9 KB
  • Updated 2 weeks ago
  • GitHub
Use this Skill: https://skilld.dev/gh/a2ui-project/a2ui/inference-format-optimizer

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

templatessubagent_prompt.md

≈322 tokens on demand. Your agent reads this file only when SKILL.md points to it.

You are tasked with executing Optimization Pass {{PASS_NUM}} on the {{FORMAT}} inference format in the dedicated worktree: Directory: {{WORKTREE_PATH}}

Task instructions:

  1. Edit file: {{TARGET_FILE}} Hypothesis: {{HYPOTHESIS}}

  2. Run Pytest unit tests: PYTHONPATH=python/a2ui_agent/src:python/a2ui_core/src /usr/local/google/home/gspencer/code/a2ui/iterative_optimization/.venv/bin/python -m pytest python/a2ui_agent/tests/{{FORMAT}}/

  3. Run optimization evaluation: /usr/local/google/home/gspencer/code/a2ui/iterative_optimization/.venv/bin/python eval/iterative/optimize_format.py --format {{FORMAT}}

  4. Decision rules:

    • If unit tests fail, Quality Score regresses below baseline, or Output Tokens expand by > 5%: Revert changes using git reset --hard HEAD and archive the run: /usr/local/google/home/gspencer/code/a2ui/iterative_optimization/.venv/bin/python eval/iterative/optimize_format.py --format {{FORMAT}} --archive --hypothesis "Pass {{PASS_NUM}}: {{HYPOTHESIS}}" --status REVERT --notes "<reason>"
    • Else keep the changes and archive with --status KEEP.
  5. Run history sync: /usr/local/google/home/gspencer/code/a2ui/iterative_optimization/.venv/bin/python eval/iterative/sync_history.py

Provide a summary of the outcome when complete.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at 6bf4cc2. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 weeks ago
metadata
{
  "internal": true
}

README badge

README badge for a2ui-project/a2ui/inference-format-optimizer