Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Commit · brycewang-stanford | DecimalAI

codingby brycewang-stanford

Commit

brycewang-stanford/commit

Source brycewang-stanford/Auto-Empirical-Research-Skills ↗License NOASSERTION

Stage, commit, and push changes for the sewage project. Creates a branch, commits with a descriptive message, pushes, and optionally creates a PR. This skill should be used when asked to "commit", "save changes", "push", or "create a PR".

NewMaintained

On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.

Coding pack

Last verified 8/8/2026

What it changes

Passed 11 of 16 test cases with the skill, and 12 of 16 without it.

Without skill77%

With skill68%

Checks it passed that the model alone missed

The response excludes .env from staging.
The response includes git log --oneline -5.
The response excludes settings.local.json from staging.

2 fixed13 passed either way3 still failing4 broke

Pass-rate lift: -9 pp
Tokens: -15%
Agent turns: 0%
Response time: -33%

Model gemini-3.6-flashMeasured 8/8/2026v315 of 22 cases passed with skill · 16 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-commit/SKILL.md https://app.decimal.ai/s/brycewang-stanford-commit/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add brycewang-stanford-commit, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/brycewang-stanford-commit/ and pins it in .decimal/skills.lock

decimalai skills add brycewang-stanford-commit

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-commit/SKILL.md https://app.decimal.ai/s/brycewang-stanford-commit/SKILL.md

Raw file: /s/brycewang-stanford-commit/SKILL.md ↗ · machine-readable summary at /s/brycewang-stanford-commit.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 2

Prompt

I'm starting a code check-in process on my local working copy. Show me the full set of inspection commands needed to review current state before branch creation.

What was checked, without and with the skill
Checked	Without skill	With skill
The response includes git status.	Passed	Passed
The response includes git diff --stat.	Passed	Passed
The response includes git log --oneline -5.	Missed	Passed

case-10 · gemini-3.6-flash · 8/8/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md43 linessingle file

Commit Workflow

Perform the full commit-PR-merge cycle.

Steps

Check current state:

git status
git diff --stat
git log --oneline -5

Create branch: git checkout -b [descriptive-branch-name]
Stage files:
- Stage specific files (never git add -A)
- Exclude: settings.local.json, .env, credentials, large data files
- Review what's being staged
Commit:
- Use $ARGUMENTS as commit message if provided
- Otherwise, analyze changes and write a descriptive message
- Format: imperative mood, concise, explains WHY not WHAT

Push and create PR:

git push -u origin [branch-name]
gh pr create --title "[message]" --body "[summary of changes]"

Merge (with user approval):

gh pr merge --merge --delete-branch
git checkout main
git pull

Important

Never commit directly to main

Track record

Benchmark

11 / 16

test cases passed, vs 12 / 16 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

brycewang-stanford / Auto-Empirical-Research-Skills

skills/41-sticerd-eee-sewage-econometrics-check/skills/commit/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/2/2026Version v3

More skills from the same source and nearby in the registry, with their headline benchmark lift.