Ready to supercharge your AI agents?

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

Git Review · umputun | DecimalAI

code reviewby umputun

Git Review

umputun/git-review

Source umputun/cc-thingz ↗License MIT

Interactive git diff annotation review. Generates a cleaned-up diff, opens in editor for user annotations, and addresses feedback in a loop. Activates on "git review", "review changes", "review my changes", "annotate changes", "interactive review".

SkillScore55Maintained

Automatic

Coding pack

Last verified 8/20/2026

What it changes

Passed 10 of 19 test cases with the skill, and 9 of 19 without it.

Without skill45%

With skill55%

Checks it passed that the model alone missed

Runs git-review.py with the --test flag.
Runs git-review.py with the --clean flag.
States that agterm version 0.20.0 or higher is required.

and 1 more in the full report

4 fixed8 passed either way8 still failing2 broke

Pass-rate lift: +9 pp
Tokens: +10%
Agent turns: 0%
Response time: -56%

Model gemini-3.6-flashMeasured 8/20/2026v212 of 22 cases passed with skill · 19 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/umputun-git-review/SKILL.md https://app.decimal.ai/s/umputun-git-review/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add umputun-git-review, 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/umputun-git-review/ and pins it in .decimal/skills.lock

decimalai skills add umputun-git-review

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

curl -fsSL --create-dirs -o .claude/skills/umputun-git-review/SKILL.md https://app.decimal.ai/s/umputun-git-review/SKILL.md

Raw file: /s/umputun-git-review/SKILL.md ↗ · machine-readable summary at /s/umputun-git-review.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 4

Prompt

Which version of agterm is required to support pane-scoped overlays during interactive diff sessions?

What was checked, without and with the skill
Checked	Without skill	With skill
States that agterm version 0.20.0 or higher is required.	Missed	Passed

case-15 · gemini-3.6-flash · 8/20/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md102 lines2 filesincludes scripts

Git Review

Interactive annotation-based code review using editor overlays.

Activation Triggers

"git review", "review changes", "review my changes"
"annotate changes", "interactive review"
"review diff", "annotate diff"

How It Works

Script generates a cleaned-up diff file (friendly headers, no technical noise)
Opens in $EDITOR via agterm overlay, tmux popup, kitty overlay, or wezterm split-pane
User adds annotations (comments, change requests) directly in the file
Script returns user's annotations as a git diff
Claude reads annotations, fixes code in the real repo
Script regenerates fresh diff (reflecting fixes), opens again
Loop until user closes editor without changes

Workflow

Step 1: Run the script

${CLAUDE_PLUGIN_ROOT}/skills/git-review/scripts/git-review.py [base_ref]

No arguments: auto-detects uncommitted changes or branch vs default branch
With argument: diffs against the specified ref (branch, tag, commit, HEAD~3)

Step 2: Process annotations

If the script produces output (stdout), the user made annotations. The output is a git diff showing what the user added/changed in the review file.

Read the diff carefully:

Added lines (+): user's annotations, comments, or change requests
Removed lines (-): user wants something removed or changed
Modified lines (- then +): user replaced text to show desired change

Track record

Benchmark

10 / 19

test cases passed, vs 9 / 19 without

Adoption

Users: 1
Times used: 13

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/17/2026

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

umputun / cc-thingz

plugins/review/skills/git-review/SKILL.md

View on GitHub ↗

License MITImported 8/17/2026Version v2Bundled 1 file · scripts

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

Ready to supercharge your AI agents?

See it in action

What's inside

Git Review

Activation Triggers

How It Works

Workflow

Step 1: Run the script

Step 2: Process annotations

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills