Ready to supercharge your AI agents?

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

Get Started Free →

Verify Change · fengshao1227 | DecimalAI

code reviewby fengshao1227

Verify Change

fengshao1227/verify-change

Source fengshao1227/ccg-workflow ↗License MIT

变更校验关卡。分析代码变更，检测文档同步状态，评估变更影响范围。当用户提到变更检查、文档同步、代码审查、提交前检查、diff分析时使用。在设计级变更、重构完成时自动触发。

SkillScore96Maintained

Automatic

Coding pack

Last verified 8/9/2026

What it changes

Passed 22 of 23 test cases with the skill, and 15 of 23 without it.

Without skill65%

With skill96%

Checks it passed that the model alone missed

Evaluates documentation synchronization status.
Requires recording technical constraints in DESIGN.md.
Evaluates documentation synchronization for modified files.

and 8 more in the full report

8 fixed14 passed either way0 still failing1 broke

Pass-rate lift: +30 pp
Tokens: +33%
Agent turns: 0%
Response time: -43%

Model gemini-3.6-flashMeasured 8/9/2026v122 of 23 cases passed with skill

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/fengshao1227-verify-change/SKILL.md https://app.decimal.ai/s/fengshao1227-verify-change/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add fengshao1227-verify-change, 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/fengshao1227-verify-change/ and pins it in .decimal/skills.lock

decimalai skills add fengshao1227-verify-change

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

curl -fsSL --create-dirs -o .claude/skills/fengshao1227-verify-change/SKILL.md https://app.decimal.ai/s/fengshao1227-verify-change/SKILL.md

Raw file: /s/fengshao1227-verify-change/SKILL.md ↗ · machine-readable summary at /s/fengshao1227-verify-change.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

We are integrating our repository change audit into an automated CI pipeline. We need the change analyzer script to inspect staged files and return raw structured data rather than formatted text. Which command flags should be passed?

What was checked, without and with the skill
Checked	Without skill	With skill
Includes the --json flag when invoking the analysis script.	Missed	Passed
Includes the --mode staged flag when invoking the analysis script.	Missed	Passed

case-04 · gemini-3.6-flash · 8/9/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md129 lines2 filesincludes scripts

⚖ 校验关卡 · 变更校验

核心原则

变更 = 代码改动 + 文档更新 + 理由记录
无理由的变更是隐患，无记录的变更是灾难
每一次变更都是历史，每一个决策都要留痕

自动分析

运行变更分析脚本（跨平台）：

# 在 skill 目录下运行
node scripts/change_analyzer.js                    # 分析工作区变更（默认）
node scripts/change_analyzer.js --mode staged      # 分析暂存区变更
node scripts/change_analyzer.js --mode committed   # 分析已提交变更
node scripts/change_analyzer.js -v                 # 详细模式
node scripts/change_analyzer.js --json             # JSON 输出

检测能力

自动检测项

检测项	说明
文件分类	自动识别代码/文档/测试/配置文件
模块识别	识别受影响的模块
文档同步	检测代码变更是否同步更新文档
测试覆盖	检测代码变更是否有对应测试
影响评估	评估变更规模和影响范围

触发警告的情况

⚠️ 代码变更 > 50 行但 DESIGN.md 未更新
⚠️ 代码变更 > 30 行但无测试更新

Track record

Benchmark

22 / 23

test cases passed, vs 15 / 23 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 — 8/3/2026

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

fengshao1227 / ccg-workflow

templates/skills/tools/verify-change/SKILL.md

View on GitHub ↗

License MITImported 9/1/2026Version v1Bundled 1 file · scripts

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

telagod/analyzing-changesAnalyzes code changes, detects documentation drift, and evaluates change impact scope. Use when reviewing diffs, checking doc sync, or running pre-commit analysis. Automatically triggered after design-level changes or refactoring.Close match+35 pp pass-rate lift

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