Repo audit
Полная коллекция скиллов Kimi (267 built-in + 7 plugin skills), выгруженная из сандбокса агента
npx -y skills add serejaris/kimi-skills --skill repo-auditAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 20 days oldThe repository was created 20 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Deep analysis of Git history: identify frequently changed hotspot files, analyze code ownership by contributor, and scan for leaked secrets. Triggered when users ask about Git analysis, code hotspots, who owns what code, secret scanning, security audits of commit history, or optimizing code review assignments.
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
3.2 KB, 714 tokens by cl100k_base, as published. Nobody here has run it
Repo Audit — Deep Analysis of Git History
Perform three-dimensional analysis on a Git repository: hotspot file detection, code ownership analysis, and secret leak scanning.
Feature Overview
1. Hotspot File Analysis (scripts/hotfiles.sh)
Identify the most frequently changed files in a repository to help spot:
- High-risk code areas (frequent changes = potential instability)
- Files that deserve extra attention during code review
- Modules that may need splitting or refactoring
Usage:
bash scripts/hotfiles.sh [options]
| Option | Description | Default |
|---|---|---|
--repo PATH | Repository path | Current directory |
--top N | Show top N files | 20 |
--since DATE | Start date (e.g. 2024-01-01) | None |
--until DATE | End date | None |
--author AUTHOR | Filter by author | None |
--format FORMAT | Output format: table / csv / json | table |
2. Code Ownership Analysis (scripts/ownership.sh)
Analyze actual code ownership, reporting for each contributor within the specified scope:
- Commit count and percentage
- Lines changed (additions/deletions)
- Last active date
Usage:
bash scripts/ownership.sh [options]
| Option | Description | Default |
|---|---|---|
--repo PATH | Repository path | Current directory |
--path SUBPATH | Analyze a specific subdirectory or file | Entire repo |
--top N | Show top N contributors | 10 |
--since DATE | Start date | None |
--format FORMAT | Output format: table / csv / json | table |
3. Secret Leak Scanning (scripts/secret-scan.sh)
Scan the full Git history (including deleted commits) for common secrets and sensitive information:
- AWS Access Key / Secret Key
- GitHub / GitLab / Slack Tokens
- SSH Private Keys
- Generic API Keys, passwords, and secret patterns
Usage:
bash scripts/secret-scan.sh [options]
| Option | Description | Default |
|---|---|---|
--repo PATH | Repository path | Current directory |
--branch BRANCH | Scan a specific branch | All branches |
--since DATE | Start date | None |
--format FORMAT | Output format: table / csv / json | table |
--severity LEVEL | Minimum severity level: low / medium / high | low |
Use Cases
- Security audits: Scan history for leaked secrets before deploying to production
- Code review optimization: Identify hotspot files and prioritize reviewing high-risk areas
- Team collaboration: Understand who knows which parts of the code best, and assign reviews accordingly
- Tech debt assessment: Frequently changed files are strong candidates for refactoring
Dependencies
git(>= 2.20)bash(>= 4.0)- Standard Unix utilities:
awk,sort,head,grep
No additional dependencies or paid APIs required.
Gives 0 of the 12 instructions most research analysis skills give in 714 tokens
Counted across 1,063 of the 1,754 authors here whose files we hold, read 2026-08-06
- generate a markdown reportin 32 of 1063, across 17 files
- cite each claim's sourcein 31 of 1063, across 14 files
- define the ideal customer profilein 20 of 1063, across 2 files
- search for companies matching the criteriain 20 of 1063, across 2 files
- assign a fit score from one to tenin 20 of 1063, across 2 files
- format results in a scannable markdown templatein 20 of 1063, across 2 files
- analyze the codebase to understand the productin 19 of 1063, across 1 file
- ask clarifying questions about the value propositionin 19 of 1063, across 1 file
- look for signals of immediate needin 19 of 1063, across 1 file
- identify the target decision maker rolein 19 of 1063, across 1 file
- suggest a personalized contact strategyin 19 of 1063, across 1 file
- provide conversation starters for outreachin 19 of 1063, across 1 file
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.