Skip to content
Agentmart
Submit a tool

code-analyze

Record and update project documentation in a readable state for both humans and AI.

Skill by hidao80

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/hidao80-code-analyze

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Record and update project documentation in a readable state for both humans and AI.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/code-analyze

What's inside

Skill name
code-analyze
Description
Record and update project documentation in a readable state for both humans and AI.
License
MIT
Instructions
64 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Details

- [Details](#details)
  - [1. Traceability \& Integrity](#1-traceability--integrity)
  - [2. Documentation Hygiene](#2-documentation-hygiene)
  - [3. Quality of Information](#3-quality-of-information)
  - [Target files](#target-files)

## 1. Traceability & Integrity

- **Commit Hash**: Append the current commit hash as the final line of every modified/created file.
- **Source of Truth**: Always prioritize test code (unit/integration) over implementation when detecting discrepancies.
- **Verification**: If a discrepancy is found between layers (e.g., DB vs. API), document it as a "Known Bug" or "Inconsistency".

## 2. Documentation Hygiene

- **Pruning**: Completely delete any entries, notes, or TODOs related to files, components, or features that no longer exist in the codebase.
- **Structure**: Maintain a clean directory structure under `.claude/analyzed/{CATEGORY_NAME}.md`. Organize your knowledge using Markdown files and a directory structure, and create a mind map. You may include linkable files.
- **Front matter**: Every generated `.md` file must include the standard front matter:  

    ```md
    ---
    name: analyzed-{basename}
    description: {State the purpose in one sentence.}
    type: analysis
    commit-hash: {target commit hash}
    ---
    ```

## 3. Quality of Information

- **No Hallucinations**: Clearly state if information is "Unconfirmed", "Speculative", or "Unknown".
- **Speculation Protocol**: When making suggestions/speculations, provide concise options and a recommendation level (1-5) for each.
- **Clarity**: Use Mermaid notation for all diagrams (ER, Flow, Use Case).
- **Simplicity**: Remove descriptive/boilerplate text from configuration files; provide only summaries or references.

## Target files

**Excution Rules**:

- Do not create or update in the following order.
- Update the memory after each step is completed.

| Step No. | Category Name | Target topics |
| --- | --- | --- |
| 1 | dependencies | Library name, version, license, vulnerability, update status. |
| 2 | infrastructures | CD/CI and IaC. |
| 3 | databases | Connection Informations, Architecture, Migration, List of tables by category and their summaries, Summary of domain areas. |
| 4 | screens | Entry Point, Default Route, URL Pattern, Controller inheritance hierarchy, Base class, View File Convention, Basic template files. |
| 5 | configurations |Main configuration files, Environment-specific settings. |
| 6 | components | Application Structure, Custom Vendor Namespace. |
| 7 | utilities | Global helper Classes, functions, Traits. |
| 8 | performance | Performance check, Identify processing time, number of parallel processes, and bottlenecks. |
| 9 | known_bugs | Security issues, Architectural/design issues, Compatibility issues, Notes on analytical limitations. |
| 10 | security | **[Required]**: Injection (SQL/XSS/Command/Path traversal), Secret & Credential leakage (hardcoded keys, .env commits), Authentication & Authorization (unprotected endpoints, bypass), **[Recommended]**: CORS / Security Headers (CSP, HSTS, X-Frame-Options), Data Exposure (sensitive fields in API responses, stack traces in errors), Dependency Vulnerabilities (known CVEs in lockfile), **[Optional]**: Rate Limiting / Brute-force protection,  File Upload validation (MIME type, path restriction), Transport Security (TLS version, cipher suites). |
| 11 | test | The content of the test that will be provided. |
| 12 | development-workflow | Development Workflow. |
| 13 | overview | Project Overview, Technology stack, Repository structure, Request Flow, Domain configuration, scale, Number of steps (approximate number of lines), Main features, Development Workflow. |
| 14 | notes | The content of the test that will be provided. |
| 15 | todo | Security (high priority), Test, Database, Code Quality, Infrastructure, Developer Experience, Performance. |
| 16 | naming_convention | Variable, Table name, Column name, Function name, Class name. |
| 17 | use_cases | Use case diagram (using Mermaid notation). |

From hidao80/ai-agent-plugins, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jun 24, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from hidao80

Cite this page

code-analyze skill. Agent Mart. https://agentmart.dev/skills/hidao80-code-analyze (last updated 2026-10-24)