Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Docs

ASecurity

Code documentation agent — write/update docs with /docs write, check status with /docs check. Minimal code blocks, reference pointer based.

207 stars
0 votes
0 copies
1 views
Added 9/4/2026
documentationgodocumentation

Security Analysis

A100/100

Scanned 9/4/2026

Install to Claude Code

$npx -y skills add NeverSight/skills_feed --skill docs --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Docs?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Docs
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/neversight-docs/badge)](https://www.skillsdirectory.com/skills/neversight-docs)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: docs
version: 0.0.2
category: productivity
description: "Code documentation agent — write/update docs with /docs write, check status with /docs check. Minimal code blocks, reference pointer based."
argument-hint: "<write|check> [topic] [code-path]"
---

## Input

```text
$ARGUMENTS
```

## Instructions

### Document Root

Documents managed by this skill are stored under `docs/generated/`.
They are organized by category subdirectories: `docs/generated/<category>/<slug>.md`

Documents outside `docs/generated/` are considered manually written and must never be modified.

### Tool Usage Rules

Always use the tools below for document search and management. Do not open files one by one — search smartly using patterns.

| Purpose | Tool | Usage |
|---------|------|-------|
| Find document files | **Glob** | `docs/generated/**/*.md` pattern to get full document list |
| Search frontmatter | **Grep** | Filter by `title:`, `category:` patterns |
| Read existing docs | **Read** | Read frontmatter + body (only necessary documents) |
| Verify code references | **Glob** | Check if file paths in `code_refs` exist |
| Create documents | **Write** | Create new document files |
| Update documents | **Edit** | Update specific parts of existing documents |
| Scan INDEX | **Read** | Read `docs/generated/INDEX.md` for category structure and document list |

### Subcommand Routing

The first word of `$ARGUMENTS` determines the subcommand.

| First word | Action |
|------------|--------|
| `write` | Read and execute `references/write-procedure.md` |
| `check` | Read and execute `references/check-procedure.md` |
| (none / help) | Print usage below and stop |

**When run without a subcommand:**

```
## docs

Code documentation agent — systematically records development knowledge.

### Commands

| Command | Description |
|---------|-------------|
| write <topic> [code-path] | Write or update a document on the topic |
| check | Check all document status (stale, broken refs, orphan docs) |

### Features

- Uses `[symbol](file-path)` reference pointers instead of code blocks
- Organized by category folders under `docs/generated/`
- INDEX.md based document indexing
```

### Argument Parsing

Parse the remaining arguments after removing the subcommand keyword (`write` / `check`).

**`write` arguments:**
- First argument: **topic** (required) — title/topic of the document
- Second argument: **code-path** (optional) — path to related code (file or directory)

Examples:
- `/docs write "auth flow design"` → topic only
- `/docs write "auth flow" src/auth/` → topic + code-path

**`check` arguments:** None.

### Document Writing Principles

1. **Minimize code blocks**: Do not include code snippets directly in documents. Instead, use markdown links in the form `[symbol](project-root-relative/file-path)` as references.
2. **Focus on design intent**: Record "why it was done this way" rather than "what was done".
3. **Protect manual documents**: Never modify documents outside `docs/generated/`.

Attribution

NeverSightNeverSight
View sourceMore from NeverSight →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Context Fundamentals

Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.

179001 votes

release-notes

Draft release notes and changelog entries from git history or merged PRs between two refs (tags/SHAs/branches), including breaking changes, migrations, and upgrade steps. Use when the user asks for release notes, changelog updates, or a GitHub Release draft.

1301 votes

docs-style-guide

Documentation style guide enforcer by @planetabhi. Applies and reviews the writing style guide when authoring or editing product documentation and tutorials. Use to check prose for voice, tense, word choice, inclusive language, formatting, code block, UI, Markdown, and number/date conventions.

11 votes

Caveman Help

Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".

1023330 votes

How It Works

Explain how claude-mem captures observations, when memory injection kicks in, and where data lives. Use when the user asks "how does claude-mem work?" or "what is this thing doing?".

942310 votes
View all in documentation →