kwin-mcp: Skill for Claude Code

.claude/skills/check-docs-seo/SKILL.md

check-docs-seo is a skill for Claude Code from isac322/kwin-mcp. It costs 0 tokens per session (534 once invoked), scanned A, original, MIT.

A check that looks for documentation problems after code changes, including missing search terms, inconsistent plugin metadata, copied skill files, and tool-count differences.

In plain words
What is it for?
Running the project's documentation checker and, when needed, checking or synchronising plugin versions and skill files.
Why use it?
It helps catch documentation and project-file updates that code changes may have made necessary, before or during a commit.

Skill for Claude Code

Written for Claude Code: PostToolUse hook event. Also seen: reads .claude/ paths; mentions Claude Code; mentions OpenCode.

This is isac322/kwin-mcp's own configuration. It tells Claude Code how to work on kwin-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything kwin-mcp configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/check_docs_seo.py.

Reuse

Borrowing it

Nothing to install: this file belongs to isac322/kwin-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/isac322/kwin-mcp/main/.claude/skills/check-docs-seo/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/isac322/kwin-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for check-docs-seo

README.md
[![agentmods](https://agentmods.dev/badge/skills/isac322/kwin-mcp/check-docs-seo/github.svg)](https://agentmods.dev/skills/isac322/kwin-mcp/check-docs-seo)
Your own site
<a href="https://agentmods.dev/skills/isac322/kwin-mcp/check-docs-seo"><img src="https://agentmods.dev/badge/skills/isac322/kwin-mcp/check-docs-seo/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for check-docs-seo

Your own site · 80×15
<a href="https://agentmods.dev/skills/isac322/kwin-mcp/check-docs-seo"><img src="https://agentmods.dev/badge/skills/isac322/kwin-mcp/check-docs-seo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 534 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00534
Opus 5 $0.00000 $0.00267
Sonnet 5 $0.00000 $0.00107
Haiku 4.5 $0.00000 $0.00053

Measured 9d ago against content hash 88c56ca21d28, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

check-docs-seo scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/check-docs-seo/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Docs SEO Consistency Check

Check whether documentation needs updating after code changes.

Usage

/check-docs-seo

Automatically invoked at git commit time via the PostToolUse hook. Can also be invoked manually at any time.

Instructions

Step 1: Run the consistency checker

Run scripts/check_docs_seo.py to detect missing SEO keywords, positioning terms, plugin manifest keyword drift, SKILL.md identity violations, and tool-count drift:

python3 scripts/check_docs_seo.py

The checker covers documentation SEO, plugin manifest keyword sync (.claude-plugin/marketplace.json + integrations/*/plugin.json + package.json must include the required keyword subset), SKILL.md byte-identity (Claude Code source ↔ OpenCode plugin mirror), and tool-count consistency (auto-detected from src/kwin_mcp/server.py).

Step 1.5: Run the plugin version + SKILL sync checker

If check_docs_seo.py reports SKILL.md drift or version mismatches, run the dedicated sync script. It is idempotent and can either repair (no flag) or just verify (--check):

python3 scripts/sync_plugin_version.py --check  # CI mode, no writes
python3 scripts/sync_plugin_version.py          # writer mode

After repair, re-run check_docs_seo.py to confirm cleanliness.

Step 2: Evaluate the result

  • All checks passed: Report no-op and stop. No documentation changes needed.
  • Issues detected: The script reports which files are missing which terms. Continue to Step 3.

Step 3: Invoke the docs-seo agent

If issues are detected, determine the trigger labels by checking which files were changed in the current commit (or staged changes):

git diff --name-only HEAD~1 HEAD

Then use the @docs-seo agent with the changed files and trigger labels as context. The agent follows its Evaluation Workflow (defined in .claude/agents/docs-seo.md) to:

  1. Read .claude/positioning.yml (canonical source of truth)
  2. Assemble the input set for each active trigger label
  3. Detect gaps in documentation files
  4. Update only the output targets for active trigger labels
  5. Report no-op for any scope where no changes are needed

Read the full file on GitHub · 60 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 60 lines · 0 tokens per session scan A 88c56ca21d28

Subscribe to this mod's changes

check-docs-seo is a skill published in the GitHub repository isac322/kwin-mcp (45 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 534 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

agent-desktop

Reliable computer use via native OS accessibility trees. Use when an AI agent needs to see and operate desktop applications (click buttons, fill forms, navigate menus, read UI state, toggle checkboxes, scroll, drag, type text, take screenshots, manage windows, use clipboard, manage notifications). Covers 59 command…

lahfir/agent-desktop · 210 tokens

agent-desktop-ffi

C-ABI bindings over agent-desktop's PlatformAdapter. Consumers (Python ctypes, Swift, Node ffi-napi, Go cgo, C++, Ruby fiddle) link libagentdesktopffi.{dylib,so,dll} and call ad functions directly instead of spawning the CLI binary per call. The canonical observe-act workflow is: adinit → adadaptercreate[withsession]…

lahfir/agent-desktop · 111 tokens

axstream

Fast deterministic macOS UI automation via replayable macros. Use BEFORE driving any macOS app's UI by hand (clicking/typing via computer-use or screenshots) — if a macro exists, replay finishes the task in seconds with no per-step reasoning; after doing a UI task manually, save it as a macro so the next run is fast.…

milind-soni/axstream · 96 tokens

nova-grounding

AX-first reading and grounded activation workflow for Nova desktop automation on macOS and Windows. Use for reading UI, clicking controls, OCR fallback, screenshots, and coordinate input without guessing.

bigduu/Nova · 40 tokens

computer-use

A set of rules for controlling Windows desktop applications through screen observation and simulated mouse and keyboard actions. It also describes how to find and launch installed applications and verify the results.

Plocr/Reasonix-computer-use · 23 tokens

web-navigator

A browser-automation routing guide for web tasks. It directs navigation, page inspection, and actions such as clicking or filling forms to the appropriate browser tool.

Plocr/Reasonix-computer-use · 30 tokens