Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
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
  • Authors
  • 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
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Check Skills

ASecurity

Status and management of the master-of skill-gate system: shows the brief report (per-gate counts, what is broken, token savings), and files newly discovered skills into the right gate. Invoke for '현황', '점검해줘', 'what skills are gated', 'why is X disabled', or when the SessionStart hook says components are unclassified. Also the first-time setup guide when mo CLI is not yet configured.

3 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsgobash

Works with

climcp

Security Analysis

A100/100

Scanned 9/22/2026

$npx -y skills add devrudals/master-of --skill check-skills --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Check Skills?

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

Security grade badge for Check Skills
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/devrudals-check-skills/badge)](https://www.skillsdirectory.com/skills/devrudals-check-skills)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: "check-skills"
description: "Status and management of the master-of skill-gate system: shows the brief report (per-gate counts, what is broken, token savings), and files newly discovered skills into the right gate. Invoke for '현황', '점검해줘', 'what skills are gated', 'why is X disabled', or when the SessionStart hook says components are unclassified. Also the first-time setup guide when mo CLI is not yet configured."
allowed-tools: Read, Bash
---

# check-skills

The engine is the `mo` CLI. Everywhere below, `mo` means the wrapper at
`~/.master-of/mo` (written by `claude-setup` — see Setup below).

Never read `registry.json` directly and never edit it by hand — it is large,
and every question below has a CLI command that reads it correctly.

---

## 1. Status (「현황」, 「점검해줘」)

```bash
~/.master-of/mo status
```

Show the output as-is. It lists broken items (disabled plugins whose gates
still offer them, dead MCP servers) with the fix for each.

### PROACTIVE TOKEN GATEKEEPER DUTY (CRITICAL)
Do NOT stop passively after showing the brief report!
Run:
```bash
~/.master-of/mo unparked --json
~/.master-of/mo unclassified --json
```
If unparked skills > 0 or Always-on token consumption is heavy (saving < 70%):
1. **Warn the user explicitly** about the exact wasted token count (e.g. 30,000+ tok loaded every session).
2. **PROACTIVELY ASK THE USER** to batch-park raw skills into `skills-library` (`mo park --all`) to instantly achieve 85%+ token savings.
3. Upon user approval, run `~/.master-of/mo park --all` and show the updated savings!

## 2. Unclassified components

The SessionStart hook reports how many components still carry the scanner's
category guess. To file them:

1. `~/.master-of/mo unclassified --source claude --json` — each entry has
   `name`, `type`, `category` (the guess), `description`, `rel_path`, `source`.
2. For each entry decide, from its description, which gate it belongs to:
   `design` / `dev` / `research` / `stock` / `planning` / `pipelines`.
   Rules of thumb:
   - An end-to-end workflow that runs a whole project phase → `pipelines`
     (needs `--domain <gate>` to surface from that gate's index too)
   - GSD/planning skills → `planning`, add `--cluster <name>`
   - A skill whose only job is to call a plugin's MCP server → mark it
     `requires` that plugin; it's hollow when the plugin is disabled
   Write a one-line Korean summary for `--desc`.
3. `~/.master-of/mo classify <name> <gate> --desc "한 줄 요약" [--cluster x] [--domain gate]`
   To permanently skip a component (harness-internal helper, exact duplicate):
   `~/.master-of/mo ignore <name>`
4. After the batch: `~/.master-of/mo claude-sync` re-renders the gate indexes.

**Bulk first run (5+ entries)**: classify them all, then show a one-line plan
per gate ("design ← a, b, c; planning ← …") and get a yes BEFORE running
`claude plugin disable` or moving folders. Reorganising a full library without
asking is not routine.

### Dormancy rules (how to make a component stop loading every session)

| Component type | How to gate it |
|---|---|
| Raw skill (`~/.claude/skills/<name>/SKILL.md`) | `mo classify` → `mo claude-sync` moves it to `~/.claude/skills-library/<cat>/` |
| Raw command (`~/.claude/commands/<name>.md`) | Same — moved to `~/.claude/skills-library/<cat>/_commands/` |
| Raw agent (`~/.claude/agents/<name>.md`) | Same — moved to `~/.claude/skills-library/<cat>/_agents/` |
| Plugin-bundled component | `claude plugin disable <plugin>@<marketplace>` |
| Agents spawned by gated skills | Keep always-on (file under `always_on` with `reason: "spawn_cost"`) — reading each on every spawn costs more than their always-on tax |

## 3. Everything else

| Goal | Command |
|---|---|
| Full inventory | `~/.master-of/mo full` |
| Search | `~/.master-of/mo search <keyword>` |
| Remove a stale entry | `~/.master-of/mo remove <name>` |
| Re-scan now | `~/.master-of/mo sync && ~/.master-of/mo claude-sync` |
| Gate files up to date? | `~/.master-of/mo claude-sync` (re-renders indexes) |

## 4. Brief report

Run `~/.master-of/mo status` and show its output. That's the brief view.
For the full inventory the user asked for the whole list ("전체 보여줘"),
use the sibling skill `check-skills-all`.

### Permanent exemptions

Some plugins/skills are never gated (hook-dependent, output-style, near-zero
cost, silently-opportunistic). These are tracked in the `always_on` section
of the v2 registry — `mo status` shows them. To add one:
`~/.master-of/mo always-on <name> --reason <reason>`.

Attribution

devrudalsdevrudals
View sourceSee grades on GitHubMore from devrudals →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →