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

Start

ASecurity

Open the Loanword trainer — FSRS flashcard review in the browser at localhost:4747. Use when the user asks to review vocabulary, practise, or open the trainer.

5 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgobashnode

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add MarcSky/loanword --skill start --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Start?

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

Security grade badge for Start
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/marcsky-start/badge)](https://www.skillsdirectory.com/skills/marcsky-start)

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

Download Zip
Files
SKILL.md
---
name: start
description: Open the Loanword trainer — FSRS flashcard review in the browser at localhost:4747. Use when the user asks to review vocabulary, practise, or open the trainer.
disable-model-invocation: false
allowed-tools: Bash, Read, Write
---

# /loanword:start — the trainer

One command: it serves the trainer and opens the browser itself. It exits by
itself if the port is already serving a trainer.

```bash
CLAUDE_PLUGIN_DATA="${CLAUDE_PLUGIN_DATA}" node "${CLAUDE_PLUGIN_ROOT}/scripts/serve.mjs"
```

Use `run_in_background: true` — the server has to stay up while the user works
through the deck. It closes itself after 30 minutes with no requests, so a
finished session never leaves the port held.

Say it in one line: opened http://localhost:4747 — `space` reveals the answer,
`1–4` grade, `esc` quits.

To close it before then:

```bash
CLAUDE_PLUGIN_DATA="${CLAUDE_PLUGIN_DATA}" node "${CLAUDE_PLUGIN_ROOT}/scripts/serve.mjs" stop
```

`LOANWORD_PORT` overrides the port, `--idle=<minutes>` the timeout (`0` disables
it), `--no-open` skips the browser. The server binds `127.0.0.1` only.

If there are no cards the UI says so itself. Do not check that up front and do
not run build unless asked.

## Interface language

The trainer renders in the user's **native** language when a dictionary exists.
Check once, after opening the browser — never before, and never twice in a
session:

```bash
CLAUDE_PLUGIN_DATA="${CLAUDE_PLUGIN_DATA}" node "${CLAUDE_PLUGIN_ROOT}/scripts/i18n.mjs" audit "$(CLAUDE_PLUGIN_DATA="${CLAUDE_PLUGIN_DATA}" node "${CLAUDE_PLUGIN_ROOT}/scripts/store.mjs" config | node -pe 'JSON.parse(require("fs").readFileSync(0)).native')"
```

- Clean, or the native language is `en`: say nothing.
- **No dictionary at all:** offer in one line — "the trainer is in English;
  want me to translate it into <language>? about a minute, nothing leaves the
  machine". Only if they say yes:
  1. `CLAUDE_PLUGIN_DATA="${CLAUDE_PLUGIN_DATA}" node "${CLAUDE_PLUGIN_ROOT}/scripts/i18n.mjs" keys` for the exact list,
  2. translate every key yourself and Write
     `${CLAUDE_PLUGIN_ROOT}/ui/i18n/<code>.json`,
  3. re-run `audit <code>` and fix what it reports.

  Keep `{placeholders}` and inline HTML tags exactly as they appear in the key.
  Plural keys look like `card|cards` and take an object of CLDR categories —
  see [`ui/i18n/README.md`](../../ui/i18n/README.md).
- **Dictionary exists but `audit` reports missing keys:** mention the count in
  one line and offer to fill them. Do not rewrite entries that are already
  translated.

Never offer this twice, and never block opening the trainer on it.

Attribution

MarcSkyMarcSky
View sourceMore from MarcSky →
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

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 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', ...

686011 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.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →