Agent skill

simulate

How to simulate a Lagune command end to end so the user sees both the process and the results in chat. Use when the user asks to simulate, demo, preview, run, or see in action any lagune command. Read this before attempting any such simulation.

wellwelwelgithub.com/wellwelwelGitHub ↗
claude-codecodexcopilotcursorships scriptsMIT
Install
npx skills add wellwelwel/lagune --skill simulate --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 19
SKILL.md size: 11 KB
Bundled scripts: yes
Path: .claude/skills/simulate/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 89
Language: TypeScript

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Simulating a Lagune command This skill exists because simulating a command is deceptively easy to get wrong in a way that wastes the user's time and trust. Hard sessions produced four non-negotiable rules and a method. Follow them exactly. Use this skill whenever the user asks to "simulate", "demo", "show in practice", "run", or "see in action" any `/lagune.*` command (`charter`, `detect`, `plan`, `harden`, `verify`), or to preview how a command behaves before shipping it. ## Before you start (mandatory) Do not begin a simulation, build a scenario, or copy a fixture until both of these are settled, in this order: 1. **The user must tell you which Lagune command to simulate.** This is required, never assume or pick one. If the user has not named a command (`charter`, `detect`, `plan`, `harden`, or `verify`), ask which one before doing anything else. If they named more than one, confirm the order you will run them in. 2. **Then suggest the fixture, enumerated, and let the user choose.** Once the command is known, list the available fixtures (from `.claude/skills/simulate/fixtures/`) as a numbered list, each with a one-line description of its scenario, and ask the user to pick one b

What's inside
Steps it walks through
  1. Before you start (mandatory)
  2. Why this skill exists (read this first)
  3. The four hard rules
  4. Rule 1: Run the scenario under ./temp
  5. Rule 2: Expose prompts and responses as fenced code blocks IN the chat message
  6. Rule 3: You are the command, so follow its spec to the letter
  7. The method, step by step
  8. Honesty checks before you present anything
Ships with 18 files
  • fixtures/image-upload-service/package.json
  • fixtures/image-upload-service/src/lib/fetch-remote.js
  • fixtures/image-upload-service/src/lib/thumbnail.js
  • fixtures/image-upload-service/src/lib/transcode.js
  • fixtures/image-upload-service/src/routes/avatar.js
  • fixtures/image-upload-service/src/routes/import.js
  • fixtures/image-upload-service/src/routes/photos.js
  • fixtures/image-upload-service/src/server.js
  • fixtures/image-upload-service/uploads/.gitkeep
  • fixtures/template-toolkit/bin/cli.js
  • fixtures/template-toolkit/package.json
  • fixtures/template-toolkit/src/index.js
  • fixtures/template-toolkit/src/plugin.js
  • fixtures/template-toolkit/src/plugins/markdown.js
  • fixtures/template-toolkit/src/plugins/slug.js
  • fixtures/template-toolkit/src/remote.js
  • fixtures/template-toolkit/src/render.js
  • fixtures/template-toolkit/src/validate.js
Commands it runs
rm -rf ./temp && mkdir -p ./temp
cp -R .claude/skills/simulate/fixtures/<name>/. ./temp/
More from lagune
All skills →
About this skill
What does the simulate skill do?

How to simulate a Lagune command end to end so the user sees both the process and the results in chat. Use when the user asks to simulate, demo, preview, run, or see in action any lagune command. Read this before attempting any such simulation.

How do I install it?

Run `npx skills add wellwelwel/lagune --skill simulate --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From wellwelwel/lagune, a repository with 89 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going