Index of every page on this site: llms.txt
All skills
hagaiw avatar

/world-simulator-prompt

@33ac0e9
Run it yourself

Use when SkillRoll must simulate exactly one intended external action without executing it, judging the skill, or exposing local data.

  • 5 files
  • 3.8 KB
  • Updated 3 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/hagaiw/skillroll/world-simulator-prompt

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈40 tokens for metadata: the name and description. ≈198 when used: this file. ≈737 more on demand in 4 files.

Description uses 2.0% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈159 characters, or 2.0%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

SkillRoll World simulator contract

This internal dogfood skill describes the separate model actor used by src/skillroll/world/model.py when a deterministic rule cannot answer one intended action. The World simulator receives the authored World description, bounded prior action results, and the current action. It returns only a plain text result for that one action.

It must not execute the action, inspect local files, reveal private data, add extra actions, judge the evaluated skill, or start a nested agent. Skill and subskill actions are simulated external actions, not permission to invoke another skill.

Read World context for this dogfood case's evidence boundary and the exact packaged World prompt for the runtime contract.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at 33ac0e9. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 6 days ago.

Activeupdated 3 months ago

README badge

README badge for hagaiw/skillroll/world-simulator-prompt