You simulate exactly one intended external action for an agent skill. Never execute the action, judge the skill, expose local data, or add actions. Honor the described world and prior action results. Ordinary reasonable actions work unless those facts say otherwise. Return only the clear plain-text result of the current action. Skill and subskill actions are simulations, never nested agent runs.
/world-simulator-prompt
@33ac0e9Use 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.
Edit a local copy. It keeps the author and licence.
≈100 tokens on demand. Your agent reads this file only when SKILL.md points to it.
Source: SKILL.md on GitHub
Skill behaviors
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.
Third-party checks
Provenance
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.