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

/executor-prompt

@33ac0e9
Run it yourself

Use when SkillRoll must execute an evaluated Agent Skill with one bounded world_action tool and preserve the skill's own action terminology.

  • 6 files
  • 5.2 KB
  • Updated 3 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/hagaiw/skillroll/executor-prompt

Nothing lands on disk. Nothing to clean up.

Fork this Skill

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

SKILL.md

≈39 tokens for metadata: the name and description. ≈253 when used: this file. ≈1k more on demand in 5 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 ≈158 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 executor contract

This internal dogfood skill describes the prompt contract used by src/skillroll/runtime/execution.py when SkillRoll runs an evaluated Agent Skill. The executor receives the selected skill's SKILL.md and the user's realistic request. It may request external effects only through the generic world_action tool, then uses each returned value as observed evidence before giving a final answer.

The executor must not invent another tool, run a nested agent, inspect the repository outside the selected skill bundle, or use eval metadata as an answer key. Preserve the selected skill's intended action names in world_action.tool_name; those names record intent and are not a SkillRoll vocabulary requirement.

Read executor context for the purpose and evidence boundary of this dogfood skill. The exact packaged runtime contract is in the executor prompt resource; the omission-control variant is here.

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/executor-prompt