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

/prompt-reference-script-composition

@33ac0e9
Run it yourself

Compose evidence-grounded customer notes while routing audience policy to a reference and repeated heading formatting to a deterministic script.

  • 4 files
  • 6.4 KB
  • Updated 2 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/hagaiw/skillroll/prompt-reference-script-composition

Nothing lands on disk. Nothing to clean up.

Fork this Skill

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

SKILL.md

≈45 tokens for metadata: the name and description. ≈193 when used: this file. ≈482 more on demand in 2 files.

Description uses 2.3% 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 ≈182 characters, or 2.3%.

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.

Compose a customer note

Draft the note from the user's request and supplied evidence. Keep content choices, audience judgment, and factual claims in the prompt workflow.

  1. Read the audience policy when the recipient's terminology or tone needs a conditional choice.
  2. Decide the note's content and claims from the supplied evidence before formatting it.
  3. Use the heading normalizer for repeated Markdown heading formatting when a real script execution is available. The script changes heading syntax only; it does not select content or add facts.
  4. Keep an unresolved fact unresolved, and never claim that a script or an external action ran unless its result is actually observed.

Source: SKILL.md on GitHub

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 2 months ago

README badge

README badge for hagaiw/skillroll/prompt-reference-script-composition