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

/finalize-agent-prompt

@f10fdb8 official
by githubgithub/awesome-copilot41k stars
5,399
Run it yourself

Finalize prompt file using the role of an AI agent to polish the prompt for the end user.

Use this Skill: https://skilld.dev/gh/github/awesome-copilot/finalize-agent-prompt

Nothing lands on disk. Nothing to clean up.

Fork this Skill

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

SKILL.md

≈28 tokens for metadata: the name and description. ≈189 when used: this file.

Description uses 1.4% 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 ≈113 characters, or 1.4%.

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.

Finalize Agent Prompt

Current Role

You are an AI agent who knows what works best for the prompt files you have seen and the feedback you have received. Apply that experience to refine the current prompt so it aligns with proven best practices.

Requirements

  • A prompt file must be provided. If none accompanies the request, ask for the file before proceeding.
  • Maintain the prompt’s front matter, encoding, and markdown structure while making improvements.

Goal

  1. Read the prompt file carefully and refine its structure, wording, and organization to match the successful patterns you have observed.
  2. Check for spelling, grammar, or clarity issues and correct them without changing the original intent of the instructions.

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.

1 warning2mo5 checks · Risk SAFE
  • Gen Agent Trust Hub2mo

    The skill is generally safe but contains a vulnerability to indirect prompt injection as it processes external prompt files without sanitization or clear boundary markers.

  • Socket2mo

    No alerts

  • Snyk2mo

    Risk: LOW · No issues

  • Runlayer8mo

    1/1 file flagged

  • ZeroLeaks7mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at f10fdb8. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 9 months ago
  • prompting
  • agent
  • llm
  • prompt-engineering
  • refinement
  • markdown
  • instruction-tuning

README badge

README badge for github/awesome-copilot/finalize-agent-prompt

Refines AI agent prompt files by applying observed best practices for structure, wording, and clarity while preserving frontmatter and markdown formatting. Targets users iterating on prompt engineering and looking to align their instructions with proven patterns for agent behavior.

Generated from the current SKILL.md.

Does this skill modify the prompt's intent or just refine the wording?
It refines structure, wording, and organization while preserving the original intent. Spelling, grammar, and clarity are corrected, but the core instructions remain unchanged.
What file formats does this skill work with?
The skill works with prompt files in markdown format, preserving front matter, encoding, and markdown structure during refinement.
What happens if I don't provide a prompt file?
The skill will ask you to provide the prompt file before proceeding with any refinement.

Generated from the current SKILL.md. These answers refresh after source changes.