Skip to main content
skill CX Codex GP ChatGPT official · OpenAI

improve-skill — Codex skill: what it does, how to install

Converts plugin-eval test reports into a concrete rewrite brief for Codex skills. Useful when you need to trim token costs and clean up frontmatter.

Install into Codex · Skills CLI (Vercel) All methods and platforms ↓
npx skills add openai/plugins --skill improve-skill -a codex
Open on GitHub

What improve-skill does

This skill restructures local Codex skills after testing them with the plugin-eval tool. It relies on output from plugin-eval analyze <skill-path> --brief-out <brief.json>. The skill splits findings into mandatory fixes and optional recommendations.

The process incorporates guidelines from skill-creator. It trims SKILL.md down, offloads large context blocks into external references or scripts, and refines trigger phrases. It also flags broken links and frontmatter issues.

Without a prior plugin-eval run, the skill has no findings to act on. After editing, verify changes with plugin-eval compare before.json after.json.

What it helps with

  • turn plugin-eval test outputs into a structured rewrite brief
  • reduce trigger and invoke token overhead
  • offload heavy context from SKILL.md into reference docs
  • fix broken links and frontmatter mistakes
  • compare evaluation scores before and after refactoring

Example prompts for the agent

  • Improve this skill based on the evaluation.
  • What should I fix first in this skill?
  • Rewrite this skill using the plugin-eval findings.

How to install improve-skill

1Skills CLI (Vercel)

npx skills add openai/plugins --skill improve-skill -a codex

2Manually: put the files in place

.agents/skills/improve-skill/SKILL.md

For all projects use ~/.agents/skills/

Step by step, with commands for each platform: Codex skills: how to install, where they live, how to call them

Questions about improve-skill

How to install improve-skill in Codex?

Run npx skills add openai/plugins --skill improve-skill in your terminal.

What does improve-skill do?

It processes plugin-eval analysis data and creates a clear action plan for skill refactoring. It helps optimize prompt length, refine trigger wording, and cut token costs.

What is required before running improve-skill?

You need plugin-eval to generate an evaluation brief first. The workflow also references instructions from skill-creator to guide the rewrite.

Source text

SKILL.md · MIT
---
name: improve-skill
description: Turn plugin-eval findings into a concrete rewrite brief for a Codex skill. Use when the user already evaluated a skill and now wants Codex to improve it, especially after asking what to fix first.
---

# Improve Skill

Use this skill after `plugin-eval` has already produced findings for a local skill.

## Workflow

1. Run `plugin-eval analyze <skill-path> --brief-out <brief.json>`.
2. Read the improvement brief and group work into required fixes versus recommended fixes.
3. Apply the `skill-creator` guidance from `/Users/benlesh/.codex/skills/skill-creator/SKILL.md`.
4. Re-run the evaluation and compare before and after outputs.

## Chat Requests To Recognize

- `Improve this skill based on the evaluation.`
- `Rewrite this skill using the plugin-eval findings.`
- `What should I fix first in this skill?`

## Focus Areas

- reduce trigger and invoke token costs
- keep `SKILL.md` compact
- move bulky details into references or scripts
- improve trigger descriptions
- fix broken links and manifest/frontmatter issues

## Commands

```bash
plugin-eval analyze <skill-path> --brief-out ./skill-brief.json
plugin-eval compare before.json after.json
```

## Reference

- `../../references/chat-first-workflows.md`

© OpenAI Codex · MIT · openai/plugins

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set528

The whole set →

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor