newmindsgroup/ai-agent-skills-library/codex-skill-orchestrator

Claude Code and agent skill by newmindsgroup/ai-agent-skills-library

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

A Codex-first meta-skill that evaluates task complexity, selects the minimal useful skill set, and avoids unnecessary skill usage for simple work.

Install

npx vskill@latest install newmindsgroup/ai-agent-skills-library/codex-skill-orchestrator

SKILL.md

The same SKILL.md was published earlier as newmindsgroup/ai-agent-skills-library/codex-skill-orchestrator.

Codex Skill Orchestrator

Use this skill when a task is complex, multi-step, or clearly spans multiple domains and you want Codex to choose a minimal, sensible set of installed skills.

When to Use

  • The user wants the best combination of skills for a large task
  • The request spans planning, implementation, testing, and verification
  • The right skill is not obvious from the request alone
  • You want a Codex-first orchestration layer instead of relying on upstream branding

Core Rules

  1. Check complexity first. If the task is simple, do the work directly without orchestrating skills.
  2. Prefer the smallest skill set that covers the task.
  3. Use one primary skill whenever possible.
  4. Add another skill only when it covers a distinct phase or domain.
  5. Search the installed Codex skill library before assuming no relevant skill exists.

Routing

  • Vague or exploratory request: use skill-router
  • Planning-heavy request: use brainstorming, concise-planning, or writing-plans
  • Debugging-heavy request: use systematic-debugging
  • Implementation with tests: use the most specific domain skill, then test-driven-development if appropriate
  • Final validation: use verification-before-completion

Process

  1. Evaluate whether the task is simple or complex.
  2. Search the local installed skills by name and frontmatter when the best fit is not obvious.
  3. Select the minimal useful combination.
  4. Execute in order, announcing the current phase when helpful.
  5. Verify outcomes before claiming completion.

Limitation

This is a local Codex alias skill for orchestration. It is meant to keep the local setup understandable and Codex-branded.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
2
7-day trend score
10

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/newmindsgroup/ai-agent-skills-library/codex-skill-orchestrator/badge)](https://verified-skill.com/skills/newmindsgroup/ai-agent-skills-library/codex-skill-orchestrator)

Something wrong with this skill or its page? Tell us.