personal
v1.10.0Personal writing and agent-collaboration skills for Codex
By makeavishLicense: MIT1 GitHub starsUpdated 1 hour ago
Directory evidence
- Runtimes
- Codex and Claude Code
- Parsed components
- 7 skill or MCP entries
- Source updated
- Oct 1, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install personal for Codex and Claude Code
codex plugin marketplace add makeavish/agent-skills
codex plugin marketplace upgrade makeavish-skills
codex plugin add personal@makeavish-skillsPaste and run these commands in a terminal with Codex. They add and refresh the makeavish-skills catalog, then install this plugin.
Compatibility: the page URL and API slug “personal-4” remain stable.
- Codex:
personal-4@agent-plugin-marketplace→personal@makeavish-skills
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/makeavish/agent-skillsClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/personal/.
Plugin files
├── .codex-plugin/plugin.json├── .claude-plugin/plugin.json├── skills/antigravity-cli/SKILL.md├── skills/chatgpt-pro/SKILL.md├── skills/claude-cli/SKILL.md├── skills/codex/SKILL.md├── skills/codex-plan-review/SKILL.md├── skills/cursor-cli/SKILL.md└── skills/writing/SKILL.md
Included Skills7
Use when the user asks to run Antigravity CLI (the agy command, agy -p) or references Google Antigravity CLI — the successor to Gemini CLI — for code analysis, refactoring, or automated editing
Consult GPT-6 Pro through an authenticated browser when requested or when hard problems stall, evidence conflicts, or consequential decisions need deeper analysis. Preserve practical results and resumable agent handoffs. Exclude routine work, missing permissions or inputs, API/CLI model selection, and tasks that forbid external consultation.
Use when the user asks to run Claude Code CLI (`claude`, `claude -p`, `claude --print`), wants a Claude peer agent/session, or asks Claude Code to perform code analysis, refactoring, reviews, automated editing, background-agent work, or structured CLI output from the terminal
Use when the user asks to run Codex CLI (codex exec, codex resume), asks to use OpenAI Codex for code analysis, refactoring, or automated editing, or explicitly asks for Codex fast mode
Send the current implementation plan to OpenAI Codex CLI for iterative review. Use when the user wants a Codex second opinion on a plan, architecture, or implementation approach. Do not use this for code diff review or file-change review. Claude and Codex go back-and-forth until Codex approves the plan.
Use when the user asks to run Cursor CLI (`agent`, `cursor-agent`), wants a Cursor peer session, or asks Cursor's terminal agent to analyze code, review changes, plan, refactor, or edit files. Does not apply to generic agents or opening files in the Cursor editor.
Draft, rewrite, critique, or unblock human-facing prose while preserving facts, intent, and authorial voice. Use whenever the user asks to write or improve an essay, article, blog post, memo, email, explanation, documentation, speech, story, scene, or dialogue; asks about prose clarity, flow, structure, rhythm, specificity, engagement, hooks, writer's block, or "show, don't tell"; or supplies prose for craft or style feedback. Do not use for source code, accuracy-only review, pure transcription, or translation unless prose craft is also part of the request.
Plugin manifests2
{
"name": "personal",
"version": "1.10.0",
"description": "Personal writing and agent-collaboration skills for Codex",
"author": {
"name": "makeavish",
"url": "https://github.com/makeavish"
},
"repository": "https://github.com/makeavish/agent-skills",
"license": "MIT",
"keywords": [
"agent-skills",
"coding-agents",
"codex",
"claude-code"
],
"skills": "./skills/",
"interface": {
"displayName": "Makeavish Skills",
"shortDescription": "Write polished prose and coordinate CLI and browser-based agent peers.",
"longDescription": "Skills for drafting and revising human-facing prose, proactively consulting GPT-6 Pro on hard problems through an authenticated browser with portable agent handoffs, and coordinating Codex CLI, Claude Code CLI, Antigravity CLI, and Cursor CLI for analysis, reviews, refactoring, and automated editing.",
"developerName": "makeavish",
"category": "Productivity",
"capabilities": [
"Code analysis",
"GPT-6 Pro browser handoffs",
"Plan review",
"Prose drafting and revision",
"Refactoring",
"Automated editing"
],
"websiteURL": "https://github.com/makeavish/agent-skills",
"defaultPrompt": [
"Rewrite this draft for clarity while preserving my voice.",
"Use Codex CLI to review this implementation plan.",
"Run a second-opinion code analysis with Claude Code CLI.",
"Consult GPT-6 Pro when a hard problem needs deeper analysis and leave a resumable agent handoff.",
"Choose the right coding-agent CLI for this task."
]
}
}{
"name": "personal",
"version": "1.10.0",
"description": "Personal skills and utilities",
"author": {
"name": "makeavish"
},
"repository": "https://github.com/makeavish/agent-skills",
"license": "MIT"
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[personal on Agent Plugins Marketplace](https://pluginsmp.com/plugins/personal-4)