Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access."..." for exact phrases · Try typography, debugging or spreadsheetProvides a self-directed research loop for Codex. Repeatedly modifies and verifies work, retains or discards changes, and continues until a measurable goal is reached.
Runs OpenAI Codex CLI as a background implementer for coding tasks or queues. Supports a workflow where the delegating agent or user reviews the diff and commits the changes, rather than relying on a one-shot forwarder.
Review Codex task time and token waste using task logs and optional Computer History evidence, then propose concrete, independently completable improvement batches. Use for efficiency retrospectives; ordinary chat lookup and general behavioral-rule reviews belong to their existing skills.
Use when Codex feels slow, bloated, or heavy after heavy use and the user wants local Codex state hygiene, handoff discipline, or archive strategy. First run is report-only. Do not use for deletion, credential cleanup, or archiving active work without handoffs and explicit confirmation.
Use when the user asks to turn a vague task into a Codex /goal command, Goal 指令, 目标指令, 中文 Goal 模板, or plan-to-goal interview. Do not load for ordinary project planning, code review, test execution, translation, simple rewrites, or generic success-criteria discussion unless the user wants an executable /goal.
Imports Codex CLI conversations and session logs into an Obsidian wiki. Mines previous coding sessions for insights and knowledge.
Use when the user wants to understand, design, or improve Codex itself: hooks, subagents, skills, AGENTS.md or PLANS.md guidance, config-aware workflow design, Codex docs navigation, or deciding when to use codex exec, the SDK, App Server, GitHub Action, or automation. Inspect the current local Codex setup before recommending repo- or machine-scoped changes.
Uses GPT Image 2 through RunComfy to create a canonical pet pose, then assembles nine animation states with ImageMagick transforms. Produces a Codex-compatible spritesheet and pet.json and places them in the custom pets directory.
Generates a canonical pet pose with GPT Image 2 through RunComfy, then assembles nine animation states using ImageMagick transforms. Produces a Codex-compatible spritesheet.webp and pet.json and places them in the custom pets directory.
Creates visually unified image-based PPT/PPTX presentations from articles, reports, papers, notes, or outlines.
Use when you want Codex to review its own recent history (last N days or specific period) and propose minimal, evidence-backed improvements to AGENTS.md or tiny reusable skills. Do not use for ordinary project retrospectives, chat search, or automatic edits without a human review gate.
Integrates Codex AI into professional code review workflows. Includes automatic changelog generation.
A growing collection of real, public skills. Descriptions and instructions indexed 25 Sept 2026.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name