Use Transcribe Skill to convert meeting recordings and podcasts into searchable text
### 正式翻译： This article introduces OpenAI's official Agent Skill `transcribe`: Based on `gpt-4o-mini-transcribe` and `gpt-4o-transcribe-diarize`, it converts audio and video files into text, with support for speaker diarization and known speaker prompts. It explains the installation directories and activation methods in Codex, Cursor and Claude Code, provides reproducible examples including fast transcription with the bundled CLI and `diarized_json` output, and lists precautions such as the 25MB file size limit, automatic chunking for long audio, and the fact that the diarize model does not support prompts.
Read MoreUsing OpenAI Speech Skill to synthesize reusable voice from text
# Official OpenAI Curated Skill: speech This article introduces the OpenAI Agent Skills-powered speech skill that calls the OpenAI Audio API. It allows users to synthesize text into narration, product voiceovers, IVR audio and accessible reading audio via the built-in CLI. The article covers the installation method, configuration of the OPENAI_API_KEY, usage of the `speak` and `speak-batch` commands, default models and built-in voices, as well as limitations including single audio length, speech rate and custom voices.
Read MoreIntegrate Official Documentation for AI Programming Assistants with openai-docs Skill: Say Goodbye to Outdated APIs and Fabricated Parameters
# Official curated Skill "openai-docs" from OpenAI: Retrieve and cite the latest documentation via Developer Docs MCP (search/fetch/OpenAPI) This skill covers API usage, Codex manual self-knowledge, model selection and prompt engineering. It explains the paired installation with Docs MCP across platforms including Codex, Cursor and Claude Code, typical prompt usage scenarios, and precautions such as read-only document access and narrow-scope migration, to alleviate the issues of outdated documentation and parameter hallucinations in AI programming assistants.
Read Morepython-tdd-with-uv: Let AI Agent Write Python in Red-Green-Refactor Cycle
### Translation: This article introduces `python-tdd-with-uv`: a SKILL.md from spencerpauly/awesome-cursor-skills that teaches AI Agents to conduct Python Test-Driven Development (TDD) using uv. It verifies the official capabilities of uv (including its project initiation with pytest, vertical slice red-green-refactor workflow, and uv run conventions), covers the installation directory and activation method under Cursor/Claude Code/Codex, provides reproducible command examples and test structure samples, and explains the applicable scenarios and limitations of this skill.
Read More# Standard Conventional Commits Written with the `writing-commit-messages` Skill
### Translated English Abstract: This article introduces the `writing-commit-messages` section in spencerpauly/awesome-cursor-skills: how to use Agent Skill to constrain commit messages to follow Conventional Commits specifications (including type prefixes, scopes, body content, and BREAKING CHANGE sections). It verifies the rules in SKILL.md, good and bad examples, commit granularity requirements, as well as the installation methods for Cursor skills: manually installing to the `.cursor/skills/` directory, and using `npx skills add` to install to both Cursor and Claude Code. This guide is suitable for teams that need standardized collaboration and automated changelog generation.
Read MoreUsing kubernetes-deploying Skill: Let AI Agents Generate Kubernetes Deployment Manifests According to Specifications
### 翻译结果： `kubernetes-deploying` from spencerpauly/awesome-cursor-skills is an Agent Skill designed for Kubernetes deployments. It encapsulates best practices including Deployment, Service, Ingress, ConfigMap, Secret, health checks, release strategies and HPA into the SKILL.md file, enabling AI programming tools such as Cursor, Claude Code and Codex to generate standardized manifests and work with common kubectl commands. This article introduces its capabilities, installation and activation methods, typical usage scenarios and usage notes based on official documentation.
Read MoreHand Over Production Incident Response Process to AI Agent via Incident-response Skill
# Incident Response in spencerpauly/awesome-cursor-skills This project packages the SEV grading, stopgap mitigation, internal and external communication, and 48-hour blameless post-incident review workflow for production incidents into an installable `SKILL.md`. It has verified official workflows and post-incident review templates, and provides enabling methods via `npx skills` or by copying to `.cursor/skills/` for use in Cursor, Claude Code, and Codex CLI, making it suitable for SRE/DevOps on-duty scenarios.
Read MoreParallelly familiarize yourself with unfamiliar codebase and generate onboarding documentation using codebase-onboarding
### 翻译结果： This article introduces the `codebase-onboarding` skill in spencerpauly/awesome-cursor-skills: it launches 5 read-only explore sub-agents in parallel to research architecture, data models, APIs, authentication and deployment respectively, then synthesizes the results into an ONBOARDING.md. Based on the official SKILL.md and Cursor Skills documentation, it explains the installation directory, the `npx skills` installation method, the calling mode of `/codebase-onboarding`, as well as applicable scenarios and review precautions.
Read MoreGenerate bitmap assets in the coding workflow using Codex's imagegen Skill
# Introduction to OpenAI Codex System-level Skill `imagegen` This skill enables generation and editing of bitmap assets including photos, illustrations, mockups and sprites within coding conversations via either the built-in `image_gen` command or an explicit CLI. Details including default auto-installation location, two operating modes, prompt templates, save path conventions, applicable boundaries and official CLI examples are provided to facilitate directly integrating visual assets into project repositories.
Read Moreplugin-creator: One-click Scaffold Codex Plugin with Official Skill
# Official OpenAI System Skill Plugin-Creator: Guide This article introduces OpenAI's official Skill Plugin-Creator system, detailing how to scaffold plugin directories for Codex/ChatGPT, generate the required `.codex-plugin/plugin.json` file, create placeholders for skills, hooks, MCP, apps as needed, and write configurations to local or repository-level `marketplace.json`. It also covers conversational invocation methods (`$plugin-creator` / `@plugin-creator`), command parameters for `create_basic_plugin.py`, conventions for manifest and marketplace fields, applicable scenarios, and common pitfalls.
Read More# skill-installer: The "Package Manager" for Installing Skills on Codex
Skill-installer is a system Skill pre-installed by OpenAI alongside Codex, used to install Skills to `$CODEX_HOME/skills` (default path: `~/.codex/skills`) from the official curated/experimental catalog or any GitHub repository path. Based on the official SKILL.md and Codex documentation, this article explains how to use `skill-installer` to list and install Skills, covers script parameters, private repository and download fallback strategies, as well as the boundaries of local testing and plugins distribution.
Read MoreBuild ChatGPT Apps with chatgpt-apps Skill: MCP Server + Widget UI
### 正式翻译结果： ### Introduction to OpenAI's official curated Skill chatgpt-apps: How to scaffold, refactor and troubleshoot ChatGPT Apps SDK applications (MCP server + Widget UI) following a docs-first workflow. The article verifies the capabilities of Skills, application prototype classification, upstream example priority, usage boundaries between MCP Apps bridge and window.openai, as well as the installation and activation methods in Codex and Cursor. It also provides prompt examples for paired use with openai-docs and local joint debugging steps for Developer Mode.
Read More`define-goal`: Clarify the Goal First, Then Let the Agent Take Action
This article introduces OpenAI's curated Skill `define-goal`: it is used to refine vague intentions into specific, measurable and verifiable goals before coding, and call `get_goal/create_goal` again in accordance with quality standards. Based on the official SKILL.md documentation, the article explains the workflow, comparisons between good and bad goals, Codex installation (via `$skill-installer`), and the method of enabling it in tools such as Cursor/Claude Code through the SKILL.md directory. It also reminds that this skill only performs goal definition and does not manage long-cycle execution deliverables.
Read MoreTurn Notion research into cited structured documents with notion-research-documentation
### Official English Translation: This article introduces the OpenAI curated skill `notion-research-documentation`: under the premise that Notion MCP has been connected, it enables cross-page retrieval and evidence synthesis within Notion, and generates cited documents in templates such as briefings, summaries, comparisons, and full reports. It follows the official SKILL.md instructions for installation and activation (including Codex's `$skill-installer` and Cursor's skills directory), covers the official five-step workflow, competitive product comparison examples, as well as precautions such as permissions, timeliness, and warehouse deprecation.
Read MoreUse notion-spec-to-implementation to split Notion PRD into executable plans
### 译文： This article introduces OpenAI curated skill `notion-spec-to-implementation`: with the support of Notion MCP, it parses PRD/functional specifications into implementation plans, 1-2 day granular tasks and progress write-back, realizing the connection between Spec ↔ Plan ↔ Tasks. The article verifies the installation methods (Codex $skill-installer and Skills directory of Cursor/Claude Code), MCP configuration (mcp.notion.com), workflows and official API examples, and explains applicable scenarios and common precautions.
Read MoreEquip Agents with "Eyes" Using Screenshot Skill: Desktop Screenshot and Visual QA
# OpenAI Curated Screenshot Agent Skill This skill enables agents to capture full-screen, window-specific, or pixel-region screenshots across macOS, Linux and Windows for visual analysis and UI validation. It prioritizes tools like Figma and Playwright first, with system-level screenshots as a fallback. The article details its save path rules, official installation methods (using Codex's $skill-installer and placing files in Cursor/Claude Code directories), cross-platform script usage, as well as considerations around permissions, dependencies and multi-monitor setups, helping to build a complete front-end visual QA workflow that connects design mockups, browser pages and desktop applications.
Read More`playwright-interactive: Using Persistent JS_REPL for UI Iteration and Debugging`
# Introduction to OpenAI's Featured Skill: playwright-interactive This skill enables persistent handling of Playwright/Electron via js_repl, allowing rapid iterative UI debugging on local web and Electron applications. It also supports completing QA checklists, functional validation, visual QA and viewport adaptation following official workflows. This article details the installation steps, pre-configuration requirements, typical code snippets, as well as notes such as the possible removal of js_repl in the current Codex, and makes a comparison with the CLI-oriented Playwright Skill.
Read More# Figma-Create-Design-System-Rules: Develop Project-Specific Design System Rules for Agents
This is an introduction to `figma-create-design-system-rules` in the openai/skills curated catalog: On the premise of connecting Figma MCP, it analyzes the codebase and generates project-level design system rules, constraining component paths, Design Tokens, styling solutions and the Figma-to-code workflow, and writes them into `CLAUDE.md`, `AGENTS.md` or `.cursor/rules/figma-design-system.mdc` respectively, to alleviate problems such as random use of spacing, hard-coded colors, and repeated creation of components when AI implements UI. The article verifies the installation method, five-step workflow and precautions.
Read MoreUse figma-generate-design to reverse-generate pages from code into Figma
This article introduces the `figma-generate-design` Skill in the OpenAI curated and Figma MCP ecosystems: on the premise that Figma MCP is connected and the target file has a design system, it writes application pages or multi-block layouts into Figma in the form of component instances and Tokens, and forcibly cooperates with `figma-use`. The article verifies official processes including plugin installation (Cursor / Claude Code / Codex), npx skills installation method, block assembly and parallel calibration of `generate_figma_design`, as well as the boundaries between adjacent Skills such as `figma-implement-design` and Code Connect.
Read MoreVisualize Security Responsibility Topology from Git History Using security-ownership-map
# Security-Ownership-Map: An OpenAI Curated Agent Skill Security-Ownership-Map is an OpenAI curated Agent Skill that constructs human-file bipartite graphs and covariation clustering based on Git history, calculates the Bus Factor of sensitive code, and supports output in CSV/JSON formats (with optional Neo4j/Gephi exports). This article introduces its positioning, installation and activation, usage of `run_ownership_map` and `query_ownership`, sensitive code rules and applicable boundaries, which is suitable for enterprise security teams to conduct inventory of ownership drift and orphaned sensitive code.
Read More# 翻译结果： security-threat-model: Let Agent perform threat modeling based on code repositories
### Official Translation: This article introduces OpenAI's curated Skill **security-threat-model**: it enumerates trust boundaries, assets, attacker capabilities and abuse paths based on repository evidence, and outputs a structured Markdown threat model. The article verifies the official workflow, reporting contract, installation and activation methods of Codex/Cursor/Claude Code (including the Trail of Bits plugin), as well as typical prompt words and usage boundaries.
Read More`render-deploy`: Analyze codebase, generate Blueprint, and deploy applications to Render
This article introduces OpenAI Curated Agent Skill `render-deploy`: it analyzes the codebase to generate a render.yaml Blueprint, or directly creates a single service via Render MCP, and provides a deep link to the Dashboard to complete the deployment. It verifies the installation methods (npx skills / Codex skill-installer), the MCP configuration for Cursor/Claude/Codex, the heuristic guidelines for choosing between Blueprint and Direct Creation, as well as precautions such as Git remote, image service restrictions, `sync:false` for secrets, port binding and other matters, and complements deployment-related Skills like Vercel/Cloudflare.
Read MoreOne-click Deployment of Frontend Projects to Netlify with the netlify-deploy Skill
### Translated Abstract: This article introduces the OpenAI curated skill `netlify-deploy`: it uses the Netlify CLI (`npx netlify`) to complete authentication, site association/creation, dependency installation, and preview/production deployment. It explains the installation methods in the Agent Skills directories of Cursor, Codex, Claude Code and other platforms, provides official workflow command examples, notes for `netlify.toml`, as well as usage suggestions such as sandbox networking and key management.
Read MoreSelf-improving Programming Agents Have Gone Viral: Long-term Autonomous Tasks, What Are Developers Betting On?
# 2026-08-10 GitHub Trending Leader: prime-agent by PrimeIntellect-ai The repo gained approximately 2,356 stars in a single day. Positioned as a self-improving RLM Agent oriented towards coding and long-term autonomy, this article verifies its two core abstractions based on the official repository and blog: Recursive Language Model (persistent IPython and programmatic sub-agents) and Continual Harness (small-step rewrite prompts/memory/skills via /refine with rollback capability). It explains how daemon, objectives, and bounded/autonomous modes support long-running tasks, clarifies that "self-improvement" refers to scaffolding state iteration rather than weight self-training, and also warns about the non-safe sandbox risk.
Read MoreClaude Code v2.1.224: Multiple independent sessions can send messages directly to each other, say goodbye to copy-pasting between terminals
Anthropic launched cross-session messaging in Claude Code v2.1.224 (released on August 7, 2026): independently running sessions on macOS/Linux can discover each other via ListAgents and send each other plain text summaries via SendMessage, without manually copying context between terminals. The messages do not carry conversation history or files, and the recipient still needs to approve sensitive operations on their own; the communication uses local sockets on the same machine, and cross-machine support is limited to replies via Remote Control. This article introduces the mechanism, scenarios, usage and security boundaries based on official documentation.
Read More