Build once, run on any agent: A practical guide to agent skills
GitHub 以 Data Forge 和 Proof Agent 为例,讲解如何编写、组合与打包可跨智能体复用的技能。技能以 SKILL.md 为核心,将项目配置放入独立 manifest,并生成适用于 Claude Code、Cursor 和 GitHub Copilot 的客户端文件,工具、凭据和权限仍由运行环境提供。
GitHub 以 Data Forge 和 Proof Agent 为例,讲解如何编写、组合与打包可跨智能体复用的技能。技能以 SKILL.md 为核心,将项目配置放入独立 manifest,并生成适用于 Claude Code、Cursor 和 GitHub Copilot 的客户端文件,工具、凭据和权限仍由运行环境提供。
GitHub 给出 Copilot 智能体工程指南,将 AI 辅助开发扩展到规划、构建、验证与上线观察四个阶段。流程涵盖汇集上下文并生成带验收标准的 Issues、在隔离会话中推进任务、拆分依赖关联的拉取请求并执行质量与安全检查,以及利用运行证据形成后续任务。文中引用 Faros AI 研究称,团队从低 AI 采用率转向高采用率后,拉取请求在评审环节停留的时间增加了 441%。
三位 Java Champions 分享了使用 GitHub Copilot 开发功能、迁移教学材料和排查缺陷的实践,并强调开发者仍须负责验证与维护。
OpenAI 公布低资源编程语言评测结果,GPT‑6 Astra 在 MultiLangBench 的 20 种语言上平均测试通过率达 87.4%,GPT‑5.6 Sol 为 26.8%。
GitHub Copilot app 会话可直接在 VS Code 中继续,保留原有任务、计划、对话、代码差异和工作树。教程说明如何通过 Open in VS Code 打开会话,逐行审查改动、继续与 Copilot 对话、手动编辑并运行本地测试。完成后在会话关联的分支上提交并推送,即可更新已有的 pull request,无需复制文件或手动重新关联。
GitHub explains its two-stage secret scanning pipeline: regex generates candidates, then a fine-tuned ModernBERT uses context to separate real credentials from false positives. Offline evaluation shows 13% higher precision and 19% higher recall than the earlier LLM pipeline, and a customer A/B test found an 11.5% rise in alert acceptance rate weighted by repository owner. Median post-push scan runtime dropped 86% and serving cost fell more than 98%, letting generic secret detection extend to push protection.
Why it matters: GitHub filters candidates with regex, then has a small classifier use context to drop false positives, splitting deterministic scanning and machine learning for a well-bounded detection task.
GitHub describes a ModernBERT classifier fine-tuned with Microsoft Applied Sciences that extends unstructured secret detection to push protection, evaluating batches of candidate secrets in under 2 milliseconds.
Why it matters: GitHub compares nine quarters of code pushes against credential leaks, and the leak rate per push shows no clear trend while the growing volume adds to manual handling.
A Claude Code cloud sessions guide walks through four real runs covering parallel coding in separate VMs, environment setup, and how cloud sessions hand off to local ones. Three tasks started within 16 seconds of each other and all finished 87 seconds after the first launch. A cache fix passed 40 consecutive tests. Separate branches don't share fixes, so merge order has to be planned.
Why it matters: It shows how to split work by file boundary across parallel cloud tasks, and to build acceptance commands and branch merge order into the task design.
GitHub has put out a research preview of ReviewBench, an open benchmark for AI code review, with a public dataset, evaluation method and self-serve tooling. The benchmark mirrors the distribution of 103.9 million GitHub pull requests and covers 219 pull requests from 187 repositories across 19 languages. Senior engineers independently reviewed the labels, agreeing 96.6% of the time.
Why it matters: ReviewBench scores fixed labels and newly found valid issues separately, so review agents are compared on the same footing without being penalized for catching real problems the labels missed.
OpenAI rolled out shared projects for ChatGPT Business on September 25, 2025, and made them available for Enterprise and Edu plans. Shared projects support email or link invites, two access levels, and private project memory; Enterprise and Edu have them off by default under admin control. OpenAI also added Gmail, Google Calendar, Outlook, Teams, SharePoint, GitHub, Dropbox, and Box connectors, and said ChatGPT can now choose connectors automatically per prompt.
Why it matters: Shared projects give paid Business, Enterprise and Edu teams one space for files and instructions, so members reuse the same context instead of re-explaining it.
OpenAI released GPT-5-Codex and made it the default model for Codex cloud tasks and code review; in testing, it worked independently for more than 7 hours on complex tasks. OpenAI says it used 93.7% fewer tokens than GPT-5 on the lowest 10% of employee turns, while spending 2x longer reasoning, editing, and testing on the highest 10%. The key point is one model now spans interactive coding and long-running agentic execution; pricing and full availability details are not fully disclosed in the provided body.
Why it matters: OpenAI makes GPT-5-Codex the default model for Codex cloud tasks and code review, built for both interactive coding and long autonomous runs, with tests lasting over 7 hours.
OpenAI published a GPT-5-Codex system card addendum on September 15, 2025, stating the model is optimized for agentic coding in Codex and is available in terminal, IDE, web, GitHub, and the ChatGPT mobile app. The post says it uses reinforcement learning on real-world coding tasks, plus safety training for harmful tasks and prompt injection, with sandboxing and configurable network access. Benchmark scores, pricing, and context window are not disclosed.
Why it matters: OpenAI adds a system card addendum for GPT-5-Codex, covering the reinforcement learning used for Codex agentic coding and its safety measures, and noting it runs in the terminal, IDE, web, GitHub and ChatGPT mobile.
OpenAI published a May 16, 2025 addendum to the o3 and o4-mini system card, stating that Codex is a cloud coding agent powered by codex-1, an o3 variant tuned for software engineering. Each agent runs in an isolated cloud container preloaded with the user's code and environment, then loses internet access while it reads or edits files and runs tests, linters, and type checkers. The practical detail is the audit trail: Codex cites terminal logs and files, and its output can be exported as a GitHub PR or local diff.
Why it matters: The addendum states codex-1 is an o3 variant trained with reinforcement learning to run tests until they pass, exposing how the cloud coding agent works.
OpenAI released the Codex research preview on May 16, 2025, a cloud software engineering agent powered by codex-1 that can handle multiple coding tasks in parallel. It runs each task in an isolated sandbox, can read and edit repos, execute tests and commands, and usually finishes in 1 to 30 minutes with terminal logs and test outputs as evidence. It launched for ChatGPT Pro, Business, and Enterprise users, then expanded to Plus on June 3; the post excerpt does not fully disclose pricing or complete limitations.
Why it matters: Codex dispatches coding tasks in parallel from the ChatGPT sidebar, showing the shift from code completion to task-level agent work.
OpenAI released SWE-bench Verified, a human-validated subset built with the benchmark’s authors to assess real software issue resolution more reliably. The post names 3 failure modes in SWE-bench: overly narrow tests, underspecified issue statements, and unreliable environment setup; as of Aug. 5, 2024, top agents scored about 20% on SWE-bench and 43% on SWE-bench Lite. The key point is that the original benchmark can systematically underestimate coding-agent ability.
Why it matters: OpenAI and the original SWE-bench authors built a human-verified subset, arguing the original systematically underestimates real coding ability due to rigid unit tests, vague descriptions and environment issues.