@microsoft
Official · MicrosoftOrganization
Open source projects and samples from Microsoft
578 skills11 repositories 65.2K
Review past dsh agent sessions to identify recurring tasks and test proposed skill or memory improvements. This skill guides preview runs, validation on reserved tasks, staged proposals, adoption with backups, and scheduled nightly cycles.
Use past local Codex sessions to propose updates to a selected skill and project memory file. Recurring tasks are replayed, changes are checked on separate validation tasks, and proposals are staged for review before adoption.
Review past Claude Code sessions and turn recurring tasks into proposed updates to skills and project memory. Replay tasks, compare scores on separate validation tasks, and review staged edits before applying them with backups.
Study a reference adaptation connecting the shared skillopt_sleep cycle to a custom DeepSeek backend for OpenClaw. It provides prototype wrappers, sample tasks, and a porting checklist for developers building an integration.
Review past local Cursor sessions, identify recurring tasks, and propose changes to a project skill. Changes are tested on separate validation tasks and staged for review before adoption, with backups of existing files.
Find missing data in connected sources, inspect table structure, and suggest loading options for analysis. It also helps prepare a connection form for a new source, leaving connection and loading choices to the user.
Supports analysis of tables already in the workspace through data inspection, Python calculations, and charts chosen for the question. It also explains how to ask users for clarification and label results with meaningful units and names.
Guides developers in restricting server file access to approved directories. It covers validated download paths, agent file tools, local data connectors, and sandbox settings to address path traversal, where supplied paths escape their allowed location.
Guides developers in making agent replies and interface messages follow each user's language settings. It covers language instructions in prompts, frontend translation keys, and adding languages through the application's existing shared modules.
Turn data exploration findings into one Markdown report with embedded charts and tables. Adapt the structure for a short summary, blog post, executive briefing, KPI overview, or detailed analysis while checking supporting data.
Guides developers in handling API failures consistently from backend responses to frontend messages. It covers ordinary and streaming requests, translated error codes, retry and authentication handling, request identifiers, and removing credentials from server logs.
Automate browser tasks such as clicking, filling forms, and switching tabs. Inspect page structure, console messages, and network requests, capture screenshots or videos, and work with Playwright tests to check and investigate web page behavior.
Find the development workflow for updating the Playwright dependency or preparing a playwright-cli release. This skill points the agent to a separate guide for each task, providing an entry point for these two maintenance activities.
Implement one selected GitHub issue within a freshly confirmed human scope. Check ownership and existing pull requests, reproduce bugs when relevant, follow the implementation procedure, and open at most one pull request for the change.
Review OpenAPM specification changes through four specialist perspectives covering schemas, registries, dependency resolution, and web architecture. The skill combines findings and mechanical checks into one advisory comment, separating immediate fixes from work deferred to later versions.
Review an APM pull request through specialist agent perspectives selected for the changed areas. Findings are combined into one advisory comment with follow-up priorities and a shipping recommendation, leaving the final decision to maintainers and authors.
Audit an entire documentation collection against current source code and command output. Check pages for outdated claims, obsolete options, and broken links, apply small corrections, and verify the edits before preparing changes for maintainer review.
Classify how a pull request affects documentation using its changes and a documentation index. Return a JSON verdict identifying whether updates are unnecessary, already covered, needed within existing pages, or require structural changes.
Organize pull request reviews by selecting eligible labeled or explicitly named requests and distributing them to a dedicated worker pool. It records selection decisions and limits concurrent reviews, with two worker sessions by default.
Review APM positioning, public documentation, release communication, and breaking-change decisions using GitHub evidence. Check that incompatible changes include changelog entries and migration notes, and resolve disagreements among the project's specialist reviewers.
Draft a pull request description that explains the problem, implementation, trade-offs, and testing. It combines source-backed reasoning, validated Mermaid diagrams, and actual validation output into one Markdown file reviewers can assess on its own.
Turn a list of documentation pages affected by a code change into a precise editing plan. Identify sections and line ranges, record claims to verify, and flag information that must remain consistent across pages.
Assess one selected GitHub issue from user needs, security, and relevant design or documentation perspectives. Produce an advisory recommendation, a proposed scope brief, and a suggested reply for a human maintainer to consider.
Guide authentication changes in APM CLI for GitHub and Azure DevOps. Centralizes credential lookup through AuthResolver and explains token precedence, Azure CLI fallback, Git credential helper retries, and error messages for failed authentication.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)