Tools tagged with "Official"

<!-- VERSION CHECK INSTRUCTIONS When the preamble outputs text, handle it as follows:

This skill produces the Plan artifact of the /eval-guide lifecycle: a populated copy of the customer's Eval Suite Planning & Logging Template plus an interactiv

Answers AI agent evaluation methodology questions with practical, opinionated guidance grounded primarily in Microsoft's agent evaluation ecosystem (MS Learn, E

Generate standalone — turns the populated Eval Suite Planning workbook (output of /eval-suite-planner) into concrete capability eval sets and trust & safety eva

Analyzes Copilot Studio evaluation results using Practical Guidance on Agent Evaluation's 10-step playbook (Steps 6, 7, and 9) plus Microsoft's triage diagnosti

Use this skill when the user's Copilot Studio agent evaluations have come back and they need to interpret scores, diagnose root causes of underperforming test c

Finalize a rego-cpp PR for release. Use when: wrapping up a branch, preparing a release, cutting a version, or when instructed to finalize a PR. Confirms review

Use this skill when the user asks to design/build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

Generate a succinct CHANGELOG.md entry from PR descriptions since the last version bump.

Migrates an MCP server with interactive widgets from the OpenAI Apps SDK (window.openai, text/html+skybridge) to the MCP Apps standard (@modelcontextprotocol/ex

Migrates an MCP server with interactive widgets from the OpenAI Apps SDK (window.openai, text/html+skybridge) to the MCP Apps standard (@modelcontextprotocol/ex

Run a multi-perspective planning process for non-trivial design decisions. Use when: the shape of a solution is uncertain, planning new language features, new p

Check OPA Rego version compatibility for rego-cpp. Use when: updating OPA version, checking for new OPA releases, auditing rego-cpp compatibility, planning OPA

Speed and memory performance rules for Rust crates, the Node addon, webui-framework, and webui-router.

Guidance for branch naming, commit messages, and PR titles.

AUTHOR SKILL (internal to microsoft/aspire-skills). Reviews pull requests into this repo for problems only — bugs, regressions, missing eval coverage, frontmatt

Run before every commit or push: formatting, linting, tests, dependency audits, builds, and docs.

Design guide for the Trieste regex engine (include/trieste/regexengine.h). Describes the architecture, data structures, and conventions of the header-only NFA-b

Pass the rego-cpp Trieste fuzzer for a given pass collection. Use when: verifying that compiler passes are robust to all valid WF inputs, debugging fuzzer failu

Add, update, or remove OPA Rego built-in functions in rego-cpp. Use when: implementing a new builtin, replacing a placeholder with a real implementation, adding

Iterative review loop using any lens agent against any target (plan, code, design). Use when you want to run a focused review cycle: spawn a fresh reviewer suba

Multi-perspective code review using four parallel constructive reviewers (conservative, security, usability, speed) followed by a sequential adversarial gap-ana

Test patterns, fixture structure, and when to use E2E vs unit tests.

Plan and implement Trieste-based compiler passes and AST transformations for rego-cpp. Use when: adding new compiler passes, modifying AST structure, implementi

This skill enables visual inspection of websites running locally or remotely to identify and fix design issues. Triggers on requests like "review website design

Build interactive WebUI apps with compiled-template hydration, template syntax, component patterns, and CLI usage.

Use this skill when the user wants to commit staged changes. This skill checks linting, then formatting (matching CI order), runs tests, generates a commit mess

Systematic debugging workflow for test failures. Use when tests are failing, a CI build is red, or when asked to debug test issues.

Guide for safely updating project dependencies. Use when asked to update packages, upgrade dependencies, or check for outdated libraries.

Generate a brand-aligned design guide for a new code app instead of using the default template styling. Use when: the user wants to start a new app with their o

BC-Bench example skill — a no-op skill that only exists to prove the BC-Bench plugins experiment toggle installed a plugin into the agent's isolated config home

Read and manage Asana tasks, projects, sections, comments, and workspaces. Use this whenever the user wants to list or search tasks, create or update a task, co

Add evaluation results to Hugging Face model repositories using the .evalresults/ format. Uses HF CLI for PR management and manual YAML creation.

Complete workflow for creating and managing ADRs (Architecture Decision Records). Includes duplicate checking, status determination, Microsoft documentation loo

Run SQL against Google BigQuery and browse its catalog — submit queries (sync or async), poll job status, page through results, list datasets/tables, and read t

Scaffold a PhysicsIntern research workspace in the current folder. Run only when the user explicitly invokes it to set up a new physics/maths research workspace