Testing & Quality skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

search-documents-typespec-validation

TypeSpec validation skill for Azure.Search.Documents SDK. Performs a COMPLETE validation of ALL operations, ALL models, ALL enums, and ALL properties against the TypeSpec definition at any pinned commit. Works for any API version. Generates a full gap report: missing features, extra features, naming mismatches, and recommended fix location. WHEN: "validate Azure.Search.Documents SDK against TypeSpec", "detect Azure.Search.Documents typespec feature gaps", "what is missing from the Azure.Search.Documents SDK", "compare Azure.Search.Documents SDK to spec", "full spec coverage audit for Azure.Search.Documents". Do NOT use for version-to-version diff or regression detection — use search-documents-version-diff instead.

6.03k repo starsObserved in 1 repos
Testing & Quality
GitHub

search-documents-version-diff

Diff the current Azure.Search.Documents public API surface against a previous published version and detect preview-to-preview regressions where the SDK customization layer was not bubbled up after a TypeSpec change. Use whenever the user asks to compare Azure.Search.Documents betas, verify no Azure.Search.Documents preview features dropped, regression audit between Azure.Search.Documents versions, sanity-check a release branch for Azure.Search.Documents, or investigate a missing Azure.Search.Documents preview feature — even if they don't say the word "diff". Specifically catches dropped wrappers (QueryAnswer/QueryCaption/QueryRewrites style), lost SearchOptions aggregator redirectors, `@@access("internal")` flips, deleted-instead-of-gated `#if AZURE_SEARCH_PREVIEW` blocks, dropped `ServiceVersion` enum values, and convenience-to-protocol downgrades.

6.03k repo starsObserved in 1 repos
Testing & Quality
GitHub

tool-audit

Audit OpenAlice's AI tools end-to-end — call each one (using its declared example input as the starting point), judge whether it runs, whether its description / params / output are good, and write a review with concrete "how to change it" notes. Use when the developer wants to dogfood the tool surface, find tools that are broken / thin / confusing, or get an optimization to-do list: "audit the tools", "which tools are broken", "review all the MCP tools", "test the tool surface", "go use every tool and tell me what to fix". A half-automatic regression + tool-optimization input.

6.00k repo starsObserved in 2 repos
Testing & Quality
GitHub

benchmark-kernel

Guide for benchmarking FlashInfer kernels with CUPTI timing

5.99k repo starsObserved in 1 repos
Testing & Quality
GitHub

asim-parser-filter-validator

Validates ASIM parser filtering parameters by running filter tests against a Log Analytics workspace. Pure PowerShell using az CLI for authentication — no Python or Azure SDK packages required. Use this skill after creating or modifying an ASIM parser to verify that its filtering parameters work correctly.

5.98k repo starsObserved in 1 repos
Testing & Quality
GitHub

asim-parser-pr-reviewer

Reviews pull requests for ASIM parser changes and summarizes suggestions. This is not to be called by asim-parser-creator-orchestrator or when creating ASIM parsers in general. This is strictly for reviewing pull requests after necessary workflows have ran.

5.98k repo starsObserved in 1 repos
Testing & Quality
GitHub

asim-parser-validator

This skill will validate an ASIM by checking the schema output of the parser and also checking the data that the parser represents in the columns. Use this skill after you have created or updated an ASIM parser to validate that the parser is correctly mapping the source data to the ASIM schema.

5.98k repo starsObserved in 1 repos
Testing & Quality
GitHub

debug-local

Debug the Lightdash app using PM2 logs, Spotlight traces, and browser automation. Use when investigating issues, tracking down bugs, understanding request flow, or correlating frontend actions with backend behavior.

5.97k repo starsObserved in 1 repos
Testing & Quality
GitHub

har-replay

Replay a HAR file as a mock backend to reproduce frontend performance issues with production data. Use when asked to replay a HAR file, reproduce a dashboard with a HAR, or test frontend performance with captured traffic.

5.97k repo starsObserved in 1 repos
Testing & Quality
GitHub

renovate-pr

Test and assess an open Renovate dependency-bump PR. Picks the first open Renovate PR, checks out the branch, starts the app, exercises code paths affected by the upgraded package, reviews the changelog and (if needed) the upstream source diff, and reports whether the bump is safe to merge. Use when asked to "test a renovate PR", "triage renovate", "assess a renovate bump", or "check a dependency upgrade".

5.97k repo starsObserved in 1 repos
Testing & Quality
GitHub