Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to \"review since X\".
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
General repository code review for microsoft/mssql-python, based solely on .github/copilot-instructions.md. Use when reviewing pull requests or diffs across the Python API, native bindings, packaging, tests, CI, or documentation. Apply the repository's existing architecture, correctness, compatibility, testing, and credential-handling expectations without replacing normal Copilot review.
Review methodology for pull requests to the mssql-django SQL Server backend. Use when reviewing a PR that changes the Django database backend under mssql/ or its tests under testapp/. Adds whole-PR, cross-file, and cross-version review procedure on top of the path-scoped instructions in .github/instructions/.
Use when the user asks for a code review, asks to "review the code", or requests review of a feature/PR/branch. Runs the OntoBricks review checklist defined in .cursorrules.
Fast multi-perspective code review for regorus. Use for everyday code reviews. Reviews from 3 perspectives with calibrated severity and noise filtering.
Review a named diff or PR for bugs, regressions, tests, and standards. Use when asked to review code or when a shipping skill needs a review receipt. Use when asked to apply this review's findings locally. Use ce-resolve-pr-feedback for feedback already left on a PR.
Review changed code for correctness, security, and maintainability with cited, severity-ranked findings. Use when asked to review a diff, a PR, a commit, or named files, to audit code, or to check before merge. Runs isolated and read-only, reports findings, does not edit.
When the user asks for a code review, shares code for feedback, or says "review this", "check my code", "what's wrong with this". Also activate when reviewing a pull request or diff.
Use when asked to review code, audit a file for bugs, check code quality, or suggest improvements. Provides a structured review process and issue categorisation.
Analyzes code changes for bugs, security vulnerabilities, performance problems, and architectural improvements. Generates structured markdown reports with evidence-based findings tied to specific file:line references, and creates Beads tasks for tracking. Adapts review depth based on scope — from quick pre-commit checks to thorough branch reviews. Use proactively when reviewing code before commits, after implementing features, before PRs, when checking code quality, or when the user mentions "review", "check changes", "code review", "PR review", "review branch", or any code quality assessment.
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
Reviews new or changed CODE on aspire.dev for correctness, safety, and adequate test coverage — not documentation prose. USE FOR: reviewing a PR supplied as a number or URL (or the current branch's diff), checking C#/TypeScript/Astro/HTML/CSS changes for bugs, catching correctness/security/data-loss/accessibility regressions, verifying that important scenarios have unit tests, e2e tests (desktop/tablet/mobile), and axe-core accessibility tests. DO NOT USE FOR: validating documentation content or examples (use doc-tester), reviewing a documentation PR for factual accuracy (use doc-pr-reviewer), writing or fixing docs pages (use doc-writer), two-slash TypeScript blocks (use twoslash-validator), or nitpicking style/formatting (ESLint and Prettier own that). INVOKES: git (read-only diff inspection), gh (to resolve and fetch a PR by number or URL), and optionally the repo's existing test commands for verification. FOR SINGLE OPERATIONS: read the diff with git or gh pr diff and apply the relevant language checklist directly.
Reviews pull requests in this repository for the defect classes a mechanical checklist misses: documentation that outlived the code it describes, reaction and retry state that leaks or clobbers a sibling, contract widenings that leave test doubles silently asserting nothing, kind-keyed maps missing a new entry, configuration literals that mean opposite things in adjacent blocks, error-taxonomy routing gaps, and wire assumptions that break on pagination. Use on every pull request review in addition to the coding standards in copilot-instructions.md. Covers Go orchestrator code, adapter packages, the architecture specification under docs/architecture/, accepted decision records, and operator-facing strings.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.