Testing AI Skills

Review changes since the latest commit with incremental impact and blast radius analysis.

tirth8205

Review Renovate bot PRs that update GitHub Actions dependencies. Verifies supply chain integrity by checking pinned commit SHAs against upstream tagged releases, reviews changelogs for breaking changes, and confirms compatibility with existing workflow configurations.

backnotprop

Review code changes using detected modifications and their effects on dependent code.

tirth8205

Explain Git diffs or pull requests, affected components and potential change risks.

Egonex-AI

Find root causes through reproduction, localization, reduction, repair and regression protection.

Addy Osmani, Federico Bartoli and Joan León

Audit and update npm/Bun dependencies with supply chain integrity checks — verifies maintainers, publish age, tarball diffs, and provenance before bumping. Defers risky packages to ~/.supply-chain/notes/.

backnotprop

Inspect DOM, console, network and runtime behavior through Chrome DevTools MCP to investigate browser bugs.

Addy Osmani, Federico Bartoli and Joan León

Analyze failed GitHub Actions jobs, compare prior runs and identify the breaking change or flaky behavior.

ykdojo

Investigate JVM CPU spikes with thread evidence, stack inspection, and bounded method tracing.

alibaba

Investigate the root cause of errors, crashes, and regressions before proposing a fix.

tw93

Investigate Rapid MLX performance, prototype changes, benchmark results, and prepare reviewed improvements.

raullenchai

Inspect and debug Honcho workspaces via the `honcho` CLI.

plastic-labs

Use a repository knowledge graph to locate relevant code and investigate reported issues.

tirth8205

Produce a ranked repository audit covering bugs, risky untested code, slow paths and code bloat.

DietrichGebert

Review titles, text, subtitles, spoken lines, profile copy, comments, and video material for potential platform signals and substantive issues, with specific minimal edits.

dontbesilent

Use Playwright to inspect local web apps, exercise frontend flows and capture screenshots and logs.

Anthropic

Review changes for correctness, readability, architecture, security and performance with actionable findings.

Addy Osmani, Federico Bartoli and Joan León

Retrieve EagleEye trace IDs with Arthas to connect request execution with application logs.

alibaba

Audit statistical reporting across methods, results and figure legends, including replication, uncertainty and multiple comparisons.

Yuan1z0825 and contributors

Make the smallest complete change, with adjustable coding intensity and concise explanations.

DietrichGebert

Run live CodexBar provider checks and collect application and configuration evidence.

steipete

Review diffs and pull requests, assess release readiness, and follow publishing steps.

tw93

Open Plannotator's browser-based code review UI for the current worktree, another directory, or a pull request URL, then act on the feedback that comes back.

backnotprop

Review pull requests and branch diffs with graph context and a structured impact report.

tirth8205

Cross-examine non-trivial engineering decisions using fresh-context adversarial review and explicit stop conditions.

Addy Osmani, Federico Bartoli and Joan León

Display Ponytail’s recorded benchmark results for code size, cost and execution speed.

DietrichGebert

Review a change and its connected code for correctness, safety, performance and unnecessary complexity.

DietrichGebert

Review a branch, pull request or uncommitted change for introduced UI regressions.

Jakub Krehel

Use Plannotator for plan and code review, artifact annotations, archived decisions and asynchronous feedback.

backnotprop

Monitor a pull request until CI succeeds, investigate failures and retry only confirmed flaky workflow jobs.

langchain-ai

Inspect Spring application contexts, bean definitions, and configuration sources with Arthas.

alibaba

Run the Open SWE dashboard locally against real GitHub data using an authenticated gh CLI.

langchain-ai

Monitor a pull request, address actionable review feedback, and recheck CI until the PR meets its readiness criteria.

Alex Newman (thedotmack)