Communication & Collaboration Agent Skills

Use for \"interrogate\", \"adversarial review\", \"multi-model review\", \"challenge this\", \"stress test this code\", \"find blind…

Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds.

Obtain an external second opinion on a plan, spec, or options when the user asks for peer review or another reviewer; also handle reviewer…

Review TypeScript and JavaScript code changes for compliance with Metabase coding standards, style violations, and code quality issues.

Fetch, categorize, and address GitHub pull request review feedback -- inline review comments, review threads, top-level discussion…

The contract for the sdlc-agent-result-persist CLI — its modes, its flags, the paths it composes, the line grammar of the round log it…

Facilitates direct peer-to-peer communication and task handoffs between concurrent Claude Code sessions using built-in cross-session…

Requested GitHub PR/issue agent transcripts: redact, preview, and insert safely.

Interactive agent picker for composing and dispatching parallel teams.

Store, retrieve, and query shared memory records in Akasha — a distributed cognitive fabric for intelligent agent collaboration.

Coordinate with other agents through pheromone-based stigmergy signals in Akasha.

Ask Codex CLI (gpt-5.6-sol) for an independent code review of uncommitted changes, a branch diff, a commit, or a specific implementation.

Enforces Alibaba Java Development Manual (Huangshan v1.7.1) standards for Java code generation, refactoring, and structured code reviews.

Enforce the official English Alibaba Java Coding Guidelines (5 sections, 124 mandatory / 57 recommended / 24 reference rules) as the…

Implements workflow-adapter-tracker-comment through octa.

Orchestrates a complete multi-perspective Argus code review of a change — correctness, security, performance, and architecture — each…

Audit the choices an implementing agent made, not its diff — a pure decision audit that traces the session's history into a choices…

Audit work, verify claims with concrete evidence, and explain the result in simple grade-5 language.

Monitor a PR, fix feedback and CI failures until fully green for 30 min.

Drive a PR to a clean review (Greptile 5/5, zero open threads) — ships if needed, keeps it mergeable against staging, triggers…

Refine raw ideas and backlog items into decision-complete, actionable work and decide whether they need discovery, an Epic, implementation…