Communication & Collaboration Agent Skills for Microsoft Copilot

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…

Read artifacts from the shared bench — the workspace where desks leave findings, verdicts, and work products for each other and the…

Write employee recognition specific enough that it could only be about one person.

You have access to an environment variable, `BITBUCKET_DATA_CENTER_TOKEN`, which contains

Triage and steward issues in BT6 research and support repositories, deciding whether to answer, reproduce, correct evidence, link work…

Audit one pull request in a BT6 research or support repository at an exact head SHA, covering correctness, research integrity, security…

Audit the full pull-request and issue queue of a BT6 research or support repository, classifying readiness, evidence risk, and next action…

Compare a pull request's implementation against spec context in spec_context.md and feed any material mismatches into review.json.

Checks a GitHub, GitLab, or Perforce (p4) pull request (or merge request, or shelved changelist) for unresolved review comments, failing…

Reviews a code change once for material functional, security, performance, and maintainability defects and returns evidence-backed…

Consult Claude Code CLI (Claude Pro or Max, no API key) for a second opinion, plan critique, diff review, or occasional implementation.

Use when Codex should ask Claude CLI for an independent ordinary read-only code review, second-pass review, or sanity check.

Use for OpenClaw clawtributors PR/issue triage: Discrawl discovery, live-open rechecks, deep review, topic grouping, and compact…

Runs a Greptile CLI review for the current local branch, installing or authenticating the CLI when needed, then summarizes JSON findings…

Use when the user needs to update a client on progress, answer "where are we at?", or summarize a week/sprint/month of work for a…

Closes a milestone whose work is complete — verifies that all its issues are closed (paginated and against the tracker counts) and that…