core-utils

Watch a PR through CI and review feedback. Auto-fix high-confidence failures and address review comments. Use when the user says 'babysit <PR>' or 'respond to PR comments'.

Ship changes. Simplify the diff, commit, review, push, and open or update a PR. Use when the user says 'ship it', 'commit and push', or wants a PR created or updated.

Debug and fix flaky tests including Playwright E2E, NestJS service/integration, React component, and unit tests.

Adversarial reviewer for flaky-test fix plans and PRs, enforcing the flaky-fix rubric. Gates implementation tickets from Triage to Todo (enforce by default; approve releases, reject bounces; canceling tickets stays human-only). Use when running the recurring flaky-critic task, when asked to review a flaky-fix plan or PR against the rubric, or to backtest verdicts against historical tickets.

Scheduled triage stage between flake-intake and agent dispatch. Clusters flaky-investigation tickets by shared root cause, closes duplicates and infra blips, and releases one repository-owned canonical ticket per cluster for dispatch. Use when running the recurring flaky-triage task, when asked to triage the flaky queue, or to backtest clustering against historical tickets.

Sweep the flaky-test pipeline after fixes merge by closing out the root-cause KB, closing clearly superseded tickets as Done under D3, and re-dispatching critic-rejected plans for amendment. Use for the recurring flaky close-out task, a post-merge flaky-fix sweep, or a dry-run/backtest of close-out decisions.

Investigate chronic flaky-test fingerprint families with a credential-checked, dossier-first, cross-repository causal-chain method and produce a designed fix or observability design for human review. Use when flaky-triage routes a family with at least three prior implementation tickets, flaky-critic routes a family with at least two failed merged fixes, or a user asks for the chronic flake deep-dive track.

Code review of a diff, branch, or PR, with findings posted as anchored PR comments. Use when the user asks to review a diff, branch, or PR, asks to check a change against its ticket/spec/PRD, or runs /cb-review [pr-number-or-url] [--effort low|high] [--report] [--spec-context <path-or-reference-or-text>].

Implement a plan file or direct request end-to-end, validate, and ship via cb-ship. Use when the user says 'implement the plan' or clearly wants a change implemented and shipped.

Backtest an automated judgment stage (clustering, verdicts, routing, gating) against historical decisions with known outcomes. Use before any judgment skill goes live or into shadow operation, or when asked to grade an agent's decisions against a human's.

Strip AI writing tells from prose you draft or clean: PR descriptions, Slack messages, docs, emails, commit messages. Use whenever the user asks to "humanize" or "deslop" text, or runs /humanize-prose. Also applies implicitly: any prose you draft for the user must already satisfy these rules.

Create Linear tickets that Groundcrew can pick up: assigned to the current Linear user, labeled with agent-*, tied to an implementation repository in the description, optionally linked to parent and blocker tickets, and written to use the core:cb-work implementation workflow.

Use when a Clipboard frontend task involves a new UI idea, Figma/design URL, screenshot, redesign UI, design-to-code implementation, Storybook visual validation, Playwright/browser screenshot, animation/motion visual proof, or preventing design-system and visual-fidelity drift in admin or mobile UI work.

Migrate a Metabase dashboard or single card/question to a Hex app at Clipboard Health — extract the source structure via the Metabase MCP, rewrite SQL onto core dbt models, scaffold the Hex project with the CLI, and finish the Input cells / markdown / appLayout via a YAML round-trip. Use this whenever the user asks to migrate, port, rebuild, or recreate a Metabase dashboard or card in Hex, asks to make a Hex version of a Metabase question, mentions a Metabase dashboard or `/question/` URL alongside Hex, wants to recreate Metabase parameter filtering as Hex Input cells, or wants to generalize multiple migrated cards into one parametrized app. Also use when the user references a previous migration ("like the WOPs Tool one", "same pattern as the Payments Dashboard") and wants the playbook applied to a new dashboard or card.

Use when creating a Linear bug report ticket from conversation context, investigation findings, or user-provided evidence — when evidence already exists and needs structuring, not investigating.

Use when creating a Linear feature request ticket from conversation context, a brief description, or code/PR analysis — including when context is too thin to draft from.

Use when creating a Linear tech debt ticket while working in the codebase — from code review, PR comments, codebase audits, or post-incident findings.

Use when a Clipboard frontend task involves UI polish, motion or animation decisions, interaction feel, small interaction details, visual hierarchy, component craft, or reviewing whether admin/mobile UI feels consistent with Clipboard's product and design-system standards.

Use Clipboard's internal CLI to link and unlink @clipboard-health packages across repositories for local development. Use when testing local package changes, linking @clipboard-health packages between repos, or using the cbh CLI local-package command.

Use when clarifying requirements for a feature ticket. Iteratively researches and interviews the user until the problem is well-understood, then produces a structured problem brief. Dispatched by write-feature-ticket when context is insufficient.

Use when investigating a bug, incident, or issue before implementation. Researches codebase, queries Datadog, and presents structured findings with handoff options. Also use when asked to "look into" or "investigate" something.

Perform an adversarial review of proposed work. Use ONLY when the user explicitly types /adversarial-review. Never auto-trigger, even if the user mentions reviewing, questioning, or challenging their approach.

Use when looking up Cognito user details by sub UUID, finding duplicate accounts sharing phone or email, analyzing which duplicates to keep vs delete, or fixing orphaned UNCONFIRMED signups. Symptoms include 403 Forbidden on login, multiple accounts for same phone, backend sync issues.

Trigger seed data generation for test environments via GitHub Actions. Use when asked to seed, create test data, or set up HCPs/facilities/shifts.

Investigate production issues by querying Datadog logs, metrics, and APM traces, then correlating findings with the codebase. Use this skill whenever the user mentions production errors, Datadog, observability, log investigation, latency spikes, error rate increases, 500s, trace IDs, monitor alerts, or wants to debug any service issue in a deployed environment.