Deep implementation review that hunts for real bugs. Use when the user asks for adversarial review, review this implementation, audit my code, stress test this, find problems with this, ship-readiness review, is this ready to ship, check this against the plan, check this against the spec, find bugs in this, implementation audit. This skill is for IMPLEMENTATIONS — code, configs, scripts, pipelines. For plans and designs before implementation, use a plan-review or design-challenge skill instead.
Babysit a PR end-to-end — push the branch, poll CI every 3 minutes, auto-fix red checks, address PR comments via validation, then alert (or auto-merge with --auto-approve) when ready. Use this whenever a user says 'babysit this PR', 'watch the CI', '/babysit-pr', wants a PR shepherded to merge, or wants CI failures auto-fixed in a loop.
Smart Git workflow engine — repo-aware Git Flow branching, CI monitoring, auto-merge, submodule awareness, issue analysis/routing, and deploy-workflow isolation. USE WHEN commit, git, branch, pull request, release, merge, submodule, CI, checks, push and merge, monitor CI, auto-merge, wait for CI, is CI passing, merge my PR, submit PR, code review, --issue-analysis, analyze issues, label issues, route issues across worktrees, agent ownership labels, deploy workflow, push workflow to main, merge workflow only, deploy gh action.
Generate images with GPT Image 2 (ChatGPT Images 2.0) inside Claude Code, using your existing ChatGPT Plus or Pro subscription — no separate OpenAI API key required, no per-image billing. Supports text-to-image, image-to-image editing, style transfer, and multi-reference composition via the local Codex CLI. Triggers on "gpt image 2", "gpt-image-2", "ChatGPT Images 2.0", "image 2", or any explicit ask to generate or edit an image through the user's ChatGPT plan.
Audit a repository for autonomous-agent harness readiness and Symphony-style unattended ticket execution readiness across cold-start docs, rules, API documentation policy/ADRs, lint, hooks, tests, PR automation, repo skills, garbage-collection cadence, workflow contracts, evidence, observability, and smoke-ticket evals. Use for "harness audit", "agent-ready repo", "harness readiness", "make this repo agent-friendly", "API docs policy", "Symphony readiness", "prepare this repo for Symphony", "ticket-level agent automation", or surgical fixes for top harness gaps.
Set up parallel git worktrees of the same repo, one per coding harness (Claude Code, Codex CLI, Cursor, etc.), so multiple AI tools can edit/typecheck/test in parallel without trampling each other's node_modules, build artifacts, or branches. Audits the repo first for shared-state hazards (hardcoded ports, DB file paths, sockets, build dirs that would collide if two worktrees ran a live dev server simultaneously), drops a Gotcha block into CLAUDE.md/AGENTS.md so any agent in any worktree knows the rule, then creates work/<tool> branches, sibling worktrees at <repo-parent>/<repo-name>-<tool>/, and runs the right install command per stack. USE WHEN user says 'set up worktrees for my coding tools', 'I want a Claude / Codex / pi worktree of this repo', 'parallel worktrees per harness', 'harness worktrees', 'make this repo work for all 3 tools at once', 'split this repo per coding agent', 'I use multiple AI coding tools on the same codebase, set them up', or any variant where the goal is one-checkout-per-tool isol
Linear issue management via linearis CLI with team inference. USE WHEN linear, issues, tasks, tickets, backlog, sprint, resolve issue, ship issue, plan project, break down feature, ship daily, what should I work on.
Repository organization expert — structure, audit, and refactor via 8 framework archetypes. USE WHEN creating a new project, auditing repo structure, or planning refactors.