.Codex

Broad skill for building, editing, debugging, styling, and extending the OpsML UI in `crates/opsml_server/opsml_ui`. Use for Svelte 5 components, SvelteKit routes/layouts/load functions, internal `/routes/api` proxy endpoints, UI stores, Tailwind or Skeleton styling, card pages, Scouter dashboards, observability or trace views, agent or prompt interfaces, and general frontend bugfix or feature work inside the embedded OpsML frontend.

Land a PR by monitoring conflicts, resolving them, waiting for checks, and squash-merging when green; use when asked to land, merge, or shepherd a PR to completion.

Pull latest origin/main into the current local branch and resolve merge conflicts (aka update-branch). Use when Codex needs to sync a feature branch with origin, perform a merge-based update (not rebase), and guide conflict resolution best practices.

Push current branch changes to origin and create or update the corresponding pull request; use when asked to push, publish updates, or create pull request.

Create a well-formed git commit from current changes using session history for rationale and summary; use when asked to commit, prepare a commit message, or finalize staged work.

Fix bugs and technical debt with minimal ceremony. Issue GitHub optional — provide one for traceability or work free-form. Replaces /issue-fix.

Post-deploy observability for production services — structured logging, RED metrics + Prometheus, Grafana dashboards, SLO-based alerting. Use when setting up monitoring or instrumenting a live service. Trigger on "add logging", "metrics", "dashboard", "alerting", "observability", "monitor this service".

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep watching open PRs so fresh review feedback is surfaced promptly. Use when the user asks Codex to monitor a PR, watch CI, handle review comments, or keep an eye on failures and feedback on an open PR.

Choose Rust types for operating system paths across the Codex repository. Use when defining new path-bearing types or explicitly migrating existing ones.

Audit dependency freshness — scan outdated deps and CVEs, classify severity, record update/defer/skip decisions in Atrium, gate PASS/WARN/FAIL. Use when checking for outdated packages or deciding whether to upgrade. Trigger on "outdated dependencies", "dependency audit", "are my deps up to date", "should I upgrade".

Build and publish project documentation — Starlight (Astro) for apps, markdown for libraries/services, with IT+EN i18n and VPS deploy. Use when writing user guides, scaffolding a docs site, or publishing docs. Trigger on "write docs", "documentation site", "user guide", "publish docs".

Zero-ceremony atomic task execution. Use for tiny fixes or enhancements (minutes, not hours) that don't warrant SDLC ceremony. Flags: --discuss (disambiguate first), --full (delegate to /pre-commit after execution), --issue N (link commit to GitHub issue).

Turn a feature idea into INVEST-compliant user stories, epics, PRPs/PRDs, and sprint plans. Use when breaking down a feature for implementation or planning a sprint. Trigger on "write user stories", "break this into stories", "create a PRP", "plan the sprint", "story".

Testing against remote executors in integration tests.

Developer onboarding guide that composes architecture mapping, tooling review, and agentic setup review with setup, troubleshooting, and next-steps agents to produce a comprehensive guide at .turbo/onboarding.md and .turbo/onboarding.html. Use when the user asks to "onboard me", "onboard to this project", "generate onboarding guide", "new developer guide", "how do I get started", or "help me ramp up".

Stand up the project's live app and hand it to the user to try a change firsthand, then gate on their verdict before continuing. Use when the user asks to "preview the change", "let me try it", "spin up the app so I can test it", "set it up so I can poke at it", or before finalizing a UI/UX change that needs human eyes.

Post-merge deployment workflow covering feature flags, canary/blue-green rollout, smoke-test verification, and rollback triggers. Use after a PR is merged and you need to ship it safely to production. Trigger on "deploy", "roll out", "canary", "feature flag", "rollback".

Triage, fix, and pre-flight a PR before merge. Checks mergeability, CI, reviews, and bot comments — fixes issues, runs /pre-commit before pushing, then hands off to /pr-merge.

Update the title and body of one or more pull requests.

Run the post-implementation quality assurance workflow including tests, code polishing, review, and commit. Use when the user asks to "finalize implementation", "finalize changes", "wrap up implementation", "finish up", "ready to commit", or "run QA workflow".

Load code-style and task-specific skills, make the change described by the current context, then run post-implementation QA. Use for ad-hoc changes when no plan file or improvements backlog governs the work, and when the user asks to "just implement", "implement directly", "implement without a plan", or "apply the change".

Analyze task complexity and route to a mode by artifact: direct fix for clear-scope changes, or a plan file when the approach needs to be written down. Use when the user asks to "turboplan", "run turboplan", "plan this task", "turbo plan mode", "plan and implement", or "use turboplan instead of plan mode".

Update an existing GitHub pull request's title and description to reflect the current state of the branch. Use when the user asks to "update the PR", "update PR description", "update PR title", "refresh PR description", or "sync PR with changes".

Investigate bugs with unknown root cause. Spawns fresh-context investigation subagent + parallel /review solve companion, persists hypotheses across iterations, hands off to /fix when root cause found.

Safely merge GitHub pull requests using comprehensive pre-merge validation. Use this skill when the user asks to merge a PR, complete a PR workflow, or check if a PR is ready to merge. Validates CI/CD status, reviews, and conflicts before merging with the appropriate strategy.

On-demand situational awareness — fresh git/PR snapshot plus continuation, distilled into one concrete "next action" suggestion. Use mid-session when you've lost track, after a compaction, or starting a new work block. Trigger on "where was I", "what's next", "progress", "what should I do now", "/progress".

Query, update, and audit the registry of all Claude Code components (skills, agents, rules, hooks, plugins) with PDCA lifecycle tracking. Use when listing/inspecting components, finding stale ones, or registering new ones. Trigger on "list skills", "component registry", "what skills exist", "stale skills", "/registry".

Detect technical debt — duplicated code, dead code, TODOs, and oversized functions across the codebase. Use at the end of a session or when auditing code hygiene. Trigger on "find tech debt", "any dead code", "duplicated code", "code hygiene", "techdebt".

Enforce existence, reuse, mirror, and symmetry principles to keep new code minimal and consistent with surrounding code. Use when writing new code in an existing codebase, adding new features, refactoring, or making any code changes.

Produce an implementation plan at .turbo/plans/<slug>.md. Use when the user asks to "draft a plan", "draft the plan", "write an implementation plan", "plan this change", "create an implementation plan", or needs a first-draft plan file before refinement.

Run the project's full verification gate: every check the project defines as a pass/fail condition, built from its CI config, check scripts, and configured tools, or from a formatter-linter-test baseline when it declares none. Use when the user asks to "run checks", "run the verification gate", "run lint and tests", "run the test suite", "check that this passes", "does this pass CI", or "run the project's checks".

FigMirror mirrors the visual style of a top-conference paper figure (NeurIPS / ICML / ICLR / Nature family) onto the user's own data. Takes dirty data plus a reference figure screenshot (cropped or uncropped), preprocesses the reference crop, runs a Drawer/Reviewer loop, and outputs a camera-ready PDF plus a self-contained matplotlib script with an inline DATA SECTOR.

Run SQL queries against psql, BigQuery, or MySQL from the terminal, including natural-language-to-SQL and schema exploration. Use when analyzing data, inspecting DB state, or debugging tables. Trigger on "query the database", "SQL", "show me data from", "explore table".

Phase 0 validation gate — problem framing, competitive analysis, feasibility, and a go/no-go checkpoint before committing to a feature. Use when evaluating whether an idea is worth building, before /story or /design. Trigger on "is this worth building", "validate this idea", "discovery", "should we build".

Stage, format, lint, test, review, smoke test, and re-run itself until stable. Use when the user asks to "polish code", "refine code", "iterate on code quality", "review loop", "clean up, test, and review loop", or "run the polish loop".

Govern Lime legacy cleanup, fact-source convergence, current/compat/deprecated/dead classification, and guardrails.

Full validation gate before committing — quality checks, tests, coverage, security scan, changelog, and companion review. Use right before a commit to verify code is ready. Trigger on "pre-commit", "validate before commit", "ready to commit", "run all checks".

Update Codex's pinned `v8` / `rusty_v8` versions, validate the release-candidate path, and investigate failed V8 canary or artifact builds. Use when asked to bump V8, update `rusty_v8` artifacts, prepare or validate a V8 release candidate, check `v8-canary`, or diagnose why a V8 version update no longer builds.

Run a non-interactive Claude Code print-mode call from Codex. Use when the user asks to "claude print", "ask claude", "run claude", "consult claude", or when a Codex Turbo skill needs Claude as an independent peer reviewer.

Shared commit message rules and technical constraints referenced by $stage-commit and $commit-staged. Not typically invoked directly.

Shared writing style rules for GitHub-facing output (PR comments, PR descriptions, PR titles, issues, design proposals). Differentiates insider vs outsider voice based on author association. Not typically invoked directly — loaded by other skills before composing GitHub text.

Deep architecture report that fans out parallel inspections across different aspects of the codebase (structure, tech stack, APIs, patterns, data flow, dependencies, testing) and synthesizes findings into a comprehensive document at .turbo/codebase-map.md and .turbo/codebase-map.html. Use when the user asks to "map the codebase", "map codebase", "architecture report", "codebase overview", "architecture overview", "what am I looking at", or "explain this codebase".

Extract lessons from the current session, or sweep the project's past sessions when asked, and route them to the appropriate knowledge layer (project AGENTS.md, auto memory, existing skills, or new skills). Use when the user asks to "self-improve", "distill this session", "distill past sessions", "sweep past sessions", "extract lessons from all sessions", "save learnings", "update AGENTS.md with what we learned", "capture session insights", "remember this for next time", "extract lessons", "update skills from session", or "what did we learn".

Run the code and documentation simplification passes together over one scope, launching every review sub-agent concurrently before applying a single round of fixes. Use when the user asks to "simplify all", "simplify everything", "simplify code and docs", "clean up code and docs", "run both simplify skills", or "simplify code and docs in parallel".

Run a multi-agent review of changed files for scope, reuse, quality, efficiency, clarity, and altitude issues followed by fixes. Use when the user asks to "simplify code", "review changed code", "check for code reuse", "review code quality", "review efficiency", "simplify changes", "clean up code", "refactor changes", or "run simplify".

Run a multi-agent review of code comments and markdown documentation for unnecessary content, then fix the issues. Covers comments that misdescribe the code, what-restating comments, name-mirroring doc comments, status-update prose, and other documentation noise. Use when the user asks to "simplify docs", "simplify documentation", "clean up comments", "clean up docs", "review documentation", "strip unnecessary comments", "fix stale comments", "reduce doc noise", or "run simplify-docs".

Audit, design, write, materially revise, or remove Tutti tests. Use whenever Codex changes or reviews unit, component, conformance, integration, regression, platform, or repository tests; enforce a protected product contract, credible failure, correct owning boundary, negative-control evidence, overlap review, deterministic setup, and an executing CI lane.

Audit Dockerfiles and Compose files against the 10 common Docker mistakes — image security, build efficiency, runtime safety. Use when reviewing or hardening Docker configs. Trigger on "audit my Dockerfile", "check this Compose file", "Docker best practices", "is my container secure".

Validate user stories — INVEST scoring, story-to-test coverage mapping, PRP completeness, and development-readiness assessment. Use after writing stories and before starting implementation. Trigger on "validate the stories", "are these stories ready", "INVEST check", "story coverage", "is this ready to build".

Model visible context

Test authoring guidance

Apply findings by making the suggested code changes. Applies accepted verdicts, escalates ambiguous findings to the user, and offers to note genuine improvements for later. Use when the user asks to "apply findings", "apply fixes", "apply suggestions", "apply accepted findings", "fix the findings", or "apply the review results".

Consult Claude Code for second opinions, brainstorming, or difficult debugging from Codex. Use when the user asks to "consult claude", "ask claude", "get claude's opinion", "brainstorm with claude", or "discuss with claude".

Consult ChatGPT Pro via ChatGPT browser automation for problems that resist standard approaches. Use when stuck on a very hard problem, when standard approaches have failed, when multiple debugging attempts haven't worked, or when the user says "ask the oracle", "consult oracle", "consult chatgpt", "I'm completely stuck", "I've tried everything", or "nothing is working".

Write a handoff file at .turbo/handoff/<YYYY-MM-DD>-<slug>.md capturing current session state — task, status, open decisions, in-flight changes, next step — so a fresh session can continue without re-deriving context. Use when the user asks to "create a handoff", "create handoff", "save handoff", "handoff before compact", "save session state", "handoff for next session", or "capture session state".

Align on the shape of a change through an interview, then implement it. Escalates open product decisions and settles the implementation shape in conversation. Use when the user asks to "discuss this change", "align on this change first", "ask me questions first", "interview me then implement", "agree on the approach before coding", or wants the shape of a single change settled before any code is written.

Find dead code using parallel sub-agent analysis and optional CLI tools, treating code only referenced from tests as dead. Use when the user asks to "find dead code", "find unused code", "find unused exports", "find unreferenced functions", "clean up dead code", or "what code is unused". Analysis-only — does not modify or delete code.

Execute an implementation plan file produced by $draft-plan or $turboplan. Runs pre-implementation prep, then runs $implement to execute the steps and finalize once they are all done. Use when the user asks to "implement plan", "implement the plan", "execute the plan", "run the plan", "implement plans/<slug>.md", "start implementing the plan", or starts a fresh session to implement a previously drafted plan.

Close out a change without the deep review loop: stage, simplify code and docs, run the project's checks, smoke test, update the changelog, self-improve, and ship. Use when the user asks to "quick finalize", "quickly finalize", "finalize quickly", "light finalize", "wrap this up quickly", "close this out without the full review", or "ship this without the deep pass".

Detect what dev tooling infrastructure a project has and flag gaps across linters, formatters, pre-commit hooks, test runners, and CI/CD pipelines. Returns structured findings without applying changes. Use when the user asks to "review tooling", "check project tooling", "what tooling is missing", "review dev infrastructure", or "tooling audit".