Skill Claude CodeCodex
Classify finished pipeline runs from the configured tracker — clean single pass, hard recovery, loop checkpoints, or cause not recorded — and rank what the second passes cost in wall-clock hours. Read-only; hands the top cause to om-prepare-issue. Use for "pipeline retro", "why is our pipeline slow", "what is costing…
Skill Claude CodeCodex
Diagnose what state one open PR is actually in — unfinished plan steps, missing review, unresolved conversations, red CI, base conflicts, missing QA evidence, merge-ready — then run the matching chain of om- skills in order and publish a status report. Use for "finish PR 123", "what is left on PR 123", "drive PR 123…
Skill Claude CodeCodex
Create one well-formed tracker issue from a brief without implementing it — dedupes against existing issues and PRs, links a covering spec (authoring one via om-auto-write-spec on a design-only PR when a feature needs it), attaches user-provided images as tracker evidence, otherwise embeds step-by-step guidance, and…
Skill Claude CodeCodex
Prepare a reusable, technology-agnostic environment for local tests and QA. Compiles discovery into cross-platform launch scripts, provisions the configured browser provider autonomously, and writes the shared test-env descriptor consumed by UI and integration-test skills.
Skill Claude CodeCodex
Review all currently unreviewed open pull requests, newest first, using the om-auto-review-pr skill and respecting in-progress claim locks.
Skill Claude CodeCodex
Read-only root-cause analysis for a tracker issue. Identifies the bug's location and the minimal change surface so the next agent can implement the fix without re-exploring the repo. Outputs a short summary, the files that need to change, and the proposed approach.
Skill Claude CodeCodex
One-time pipeline configurator. Inspects the repo (default branch, validation scripts, labels), asks a few questions, writes .ai/agentic.config.json — the file every other skill reads — installs the tracker descriptor, and generates missing project docs (SDLC.md, CODEREVIEW.md, BACKWARDCOMPATIBILITY.md, AGENTS.md…
Skill Claude CodeCodex
Write and review feature specifications to staff-engineer standards. Skeleton-first drafting with a hard Open Questions gate, research against market leaders, an implementation breakdown into phases and steps that feeds om-auto-create-pr, and a severity-ranked architectural review format. Use when starting a new spec…
Skill Claude CodeCodex
Evidence-first design review of a PR's UI. Walks the changed screens in a real browser, performs the user's tasks, and posts findings ranked by user impact, each with evidence, a pattern, a trade-off and an acceptance criterion.
Skill Claude CodeCodex
Extract the repository's design contract (tokens, component registry, screen archetypes, conventions) into .uxproof/ so every UX skill judges against THIS repo's design system, whatever it is. Run once per repository; re-run to refresh after design-system changes.
Skill Codex
Turn a vague product, UI/UX, or AI feature idea into a decided direction. Use when shaping a feature, simplifying an overcomplicated flow, deciding whether and how to use AI, defining screen states, planning validation, or preparing a design handoff for engineering.
Skill Claude CodeCodex
Read-only triage gate for an autofix chain. Decides whether a tracker issue is a real, still-unfixed defect on the current branch. Stops the chain cleanly with NOACTIONNEEDED when the issue is already fixed, already in progress by someone else, already covered by an open PR, or not actually a bug.
Skill Claude CodeCodex
Guide a product discovery conversation and write product-brief.md with the problem, evidence, scope, decisions, and the next uncertainty to resolve. Use for product discovery, defining a product, or refreshing its brief. Supports existing products, client ideas, and own ideas.
Skill Claude CodeCodex
Turns a product brief (its Scope and Key flows) or a spec's Phasing into a tracker backlog — epics, stories with acceptance criteria, tasks — with stable ids in titles, epic checklists, and Epic links, filing every issue through om-prepare-issue so dedupe, SDLC labels, and rationale come for free. Refuses a brief that…
Skill Claude CodeCodex
Build a neutral clickable low-fi prototype from a product brief during discovery, after the first synthetic panel and before refreshing the brief or drafting a backlog. Preserve business rules and explicit assumptions, simulate the chosen flow locally, and verify navigation and relevant states in a browser. Use for…
Skill Claude CodeCodex
Adds the product layer to a repository that om-setup-agent-pipeline already configured — one yes per product role, a discovery block in .ai/agentic.config.json, the Discovery stage, Definition of Ready, product roles, and protected product decisions appended to SDLC.md between markers, the research directory, and a…
Skill Claude CodeCodex
Builds a panel of personas from real material, interviews them under decision pressure (never stated preference), and walks a flow through their eyes — on a brief, a spec, a prototype, or the running app. Fresh panels, repeated runs, believe only what repeats; saturation and a parity check against real interviews when…
Skill Claude CodeCodex
Runs a manual QA session for a PR, issue, or branch — publishes an interactive runbook the tester works through in parallel from the moment a plan exists, updated with AI verdicts and bugs at the end. Never touches the tracker itself. Unlike om-auto-qa-pr's automated sign-off, this is human-in-the-loop and grows a…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: