skills

Author local Maestro iOS-Simulator E2E flows for the Kata Code mobile app using the reusable TS orchestrator and Kata-specific flows. Use when adding or updating flows under mobile-e2e/.

Assess and selectively port changes from the upstream T3 Code fork (pingdotgg/t3code) into Kata Code. Use whenever the user wants to review what upstream has done, assess the diff, decide what to bring in, triage upstream commits, plan a vendor-pull, run an upstream scan, or figure out which upstream changes are worth porting. Covers scanning upstream since the last baseline, grouping commits by effort and risk, recommending Port/Skip/Watch per change, and re-implementing chosen changes as fork-original commits with Kata branding applied from the start.

Use this skill for multi-step, spec-driven, or acceptance-gated implementation work that should move through Plan, Build, and Verify phases.

Author local Playwright Electron E2E tests for Kata Code using the reusable harness and Kata-specific flows. Use when adding or updating tests under e2e/.

Use when preparing, packaging, tagging, or publishing Skiller Desktop releases, including GitHub release CI, macOS code signing, notarization, release secrets, and desktop version bumps.

Compact the current conversation into a handoff document for another agent to pick up.

Validate Kata Code nightly releases on macOS with the @Computer plugin. Start and update the nightly app, use its New Project flow to create a timestamp-suffixed nightly UAT project under `/Volumes/EVO/dev`, then execute explicit acceptance criteria for a Codex GPT-5.4-Mini chat, Browser and Files panels, and git commit flow; capture criterion-level screenshots and write an evidence-linked report in the created project. Use when validating or documenting the Kata Code nightly release flow.

Finalize the current feature branch by running the `simplify`, `strict-quality-review`, and `/okf update` passes in order, each through its own subagent, automatically accepting in-scope fixes and committing after each phase. Use when the user says finalize, finish this branch, prep for PR, polish and review, run final cleanup, or asks to combine `/simplify`, `/strict-quality-review`, and OKF documentation updates before shipping.

Run a strict maintainability review with parallel adversarial subagents for abstraction quality, giant files, and spaghetti-condition growth. Use for a strict quality review, deep code quality audit, or especially strict maintainability review.

Create, read, and maintain Open Knowledge Format documentation bundles in repositories. Use this skill when the user asks for /okf, OKF, Open Knowledge Format, docs-as-knowledge, reading project context from docs, reorganizing docs into an agent-readable bundle, updating docs/specs/ADRs after a session or PR, or adding AGENTS.md instructions for agents to consume and maintain the docs bundle. Supports /okf read, /okf init, and /okf update workflows.

Use when finishing a ticket, feature branch, or pull request and the user asks to validate, demo, verify, sign off, show that it works, run UAT, provide acceptance evidence, or decide whether work is ready to merge. This skill gathers tangible evidence that completed work functions as intended, with videos, screenshots, terminal recordings, JSON responses, output files, logs, and a concise human test guide. Use for web apps, CLI and TUI apps, APIs and SDKs, and native apps including Electron-type apps. Trigger on phrases like "UAT", "verify", "show me it works", "demo this", "walk me through", "ready to merge", "can we merge?", "acceptance test", "validate the changes", "sign off", or any request for proof that a feature branch or PR works.

Structured code review closeout. Codex review is the default when no engine is set and is the recommended reviewer. Use this for code-review, autoreview, second-model review, CodeRabbit, Greptile, Cursor, Codex review, Claude review, PR review, and final quality/security review requests.

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.

Act as the lead orchestrator for complex coding work. Use this skill when the user asks to orchestrate, delegate, run agents or workers, fan out work, use parallel agents, coordinate sub-agents, dispatch cloud agents, create worktrees, execute a broad plan, verify a feature, or manage multi-step implementation where independent investigation, implementation, review, or verification could improve speed, quality, or confidence. Prefer this skill for substantial cross-file or acceptance-gated work even when the user does not explicitly say "orchestrate".

AI-powered code review using CodeRabbit.Trigger for any explicit review request AND autonomously when the agent thinks a review is needed (code/PR/quality/security).

Interrogation session that challenges a spec or plan against the codebase and existing domain model, sharpens terminology, and updates the plan and project context (CONTEXT.md, AGENTS.md, README.md, ADRs) inline as decisions crystallise. Use when the maintainer wants to stress-test a plan against their project's language and documented decisions.

Simplify and refine recently modified code for clarity and consistency. Use after writing code to improve readability without changing functionality.

Use this skill for pull request workflows - creating PRs (branch, commit, push, open), reviewing PRs (code quality, test coverage, issue fixing), addressing PR review comments (fix feedback, respond to reviewers), or merging PRs (CI checks, merge, cleanup). Handles the complete PR lifecycle via gh CLI. Triggers include "create PR", "open PR", "review PR", "merge PR", "address PR comments", "fix review feedback", "respond to reviewer", "push for review", "submit PR".

Codex code review closeout: local dirty changes, PR branch vs main, parallel tests.

Repo-wide documentation sweep for updating project docs, context, ADRs, diagrams, README files, agent instructions, and documentation sites after feature work, decisions, or direction changes. Use this skill whenever the user asks to update docs, refresh documentation, prepare for PR, finish a branch, merge, ship, close out work, record what changed, or align docs with code. It first discovers the repo's key Markdown documentation and docs sites, ignores historical archives by default, presents the proposed docs plan for approval, then updates only the approved docs surgically.

Audit and improve AGENTS.md files in repositories. Use when user asks to check, audit, update, improve, or fix AGENTS.md files. Scans for all AGENTS.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "AGENTS.md maintenance" or "project memory optimization".

TypeScript/JavaScript codebase hardening: maintainability, code quality, architecture cleanup, repo scoring, agent-friendly structure, godfiles, feature folders, DRY, type safety, traversability, feedback loops, worktrees, subagents, swarm refactors.

Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.

Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions. Trigger words include: 'fix CI', 'debug GitHub Actions', 'gh pr checks', 'CI is red', 'GitHub Actions failed', 'fix the build', and similar phrases indicating a need to investigate and resolve CI failures in a GitHub-hosted repository.

Linear ticket lifecycle for any project. Use when starting work on a Linear issue, ending work on an issue, or asking what to work on next. Triggers include, start KAT-N, pick up, implement, finish, complete, done with, close, what's next, next ticket, next issue. Handles blocker validation, status transitions, context loading, branch creation, evidence gating, and chain promotion.

Comprehensive accessibility audit for iOS/macOS apps - VoiceOver, Dynamic Type, color contrast, touch targets, keyboard navigation, Reduce Motion, and App Store Review preparation

Comprehensive App Store compliance audit covering all 5 Apple guideline categories (Safety, Performance, Business, Design, Legal) with mandatory GitHub issue output

Use this skill when the user asks to run an iOS app, launch an app in the simulator, tap or click buttons, interact with simulator UI, automate iOS testing, take screenshots, enter text in fields, swipe or scroll, check accessibility, or perform any iOS simulator interaction. Covers app launching, UI navigation, gestures, form input, and simulator lifecycle management.

Run structured brainstorming sessions using paired explorer/challenger agent teams. Explorers generate ideas, challengers play devil's advocate, and 2-3 rounds of debate produce pressure-tested proposals. Use when brainstorming product ideas, exploring feature directions, evaluating strategic options, generating milestone candidates, or when the user says "brainstorm", "explore ideas", "what should we build next", "generate options", or "run an ideation session".

Use this skill when collecting TestFlight feedback, gathering beta tester screenshots, reviewing App Store Connect feedback, or when the user asks to collect TestFlight comments, compile beta feedback, or create a feedback report. Creates consolidated markdown reports from App Store Connect.

Use this skill when committing code changes, creating git commits, staging files for commit, or when the user asks to commit, save changes, or make a commit. Handles conventional commit format, explicit file staging, and commit message crafting.

Use this skill when converting Claude Code slash commands to Skills format. Handles transformation from ./commands/*.md to ./skills/*/SKILL.md, including YAML frontmatter conversion, name transformation to gerund form, description enhancement for invocation triggers, and batch processing. Invoke when user asks to convert commands to skills, migrate slash commands, or transform command files.

Use this skill when writing iOS unit tests, debugging test failures, creating Swift Testing tests, testing SwiftData models, or when the user asks to add tests, fix tests, improve coverage, or test Swift code. Covers Swift Testing framework, ModelContainer lifecycle, and coverage requirements.