orakitine
- 25 skills
- 0 followers
- 6 hours ago last updated
- ▌ Playwright Browser · orakitineHeadless browser automation using Playwright CLI. Use for browser testing, screenshots, scraping, and parallel browser sessions. Token-efficient CLI — no MCP overhead.
- ▌ Tdd · orakitine bundleTest-driven development via the red-green-refactor loop using vertical slices (one test → one implementation at a time). Tests verify behavior through public interfaces, not implementation details. Use when user wants to build a feature or fix a bug test-first, says "TDD", "red-green-refactor", "test-first", "write tests first", asks for integration tests, or invokes `/tdd`.
- ▌ Speak · orakitine bundleProvider-agnostic text-to-speech output with audio caching. Converts text to audio and plays it immediately. Caches generated audio to avoid redundant API calls on repeated phrases. Falls back through available TTS providers (elevenlabs, macOS say). Use as a composable voice output primitive from any skill, agent, or workflow. TRIGGER when: user says "say out loud", "say aloud", "announce", "read out", "tell me out loud", or any phrasing that implies audible/voice output rather than text. Also trigger when user says "say X" at the end of a task request (e.g., "do X and when done say Done") — this means spoken output, not typed. DO NOT TRIGGER when: "say" is used figuratively ("let's say we have...") or means "write/type" in context.
- ▌ Browser · orakitine bundleHeadless browser automation via playwright-cli for testing, screenshots, scraping, and parallel sessions. Use for UI testing, web scraping, screenshot capture, or any browser-based workflow.
- ▌ Caveman · orakitine bundleUltra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.
- ▌ Handoff · orakitine bundleCompacts the current conversation into a handoff document so a fresh agent can pick up the work. Use when user says "handoff", "hand off", "create handoff", "handoff doc", "pass to next session", "summarize for next agent", or invokes /handoff. Optional argument describes what the next session will focus on.
- ▌ Diagnose · orakitine bundleDisciplined diagnosis loop for hard bugs and performance regressions. Reproduce, minimise, hypothesise, instrument, fix, regression-test. Use when user says "diagnose this", "debug this", reports a bug, says something is broken / throwing / failing, or describes a performance regression. Triggers: "diagnose", "debug this", "why is X broken", "X is throwing", "X is failing", "perf regression", "this got slow", "intermittent failure", "flaky test".
- ▌ Grill Me · orakitine bundleRelentless interview mode that drives toward shared understanding of a plan or design. Walks every branch of the decision tree one question at a time, each with a recommended answer. Use when user says "grill me", "interview me", or invokes /grill-me.
- ▌ Menu App · orakitine bundleConvert a restaurant menu (PDF, image, Word, HTML, Markdown) into a self-contained single-page HTML ordering app. Extracts items, prices, categories, and contact info, then generates a mobile-friendly page with search, filters, cart, and copy-to-clipboard order text. Use when given a menu file to turn into an interactive ordering tool.
- ▌ Zoom Out · orakitine bundlePulls the agent up a layer of abstraction and maps the relevant modules and callers around the code in focus, using the project's domain glossary vocabulary. Use when you're unfamiliar with a section of code or invoke "zoom out" or `/zoom-out`.
- ▌ Doc Cache · orakitine bundleTransparent read-through cache for documentation lookups. Checks cache before WebFetch, caches results with expiration, garbage collects stale entries. TRIGGER when: fetching docs, API references, technical documentation, or user asks to look up library/framework usage. DO NOT TRIGGER when: user provides inline code or docs directly, or the information is already in context.
- ▌ Gen Image · orakitine bundleGenerate or edit images using AI image models. Currently supports Google Gemini (Nano Banana Pro for creation, Nano Banana for editing). Provider-agnostic design. Use for image generation, visual content creation, or image editing tasks.
- ▌ Elevenlabs · orakitine bundleText-to-speech, multi-voice dialogue, custom voice design, sound effects, music generation, and audio processing using the ElevenLabs API via the el CLI. Use for voice generation, character voices, designing new voices (e.g. children/creatures), expressive narration with audio tags, audio content creation, or sound design.
- ▌ Living Plan · orakitine bundleAuthors and maintains a living, executable engineering plan as a single Markdown document in docs/plans/. The plan has a fixed goal (Purpose + a Definition of Done) but a living path: a status-tracked phase/task checklist ([] idle, [wip] in progress, [x] done, [f] failed), an append-only amendments log, and metadata that survives across agents and sessions. Reads CONTEXT.md for domain vocabulary and links docs/adr/ decisions; never writes ADRs itself. Use when the user wants to plan, spec, or design new work; update or extend an existing plan; link plans/ADRs; or build (execute) a plan — or invokes /living-plan. Triggers: "plan this", "write a spec", "design doc", "living plan", "build the plan", "/living-plan".
- ▌ Skill Forge · orakitine bundleCreates, evaluates, and refines agent skills following the agentskills.io specification. Use when building new skills from scratch, auditing existing skills for quality, or cleaning up skill structure and naming. Produces portable skills that work across any compliant agent harness.
- ▌ Skill Guide · orakitine bundleDiscovers and explains installed skills and agents. Lists what's available (global and project), shows how to use them, explains skill families and dependencies. Use when asking what skills exist, how to use a skill, or what tools are available for a task.
- ▌ Fork Terminal · orakitine bundleFork a terminal session to a new window with a command or agentic coding tool (Claude Code, Codex CLI, Gemini CLI). Supports context handoff. Use when the user requests 'fork terminal', 'new terminal', or 'fork session'.
- ▌ Browser Review · orakitineParallel UI validation that discovers user stories from YAML files, fans out browser-qa agents to test each story, and aggregates pass/fail results with screenshots. Use for acceptance testing, UI review, or regression testing across multiple user stories.
- ▌ Grill With Docs · orakitine bundleGrilling interview that stress-tests a plan against the project's existing domain language and documented decisions, sharpening terminology and updating CONTEXT.md and ADRs inline as decisions crystallise. Use when user says "grill me with docs", "grill on the design", "challenge this against our context", or invokes /grill-with-docs.
- ▌ Browser Workflow · orakitineExecutes saved browser automation workflows with consistent setup, teardown, and reporting. Loads workflow files and runs them through the browser skill. Use for repeatable browser automations like scraping, form-filling, or monitoring.
- ▌ Browser Microscope · orakitine bundleReal-browser DOM and layout microscope. Runs arbitrary JS in a live page, hit-tests why a click won't land (elementFromPoint — what element is covering it), dumps scroll and box geometry (scrollWidth, offsetLeft, overflow, scroll-padding), reads CSS custom-property design tokens via getComputedStyle, and sweeps viewport widths to find container-query / breakpoint thresholds. Use when a button does not respond to clicks, an element is mysteriously overlapped, covered, clipped or off-screen, scroll / snap geometry looks wrong, computed styles or tokens need reading live, z-index / stacking is suspect, or a layout bug only appears at certain widths. Drives the local Playwright npm package (no global CLI required) and supports HTTP basic-auth and self-signed staging certs. The layout-forensics complement to the journey-walking browser and browser-qa skills.
- ▌ Setup Toolbox Context · orakitine bundleScaffolds the CONTEXT.md glossary and docs/adr/ directory that grill-with-docs and improve-codebase-architecture expect. Single-context or multi-context layout based on the repo. Use when starting a new project, adopting the CONTEXT.md convention, or invoking /setup-toolbox-context.
- ▌ IOS Simulator Microscope · orakitine bundleReproduce and measure iOS-Safari-only layout, rendering, and interaction bugs on a booted iOS Simulator (iPad/iPhone) — the real-device counterpart to the desktop-Playwright browser-microscope. Drives Safari via safaridriver WebDriver + xcrun simctl to inject JS, read live geometry / computed styles / viewport units, and screenshot the device; uses macOS CGEvent drags to scroll and collapse the toolbar so dynamic-viewport dynamics appear. Use when a bug only shows in real iOS Safari and not in Playwright/Chromium/jsdom: dynamic viewport (dvh/svh/lvh) or stale initial-containing-block gaps, 100vh/100% sizing wrong after toolbar collapse, :focus-visible over-matching on programmatic or touch focus, momentum-scroll or rubber-band glitches, sticky/fixed drift, top-layer <dialog>/sheet coverage, safe-area insets, or any "works in Storybook but broken on iPad" report. Trigger phrases: "test on the iPad simulator", "reproduce this on iOS", "iOS Safari only bug", "check on real Safari".
- ▌ Improve Codebase Architecture · orakitine bundleFind deepening opportunities in a codebase — refactors that turn shallow modules into deep ones, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. The aim is testability and AI-navigability. Use when user wants to "improve architecture", "find deepening opportunities", "rescue the ball of mud", "consolidate tightly-coupled modules", "find refactoring opportunities", "make code more testable", or invokes `/improve-codebase-architecture`.
- ▌ Registry · orakitine bundleSkill registry for distributing skills, agents, prompts, output styles, and config files across devices, projects, and teams. Use when installing, distributing, syncing, or managing skills from a catalog — including installing an output style or statusline config on a new machine.