Latest Agent Skills

Adaptive, resumable Git delivery across repositories and agent runtimes — probe policy, checkpoint coherent work, publish, review, integrate, and verify cleanup

A/B test design and experiment planning for paid advertising. Structured hypothesis framework, statistical significance calculator, test duration estimator, sample size calculator, and platform-specific experiment setup guides (Meta Experiments, Google Experiments, LinkedIn A/B). Use when user says A/B test, split test, experiment design, test hypothesis, statistical significance, sample size, or test duration.

PPC financial calculator and modeling tool. CPA, ROAS, CPL calculations, break-even analysis, impression share opportunity sizing, budget forecasting, LTV:CAC ratio analysis, and MER (Marketing Efficiency Ratio) assessment. Requires zero API access. Works with pasted data from exports. Use when user says PPC math, ad calculator, break-even, budget forecast, ROAS calculator, CPA calculator, impression share, LTV CAC, or MER.

Search Experience Optimization: reads Google SERPs backwards to detect page-type mismatches, derives user stories from search intent signals, and scores pages from multiple persona perspectives. Identifies why well-optimized pages fail to rank by analyzing what Google rewards for each keyword. Use when user says "SXO", "search experience", "page type mismatch", "SERP analysis", "user story", "persona scoring", "why isn't my page ranking", "intent mismatch", or "wireframe".

End-of-session context handoff. Saves session state so the next session or a parallel agent can pick up exactly where the left off. Run this when context is getting full (~80%) or before stopping work.

Verify project behavior anchors — compilation, tests, and interaction checks after autonomous runs. NOT the Claude Code built-in /verify (which runs the app to observe a single change working) — this one walks the CLAUDE.md "Features (Behavior Anchors)" list.

Show a provider-neutral, freshness-aware snapshot of active Agent work, Git delivery, execution identity, and usage limits. Use for “what's going on right now”, what is running, progress updates, active runtime/provider/model, or stuck-work checks.

Clade coverage-driven project review — walks every VERIFY.md checkpoint, fixes failures in-session, converges when all checkpoints pass. NOT the Claude Code built-in /review (which reviews a single pull request diff) — if the user wants a PR review, route to /review-pr (Clade's PR reviewer) or the CC built-in.

Create repository-adaptive checkpoint commits for coherent work, including requests to split changes into commits and push; publication remains separately authorized

AI image generation Creative Director powered by Google Gemini Nano Banana models. Use this skill for ANY request involving image creation, editing, visual asset production, or creative direction. Triggers on: generate an image, create a photo, edit this picture, design a logo, make a banner, visual for my anything, and all /banana commands. Handles text-to-image, image editing, multi-turn creative sessions, batch workflows, and brand presets.

Autonomous session launcher — morning briefing, unattended overnight runs, cross-project patrol, auto-research

Autonomous discovery of concepts, methods, and vocabulary we have NOT heard of yet — sweeps broadly, diffs against a known-concepts ledger, and reports only what is genuinely new plus whether it names a gap in this stack. Built because 'graph engineering' had to arrive by word of mouth: a fixed topic list can only refresh what you already named, so it can never surface the thing you did not know to look for. Use for periodic/scheduled discovery, 'what's new in agent engineering', 'what are we missing', 'anything we haven't heard of'. Triggers: radar, discover, what's new, unknown unknowns, 新概念, 我们没听过的, 有什么没跟上的 — NOT for researching a topic you can already name (use /research), NOT for model releases (use /model-research), NOT for internal priorities (use /next).

Record, search, and prune per-project learnings in .claude/learnings.jsonl — typed, confidence-scored, searchable across sessions

In-session iterative loop — keeps Claude running in the current session until a task is done. Unlike /loop (which spawns background workers), /iloop stays in the current session and re-prompts each iteration via Stop hook. Use for: 'keep fixing until tests pass', 'iterate until this feature works', autonomous debugging. Triggers on: '/iloop', 'in-session loop', 'keep iterating', 'loop until done'.

Equipment manager for Claude Code projects — inventory local skills/agents/scripts, audit external upstream repos (red-flag + prompt-injection screening), and sync selectively after user approval. Absorbs container-layout skill repos AND single-skill-at-root repos (e.g. a company design-system repo). Project-agnostic.

Generates a morning briefing — what ran overnight, what it cost, what to do next

End-of-session documentation sync — updates TODO.md and PROGRESS.md only (run /commit after to commit everything)

Full release pipeline — tests → coverage → review gate → version bump → CHANGELOG → commit → PR

Quick 1-line status check after the user hit esc during a long generation. Report whether work is still progressing or stuck, then continue if fine. NOT a plan or replan — just a heartbeat.

Clade goal-driven autonomous improvement loop (Blueprint architecture — deterministic pre/post phases + LLM supervisor/worker nodes, converges when goal met or max-iter hit). NOT the Claude Code built-in /loop (which polls a prompt on an interval like `/loop 5m /foo`) — if the user wants interval polling, route to the built-in.

Toggle the statusline quota pace indicator (mode/theme)

Accept the recommendation from the most recent A/B/C option set and execute it without re-asking. Use when the user says "按你推荐的来" / "go with your pick" — they glanced at the options, the recommendation looked right, they don't want to re-read all of them.

An autocomplete input component that provides search hints and suggestions as users type, with support for grouping, custom rendering, and various input configurations

Virtual list component for efficient rendering of large lists. Invoke when user needs to implement high-performance lists with thousands of items in Naive UI.

Notification component for displaying toast messages and alerts. Invoke when user needs to implement notification system, toast messages, or status alerts in Naive UI.

A numeric input component with step controls, formatting, validation, and min/max constraints

Global style component that syncs theme styles to document.body. Invoke when user needs to apply global theme styles like background color and font family to the entire page.

Floating action button component with menu, badge, and group support. Invoke when user needs floating buttons, FAB menus, or quick action buttons in Naive UI.

A component for dynamically adding and removing tags with customizable input and trigger elements

Descriptions component for displaying key-value pairs in a structured layout. Invoke when user needs to display item details, configuration info, or form-like read-only data in Naive UI.

A color picker component for selecting colors with support for multiple color modes, alpha channel, swatches, custom triggers, and native color selector integration

Overview of all Naive UI components organized by category. Invoke when user needs a quick reference to all available components or wants to explore the component library.

A tree-structured select component for hierarchical data selection with features like multiple selection, checkboxes, filtering, and async loading

A time selection component for choosing specific times in Naive UI. Supports 12/24 hour formats, time zones, disabled times, step intervals, and custom formatting.

Page header component for page titles with navigation and content slots. Invoke when user needs page headers, breadcrumb navigation, or page title sections in Naive UI.

Loading Bar component for showing loading progress. Invoke when user needs to implement loading indicators, route transition loading, or async operation feedback in Naive UI.

Legacy grid system based on row and column layout. Invoke when user needs to implement traditional 24-column grid layouts in Naive UI.

A comprehensive date picker component supporting various date types (date, datetime, range, month, year, quarter, week) with formatting, validation, shortcuts, and async operations

Typography components for text styling including headings, paragraphs, lists, and text elements. Invoke when user needs styled text, headings, lists, or typography in Naive UI.

Popconfirm component for confirmation dialogs in popover style. Invoke when user needs to implement confirmation prompts, delete confirmations, or action verifications in Naive UI.

Pagination component for navigating through data pages. Invoke when user needs to implement pagination, page navigation, or data pagination controls in Naive UI.

A powerful data table component for displaying structured tabular data with features like sorting, filtering, pagination, selection, tree data, virtual scrolling, and more.

Breadcrumb component for navigation path display. Invoke when user needs to implement breadcrumb navigation, show current location, or navigation hierarchy in Naive UI.

Layout system for Naive UI including Grid, Flex, Space, and Layout components. Invoke when user needs to create responsive layouts, grid systems, or understand layout components.

Border design specifications for Naive UI components. Invoke when user needs to understand border styles, radius options, or shadow styles used throughout Naive UI.

Watermark component for adding watermarks to content areas. Invoke when user needs text or image watermarks, fullscreen watermarks, or content protection in Naive UI.

Statistic component for displaying statistical values with labels, prefixes, and suffixes. Invoke when user needs to implement statistics displays, metrics dashboards, or data summaries in Naive UI.

Custom scrollbar component with consistent styling. Invoke when user needs to implement custom styled scrollbars or scrollable containers in Naive UI.

Popselect component for selecting options in a popover. Invoke when user needs a lightweight selection dropdown without a full select component in Naive UI.

A one-time password input component for entering verification codes with support for masking, custom rendering, and form integration

Highlight component for highlighting matched text patterns. Invoke when user needs to highlight search results or specific text patterns in Naive UI.

Countdown component for displaying time countdown. Invoke when user needs to implement countdown timers, deadlines, or time-based displays in Naive UI.

Color design specifications for Naive UI. Invoke when user needs to understand the color palette, main colors, semantic colors, or neutral colors used in Naive UI.

A dual-list transfer component for moving items between source and target lists with filtering, virtual scrolling, and custom rendering capabilities

A component for displaying a timeline of events with customizable items, icons, and layout options including horizontal and vertical orientations.

Skeleton component for displaying loading placeholders. Invoke when user needs to show content loading states with animated placeholders in Naive UI.

Progress component for displaying operation progress. Invoke when user needs to implement progress bars, loading indicators, or completion status in Naive UI.

Equation component for rendering mathematical equations using KaTeX. Invoke when user needs to display mathematical formulas or LaTeX expressions in Naive UI.

Text ellipsis component for truncating long text with tooltip support. Invoke when user needs to handle text overflow, multi-line truncation, or expandable text in Naive UI.

Dropdown component for displaying contextual menus and action lists. Invoke when user needs to implement dropdown menus, context menus, or cascading selections in Naive UI.