飞书审批：查询和处理审批待办/已办/实例，搜索可发起审批定义、查看定义详情并发起原生审批实例。当用户要处理审批任务、查看审批实例、搜索或发起审批时使用。审批待办不是飞书任务；非审批类待办走 lark-task。不负责创建审批定义；三方审批定义不走原生提单。

Design n8n AI agents the right way. Use when building or editing any @n8n/n8n-nodes-langchain.* AI node — an AI Agent, LLM chain, Text Classifier, or Information Extractor — and whenever the user mentions AI agents, LLM with tools, tool calling, $fromAI, system prompts, agent memory, sessionId, structured/JSON output, output parser, RAG, vector store, a chat assistant/bot, or human-in-the-loop review. Covers Agent-vs-chain-vs-classifier choice, the model/memory/tools/outputParser slots, tool names/descriptions as prompt, structured output with autoFix, memory, RAG, human review, and chat topologies.

Create a Solid Table v9 table with createTable, explicit tableFeatures, reactive data getters, stable static inputs, and Solid JSX/FlexRender. Load when starting a Solid table, replacing createSolidTable, or adapting React examples.

Query and download public cancer imaging data from NCI Imaging Data Commons. Invoke for any question about IDC collections, cancer imaging datasets, DICOM data access, radiology (CT, MR, PET) or pathology AI training sets, metadata queries, visualization, or license checks — even when the user doesn't explicitly mention "IDC". No authentication required.

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain formats are reference-only and unknown formats fail closed.

Debug, support, and build PostHog Surveys across the backend and all five SDKs (web/posthog-js, iOS, Android, Flutter, React Native). Use whenever a Surveys support ticket is pasted ("survey not showing", "fewer responses than expected", "responses disappeared", "responses are incomplete", "only the first question was answered", "the user says they didn't mean to submit", "survey shows on wrong platform"), when diagnosing why a survey does or doesn't display, or when doing survey feature work that must ship across SDKs. Covers the eligibility pipeline, how a response actually gets stored (partial responses, branching, optional questions, auto-submit), cross-SDK feature parity, the known-cause catalog, read-only diagnostic queries, staff access, and the customer-reply style guide.

Export PostHog events, persons, sessions, or the results of a HogQL query on demand and download the resulting files. Use when the user asks to download/export raw PostHog data, export HogQL query results, create a one-off file export, fetch a Parquet or JSONLines export, or use the file_download_batch_exports API. Covers starting the export with MCP, polling completion, and downloading via the existing REST redirect endpoint.

Guides an agent through reproducing, root-causing, fixing, and validating flaky tests in the PostHog monorepo. Use when a test fails intermittently in CI but passes on rerun or locally, when `hogli ci:insights` or the debugging-ci-failures skill classifies a failure as a flaky test, when given a GitHub Actions URL for a flaky job, when asked to check Trunk Flaky Tests for a test, PR, or master, or when asked to deflake, stabilize, or fix a flaky Jest, pytest, or Playwright test. Core discipline: reproduce locally before changing anything, fix the root cause (never mask it with sleeps, retries, or bigger timeouts), and prove the fix with an N-run validation loop sized to the observed failure rate. Stabilizing is not the only valid outcome — the skill also gates whether the test should exist, so deleting a test that catches nothing real, or re-leveling one that flakes because of the level it runs at, are first-class endings.

Prepare a new release by collecting commits, generating bilingual release notes, updating version files, and creating a release branch. Use when asked to prepare/create a release, bump version, or run `/prepare-release`.

Use when preparing, tagging, and publishing a Cline desktop app (apps/examples/desktop-app) release — stable (desktop-vX.Y.Z from main) or beta (desktop-vX.Y.Z-beta.N from desktop-experimental, shipped as the side-by-side "Cline Beta" app). Guides changelog drafting, version bumps in package.json + tauri.conf.json, tagging, and the desktop-publish GitHub workflow that builds, signs, notarizes, and updates the per-channel auto-update feed.

Reduce a webpage to a structural skeleton with semantic tokens. Two-phase pipeline: Phase 1 injects a browser script that tokenizes content ({TEXT}, {HEADING:n}, {IMAGE:WxH}, {CTA:label}, {LINK:label}, {INPUT:type}, {VIDEO}, {ICON}). Phase 2 applies LLM structural reasoning to collapse repeated patterns ({REPEAT:N}), remove decorative wrappers, strip utility classes, and produce skeleton.html + manifest.json. Use when migrating pages to EDS, analyzing page structure, extracting page blueprints, or preparing input for GenAI block generation. Triggers on: reduce page, page skeleton, page blueprint, extract structure, tokenize page, page reduction, structural skeleton, reduce URL.

Prepare any webpage for clean interaction by detecting and removing disruptive overlays (cookie banners, GDPR consent, modals, popups, newsletter signups, paywalls, login walls). Uses a cached database of 300+ known CMPs (Consent-O-Matic + EasyList) combined with heuristic DOM scanning. Injects a self-contained script via playwright-cli. ALWAYS use this skill before taking screenshots, scraping content, or automating interaction on any webpage that might have overlays blocking the view or preventing interaction. Triggers on: page prep, clean page, remove overlays, dismiss cookie banner, page blocked, overlay cleanup, consent banner, prepare page, unblock page, clear popups, cookie popup.

Detect all languages used on a webpage — both declared (html@lang, hreflang alternate links, nested lang= attributes, meta content-language) and actually present in the body text (Google CLD3 via cld3-asm WASM). Reconciles the two signal sets and flags mismatches such as undeclared languages in the body or declared languages absent from the content. Outputs langs.json with detected languages (probability + proportion), all declared language signals, and a reconciliation report. Use for i18n audits, EDS page migrations, hreflang validation, and multilingual content verification. Triggers on: detect languages, page languages, what language, language detection, i18n audit, hreflang, hreflang validation, lang attribute, multilingual page, page-langs, language audit, which language, content language, undeclared language.

Launch Chrome with an unpacked extension and test its UI via CDP. Auto-installs Chrome for Testing if needed. Loads the extension, opens sidepanel/popup/options page, and hands off to cdp-connect for interaction (click, type, screenshot, ax-tree). Handles Chrome 137+ branded build restrictions (Extensions.loadUnpacked via pipe), sidepanel user gesture requirements, and React input quirks. Use when you need to test a Chrome extension's UI, automate extension interactions, or validate extension behavior on a target page. Triggers on: chrome extension test, test extension, load unpacked extension, extension sidepanel, extension popup, test chrome extension, extension testing, chrome extension automation, ext pilot, cdp extension.

Connect Claude Code to an existing Chrome browser via CDP (Chrome DevTools Protocol). Zero dependencies — uses Node 22 built-in WebSocket. Attach to any Chrome running with --remote-debugging-port, then navigate, click, type, screenshot, evaluate JS, read accessibility tree, and monitor console/network. Use when you need to interact with a browser the agent already started, control an existing Chrome instance, or drive browser automation without Playwright MCP. Triggers on: cdp connect, connect to browser, connect to chrome, attach to browser, interact with browser, drive browser, browser automation, control chrome, connect 9222.

TRIGGER for authoring UiPath Maestro Case plans as `<Name>.case.ts` with the reference-mode TypeScript builder SDK (`@uipath/flow-sdk/case`), compiling to `caseplan.json`, and running the `uip maestro case` check/compile/validate loop. Covers stages, tasks, rules, bindings, published-resource references, and brownfield decompile/edit/recompile. Flow builder authoring → uipath-maestro-flow; structural-core BPMN → uipath-maestro-bpmn. DO NOT TRIGGER for C#/XAML automation → uipath-rpa.

Creates release-ready skill packages from proven workflows by drafting SKILL.md frontmatter, trigger-rich instructions, references/contract.yaml, eval scenarios, task profile, and validation commands. Use when the user asks to create a skill, skillify a workflow, package a process, write SKILL.md, make a reusable skill template, or prepare a skill for release checks.

Aha! integration. Manage data, records, and automate workflows. Use when the user wants to interact with Aha! data.

Guided multi-page redesign of an existing website through a four-phase pipeline — extract (crawl and capture the current site), direct (set a visual direction), prototype (generate redesigned HTML), and migrate (emit a deployable static site). Tracks progress incrementally per page in stardust/state.json so redesigns are resumable. Delegates the per-page design craft (typography, spacing, color, layout, motion) to the impeccable skill. Use when the user wants to redesign, revamp, modernize, or restyle an existing site they can point to by URL, run the extract/direct/prototype/migrate flow, or resume a multi-page redesign. Not for designing a brand-new site from scratch or one-off single-component edits.

Comprehensive DAG failure diagnosis and root-cause analysis with structured investigation and prevention recommendations. Use when deep failure investigation is needed, a DAG fails to import/parse or 'airflow dags list' errors on a file; a task or run is failing and must be diagnosed and fixed; requests like 'why did X fail', 'my dag keeps failing — find and fix it', or fixing a broken DAG so it loads cleanly. For simple 'why did it fail / show logs', the airflow skill handles it directly.