Data & AI skills

Financial statements, business segments, dividends, valuation multiples (PE/PB/PS), industry comparison, operating data, corporate actions, company and executive profiles, cross-stock comparison, and valuation ranking via Longbridge. Also: DCF models, value investing screens (low PE/PB, margin of safety), and behavioral finance analysis frameworks. Triggers: "财报", "三表", "利润表", "资产负债", "现金流", "估值", "PE", "PB", "分红", "公司信息", "高管", "行业估值", "并购", "DCF", "内在价值", "低估值", "安全边际", "行为金融", "小盘成长", "专精特新", "主营业务", "业务构成", "收入结构", "业务分析", "是做什么的", "是干嘛的", "公司画像", "行业排名", "行业龙头", "市场份额", "收入占比", "业务结构", "財報", "估值", "分紅", "內在價值", "安全邊際", "主營業務", "業務構成", "收入結構", "行業排名", "行業龍頭", "financial report", "income statement", "balance sheet", "valuation", "dividend", "company info", "industry valuation", "DCF", "value screen", "behavioral finance", "main business", "business composition", "revenue structure", "what does XX do", "industry ranking", "market share", "利潤表", "資產負債", "現金流", "行業估值", "併購", "行為金融", "小盤成長"

The English summary is being prepared. Showing the original description.

Turns a target someone has already committed to (a board plan, an annual plan, a contract) into a plan the team can measure: KPIs in three tiers with a guardrail for each, a baseline from real data, monthly pacing with lag and seasonality, and two or three channels chosen from how your ICP actually searches and buys. Writes context/goals/MMYY-scope.md and context/goals/measurement.md. It never invents the target. Triggers: "set our goals", "what are our KPIs", "revenue target and pacing", "which channels and what targets", "write the scope file", "are we on track". Run after /funnel-strategy. Not for designing funnel stages (use /funnel-strategy).

The English summary is being prepared. Showing the original description.

Restore IWE memory from an exocortex backup on a new device or after data loss — NL wrapper around restore-from-exocortex.sh.

The English summary is being prepared. Showing the original description.

Локальный LLM-стек на Mac (Apple Silicon, MLX) под приватность и запасной режим. NL-вход к установке/запуску/переключению моделей + слой суждения для мониторинга новых моделей. Тонкая обёртка над скриптами РП404, не замена.

The English summary is being prepared. Showing the original description.

Регистрация косяка агента в системе учёта WP-316 L1. Без LLM — детерминированный скрипт без WP Gate.

The English summary is being prepared. Showing the original description.

Write the postmortem for an incident, in its incident channel, once it is mitigated or resolved. Use on "write up this incident", "postmortem", "incident summary", "what happened here for people who weren't around", "draft the retro", or when the oncall memory says incidents of this severity get one. Reads the incident channel (and the alert thread it came from), the investigation findings and the data behind them, and writes a one-screen, zero-context write-up: what happened, impact with numbers, detection, timeline with durations, why it happened, what fixed it, follow-ups with proposed owners, and one before/during/after chart. Posted and pinned in the incident channel as its final pinned post, with edit requests updating that one pinned post in place — unless the person or the team's conventions say write-ups live elsewhere, in which case it is written there and only a link is posted, nothing pinned. A person edits and publishes it; never assigns blame.

The English summary is being prepared. Showing the original description.

Compose polished charts (timeseries, bar, line, area, pie, scatter, or anything else the data calls for) from tabular data using the chartkit primitives, producing PNG, SVG, or self-contained interactive HTML. Use when the user asks to chart, graph, plot, or visualize data and wants something better than raw matplotlib defaults.

The English summary is being prepared. Showing the original description.

Use when verifying information (fact, number, quote, event, statement) against authoritative primary sources, or cross-checking a number via one-level metric decomposition (Z = P × Q). Triggers: "verify X", "is this true", "find the original source", "where is this number from", "two sources disagree", "is it true X never did Y". Covers five scenarios: (1) basic truthfulness check, (2) completeness / out-of-context quoting, (3) one-level reasoning verification, (4) negative-statement handling, (5) multi-source conflict side-by-side output. Dig into whitelisted primary sources only (user-supplied files, official websites & databases, authoritative industry sources); cited reports / charts / datasets must be downloaded and read locally to count as verified — if download is blocked, hand the link to the user. If nothing can be found, plainly state "cannot verify" rather than guessing, patching, or citing secondary paraphrases. Always reply in the user's question language.

The English summary is being prepared. Showing the original description.

VNX-specific domain expertise for the intelligence system, central state databases, and dispatch lifecycle. Use when working on quality_intelligence.db / runtime_coordination.db / dispatch_tracker.db, code_snippets FTS5, snippet_metadata linkage, success_patterns / antipatterns, T0 state projection (t0_state.json), intelligence_injections lifecycle, dispatch → receipt → events → archive flow, central state architecture, project_id propagation across VNX, or any code that reads/writes VNX governance state. Triggers include: editing intelligence injection code, querying central DB for cross-project insights, debugging "intelligence not appearing in T0 state", modifying schema in `schemas/quality_intelligence.sql` or `schemas/runtime_coordination_v*.sql`, working with `scripts/quality_db_init.py` or `scripts/lib/coordination_db.py`.

The English summary is being prepared. Showing the original description.

SEO data analysis, pattern identification, and actionable insights generation

The English summary is being prepared. Showing the original description.

VNX-specific domain expertise for the intelligence system, central state databases, and dispatch lifecycle. Use when working on quality_intelligence.db / runtime_coordination.db, code_snippets FTS5, snippet_metadata linkage, success_patterns / antipatterns, T0 state projection (t0_state.json), intelligence_injections lifecycle, dispatch → receipt → events → archive flow, central state architecture, project_id propagation across VNX, or any code that reads/writes VNX governance state. Triggers include: editing intelligence injection code, querying central DB for cross-project insights, debugging "intelligence not appearing in T0 state", modifying schema in `schemas/quality_intelligence.sql` or `schemas/runtime_coordination_v*.sql`, working with `scripts/quality_db_init.py` or `scripts/lib/coordination_db.py`.

The English summary is being prepared. Showing the original description.

Read a Facebook Page and its audience from real data. Pull any Page's public stats (yours or a competitor's): followers, likes, categories, intro, websites. And pull the commenters on a public Page post, since Facebook hides the reactor and liker roster and shows counts only, so commenters are the signal. Powered by Apify, no login. Triggers on "analyze my Page", "competitor Page stats", "who is commenting", "read the comments", "audience insights". Not for writing Page posts (use fb-post-writer).

The English summary is being prepared. Showing the original description.

Scout a topic on YouTube. Searches YouTube Data API v3 for the most relevant videos, ranks them by views (or engagement, likes, recency, momentum, breakout), and writes a research workbook in the OWT-Social-Ads layout with Videos, Channels, and Summary sheets, plus optional Comments and Transcripts (hooks, replay hotspots) sheets. Can also append into an existing sheet. Use when the user says "scout <topic>", wants a spreadsheet of top YouTube videos on a topic, wants creator or hook research, or wants YouTube rows added to their social ads sheet.

The English summary is being prepared. Showing the original description.

Core agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple browser sessions in parallel, and troubleshooting common failures. Use when the user asks to interact with a website, fill a form, click something, extract data, take a screenshot, log into a site, test a web app, or automate any browser task.

The English summary is being prepared. Showing the original description.

Roll out governed MotherDuck analytics to internal teams, choosing trusted datasets, access boundaries, and owners.

The English summary is being prepared. Showing the original description.

Plan or implement migrations to MotherDuck with SQL translation, source-to-target validation, cutover, and rollback.

The English summary is being prepared. Showing the original description.

Design or implement MotherDuck analytical schemas and transformation models, including grain, types, and materialization.

The English summary is being prepared. Showing the original description.

Discover MotherDuck databases, tables, columns, shares, and sample data to understand an available dataset.

The English summary is being prepared. Showing the original description.

Build ingestion-to-serving pipelines on MotherDuck, including stage boundaries, transformations, and publication.

The English summary is being prepared. Showing the original description.

Write, execute, or optimize analytical DuckDB SQL against MotherDuck data.

The English summary is being prepared. Showing the original description.

Create, edit, publish, share, or embed MotherDuck Dives using their React and SQL runtime.

The English summary is being prepared. Showing the original description.

Build MotherDuck analytics into customer-facing applications with tenant isolation, backend routing, and serving APIs.

The English summary is being prepared. Showing the original description.

Create, consume, or manage MotherDuck data shares, including audience grants, table filters, and refresh policy.

The English summary is being prepared. Showing the original description.

Look up or repair DuckDB SQL syntax and verify MotherDuck-specific command and feature support.

The English summary is being prepared. Showing the original description.