bigdata-moat-governance-review

Build bull, base, and bear cases for a public company using Bigdata.com data — with explicit line-item assumptions, justified probability weights summing to 100%, a value or price per scenario with the bridge shown, a probability-weighted expected value and expected return versus spot, the upside/downside skew and risk-reward ratio, and what would move probability between the cases. Triggers: "scenario analysis for X", "bull base bear for X", "what's the upside and downside on X", "expected value for X", "probability-weighted view on X", "risk reward on X", "model out the cases for X".

Write a day-179 post-IPO note on the 180-day lock-up expiry using Bigdata.com data plus filings and market data. Covers lock-up terms from the prospectus (expiry date, covered holders, share count, early-release provisions), float and overhang math (post-expiry float, days-to-trade versus ADV), insider and VC selling-intention signals, positioning into the event (short interest, borrow, options skew), the historical lock-up-expiry effect with analogs, and a two-sided read. Balanced, no buy/avoid call. Triggers: "180-day lock-up expiry for X", "lockup expiration impact", "post-IPO day 179", "shares unlocking for X", "insider selling after lockup", "float expansion at lockup".

Write a day-365 post-IPO note on the 366-day founder and significant-investor lock-up expiry and float expansion toward 15-20%, using Bigdata.com data plus filings and market data. Covers the staggered lock-up structure from the prospectus, float expansion math and days-to-trade, the offsetting float-adjusted index reweight demand netted against new supply, a realistic read on whether founders actually sell, the dual-class governance angle, and a two-sided setup. Balanced, no buy/avoid call. Triggers: "366-day lock-up for X", "founder lock-up expiry", "float expansion for X", "post-IPO one year lockup", "index reweight after float increase", "founder selling after IPO".

Produce a balanced pre-IPO research note on an upcoming, not-yet-listed company using its S-1/F-1 plus Bigdata.com data. Covers deal structure (price range, shares, greenshoe, implied valuation, underwriters, lock-ups, share classes), two years plus interim financials, business model and funding history, TAM and listed comparables, IPO-window conditions, and 90-day sentiment — closing with bull and bear debates and watch points, never a participate/avoid call. Triggers: "analyze the IPO of X", "S-1 analysis", "upcoming listing for X", "IPO report on X", "should I look at X's IPO", "pre-IPO research on X", "X IPO valuation".

Give a fast, PM-style quick take on a stock using Bigdata.com data — a one-line current view, the 2-3 drivers that actually matter right now, the key risks and what would change the view, and the near-term setup with the next catalyst. Deliberately short: one page, no full thesis, no model. Triggers: "quick take on X", "what do you think of X", "give me a fast view on X", "thoughts on X", "X in a nutshell", "one-liner on X", "is X interesting right now".

Compare regions or blocs using Bigdata.com data — economic indicators, market performance, and cross-asset views — and turn that into an allocation recommendation. Covers growth, inflation, policy and labor per region, comparative developed-versus-emerging analysis, regional equity valuations, and fixed income and currency views for each. Triggers: "compare US vs Europe vs Asia", "which regions look attractive", "regional allocation", "developed vs emerging markets", "Europe vs US equities", "global allocation view".

Produce a comprehensive risk assessment for a public company using Bigdata.com data (10-K risk factors, 8-K material events, news, tearsheet financials). Covers six categories — regulatory and legal, competitive and moat erosion, operational, financial and balance sheet, macro, and management and governance — each rated by likelihood and impact, with a distress screen when leverage is stretched, mitigation status, a priority matrix, and a scenario bridge to value drivers. Triggers: "risk assessment for X", "assess risks for X", "what are the risks with X", "what could go wrong at X", "risk factors for X", "how risky is X", "downside risks for X".

State explicitly where your view on a public company differs from consensus, using Bigdata.com data. Establishes the consensus baseline from estimates and sell-side posture, applies the EPIC filter to candidate differentiators, frames the view on FaVeS (fundamentals, valuation, sentiment), and states the variant view as a specific, falsifiable claim with a time horizon — plus what the market is missing, why the mispricing persists, the evidence for the view, and what would disprove it. Triggers: "variant perception on X", "where do I differ from consensus on X", "what is the market missing on X", "non-consensus view on X", "what's priced in versus reality for X", "contrarian case for X".

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management" — in a project that needs ADK (Agent Development Kit) API patterns and code examples. It provides a quick reference for agent types, tool definitions, orchestration patterns, callbacks, state management, the graph Workflow API, and reference recipes to study. Do NOT use for scaffolding (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy).

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

Generate AI music on RunComfy via the `runcomfy` CLI — a smart router across the music-model catalog. Routes to ElevenLabs AI Music Generation (premium 44.1 kHz stereo vocal tracks, 5 s–5 min, $0.0083/s) and ACE Step / ACE Step 1.5 (StepFun-AI open-weights, tag-driven composition, multilingual lyrics, $0.0002–0.0003/s, ~27× cheaper), plus ACE Step audio-inpaint (regenerate a time range inside an existing track) and ACE Step audio-outpaint (extend a track before or after). Picks the right model for the user's actual intent — premium vocal hook, cheap background music library, multilingual pop song, repair a bad chorus, lengthen a 30 s draft into a 2 min cut — and ships each model's documented prompting patterns plus the minimal `runcomfy run` invoke. Triggers on "generate music", "make a song", "AI music", "background music", "instrumental track", "soundtrack", "jingle", "theme music", "royalty-free music", "compose", "music with lyrics", "extend music", "fix this song", "inpaint music", or any explicit ask to generate or edit music.

创建 lark-cli 的自定义 Skill。当用户需要把飞书 API 操作封装成可复用的 Skill（包装原子 API 或编排多步流程）时使用。