Amazon Alexa for Shopping Q&A automation: submits questions to Amazon's Alexa/Rufus AI shopping assistant and collects response text; supports optional keyword search context (navigate to search results page before asking for category-specific answers). Use when user mentions Amazon Alexa, Rufus, Amazon shopping assistant, Amazon AI chat, ask Amazon, Amazon Q&A, automate Alexa questions, Rufus chatbot, Amazon assistant automation, collect Alexa responses, bulk question submission to Amazon, keyword search context, category research. Also applies to extracting Amazon product recommendations from conversational AI, automating repeated queries to Amazon's AI shopping feature, collecting Alexa shopping responses at scale, or market research within a specific product category.

Perform cross-artifact consistency analysis across spec.md, plan.md, and tasks.md. Use after task generation to identify gaps, duplications, and inconsistencies before implementation.

Generate comprehensive market research reports and industry/competitive analysis in the style of top consulting firms. Use for market sizing, competitive landscape, market entry, investment thesis, strategic recommendations, and consulting-style business reports. Do not use for scientific reports, paper writing, LaTeX submission/PDF builds, EDGAR/FRED/Treasury/Data Commons data retrieval, or biomedical literature evidence work.

Query FRED (Federal Reserve Economic Data) API for 800,000+ economic time series from 100+ sources. Access GDP, unemployment, inflation, interest rates, exchange rates, housing, and regional data. Use for macroeconomic analysis, financial research, policy studies, economic forecasting, and academic research requiring U.S. and international economic indicators.

Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.

绝境反转方法论：当任务似乎没有希望、反复摆动、准备放弃愿景时的五步突破框架。 Use when: 任务看起来无解、多次尝试失败后想放弃、输出投降修辞（"现状最优"/"没救了"/"接受现实"）、连续 3+ 轮在希望与绝望间摆动。 Not for: 未出现绝境信号的常规 debugging（用 debugging）、常规探索/调研（用 deep-research）、operator 已签字降级的目标、trivial 任务。 Output: Desperation Packet（六问证据评估）+ 新方向行动计划 / operator 升级请求。

Author-triggered fresh-context scan of PR diff before formal review. Finding generator, NOT approval authority. Use when: quality-gate 通过、PR 非 trivial、想降低正式 reviewer 认知负荷。 Not for: 正式 review verdict、approval、merge decision。 Output: Finding list（附在 review request 中）。

跨 thread 协同：通知、归属核验、争用与责任处置。Use when: 平行 session 通知或共享文件争用。Not for: 跨猫交接或新建 thread。Output: routed cross-post + disposition。GOTCHA: ACTION/BLOCKING 不转移球权。

约定图发现方法论：进一个 repo 先识别 repo-specific conventions，再定义 domain/extractor 接 Convention Graph 引擎。Use when: 进入陌生 repo、要画约定图、要找“改 X 影响谁”的约定层关联、 F242/Convention Graph Layer 工作。Not for: 普通符号跳转/LSP、文档索引检索、记忆图谱、直接使用 codegraph/GitNexus。Output: domain 定义 + extractor 计划 + gap/freshness/provenance 报告。 GOTCHA: 沉淀的是“怎么画图”的方法，不是把 cat-cafe 的 extractor 硬搬到所有 repo。

Evaluates market bubble risk through quantitative data-driven analysis using the revised Minsky/Kindleberger framework v2.1. Prioritizes objective metrics (Put/Call, VIX, margin debt, breadth, IPO data) over subjective impressions. Features strict qualitative adjustment criteria with confirmation bias prevention. Supports practical investment decisions with mandatory data collection and mechanical scoring. Use when user asks about bubble risk, valuation concerns, or profit-taking timing.

This skill should be used when analyzing recent market-moving news events and their impact on equity markets and commodities. Use this skill when the user requests analysis of major financial news from the past 10 days, wants to understand market reactions to monetary policy decisions (FOMC, ECB, BOJ), needs assessment of geopolitical events' impact on commodities, or requires comprehensive review of earnings announcements from mega-cap stocks. The skill automatically collects news using WebSearch/WebFetch tools and produces impact-ranked analysis reports. All analysis thinking and output are conducted in English.

理解或修改 BK-CI 流水线 Model、Stage、Container、Element 结构时使用。当用户提到流水线模型、Stage/Job/Task 数据结构、模型扩展、模型校验、版本兼容、YAML 与 Model 转换时优先使用。

Ancient text restoration, attribution, dating, contextualization, and embedding via Aeneas (Latin) / Ithaca (Ancient Greek). Use when asked to "restore", "attribute", "date", "contextualize", "find parallels", "where was it written", "when was it written", "embed", or "analyze" an ancient text, inscription, or epigraphic document, or when the user mentions "Aeneas", or "Ithaca".

Act as a collaborative thinking partner for exploring complex problems through questioning, not solutioning. Use when the user wants to think out loud, explore an idea, work through a problem, or asks for a thinking partner.

Claude Science's own session database schema and SDK surface for introspection via host.query(). Load this when you need to query your own conversation history, token usage, cost accounting, execution log, or artifact metadata beyond what host.frames()/host.artifacts() provide — e.g. "how many tokens has this session used", "what was my last tool call", "list every file I've written", "where are messages stored", "what tables can I query", "inspect frames.context_data", or any time you're about to PRAGMA-probe the Claude Science metadata DB to discover its schema.

Inverse-fold a protein backbone (PDB structure) into amino-acid sequence with ProteinMPNN (Dauparas et al. 2022, github.com/dauparas/ProteinMPNN). Reach for this skill to run sequence design on RFdiffusion backbones, to redesign one chain of a PDB while holding interface residues fixed, or to generate a temperature-swept set of sequences for downstream folding.

Embed proteins with Meta AI's ESM-2 (`fair-esm` package). Use this skill when: (1) Extracting per-residue or per-sequence embeddings for downstream ML, (2) Masked-LM likelihood / mutation effect scoring, (3) Contact prediction from a sequence.

Predict small-molecule binding poses with DiffDock-L (Corso et al. 2023/2024, github.com/gcorso/DiffDock) — blind diffusion docking that places a ligand into a protein pocket without a predefined search box and ranks the samples with a learned confidence model. Reach for this skill to dock a SMILES or SDF against a PDB, to generate ranked 3D poses for a small fragment library, or to get a starting pose for downstream rescoring. DiffDock predicts geometry, not affinity.

Structure prediction for protein, nucleic-acid, and small-molecule complexes with the Chai-1 foundation model (Chai Discovery 2024, github.com/chaidiscovery/chai-lab). Reach for this skill to predict an antibody-antigen or protein-ligand complex from a single FASTA, to re-fold designed binders as an AlphaFold-multimer alternative, or to drive co-folding from Python for batched campaigns on a GPU.

Working pattern for Grida Gateway (GG) — Grida's first-party, metered, no-BYOK AI surface: the scoped-token mint, the OpenAI-compatible + native gateway endpoints, the `gg` client provider, and the desktop wiring that spends org credit without a user key. Anchor for the `GRIDA-GG: <surface>` grep marker; its security half is `GRIDA-SEC-006`. Use when adding or touching any GG file, the `gg` provider kind, the `gg:ai` token audience, or deciding whether code belongs to the gateway surface. Companions: `security` (the GRIDA-SEC-006 half), `ee-billing` (the ledger it spends), `agent-system` and `desktop` (the two hosts).