sp-api-knowledge

Guides a seller end-to-end through sending inventory to Amazon's fulfillment network: creating an inbound plan, packing, placement, transportation, delivery windows, and shipment confirmation — plus status checks, modifications, and cancellation. Drives the sequential CREATE→PACK→PLACE→TRANSPORT→DELIVER→SHIP pipeline, polls async operations to completion, and pauses at every decision gate for the seller's choice. Triggers on: send inventory to Amazon, create inbound plan, ship to FBA, inbound shipment status, cancel inbound plan, add tracking, FNSKU labels, prep requirements, schedule FC drop-off. Do NOT use for: stockout / replenishment forecasting (use stockout-prevention), listing issues, advertising, or orders.

Closes and reconciles a seller's completed Amazon month: it retrieves the monthly activity, the settlements overlapping the month, the balances carried across month boundaries, and the payout statuses, then walks the seller through an Amazon-activity reconciliation, a payout receipt check (seller supplies bank deposits — there is no bank integration), and an accountant-ready summary. Read-and-explain only: it posts no entries, changes no accounting records, and never files, submits, pays, or moves money. Triggers on: close the books for last month, help me close January/last month, month-end close, reconcile last month, do my Amazon numbers reconcile, have I received all my payouts, give me my month-end summary for my accountant. Do NOT use for: filing/submitting taxes/VAT/GST or any regulated report, paying or moving money, changing prices/listings/inventory, accessing the seller's bank account, or the current in-progress month.

Helps the account owner, an administrator, or a permissions manager of a Seller Central account invite their secondary users to use the Selling Partner plugin. Runs right after the Amazon Selling Partner Connector connector is connected: it confirms the person can grant agent access, asks whether they want to invite secondary users, then walks them through Manage Your Permissions -> Manage Agents, where they enable the agent for the account and choose which secondary users may authorize it. When the skill runs in Amazon Quick, it adds one extra step — inviting that user as a collaborator in the Quick account. Triggers on: invite users, add a secondary user, manage agents, grant agent access, "let my team use the plugin", onboard my team, give access to another user. Do NOT use for: setting up your own account/marketplace (established by the connect flow), taking selling actions, or User Permissions unrelated to AI agents.

Diagnoses why a seller's listing isn't buyable and relays the specific reason plus the next step. Checks the three things that make a listing buyable — a complete product, a valid purchasable offer, and available inventory — then fixes the offer (preview → approve) or routes inventory elsewhere. Triggers on: not buyable, can't be purchased, "why can't customers buy this", no buy box, listing inactive, missing price / offer. Do NOT use for: search/discoverability (use listing-searchability), fixing reported listing issues (use listing-issues), or inventory replenishment (use stockout-prevention).

Pre-flight compliance gate before any listing write. Identifies which Amazon listing and regulatory requirements (FDA, EPA, CPSC, FCC, FTC, disclosures, GTIN, category gating) apply, asks the seller once for the facts only they know, checks account-side gating, and holds the write until the seller gives an explicit go. Triggers on: "can I list this", "what do I need to sell X", "is this compliant", listing requirements, help me list, or when a sibling listing skill is about to change product claims, ingredients, category, condition, images, or identifiers. Do NOT use for: reported issues (listing-issues), buyability (listing-buyability), search optimization (listing-searchability), or general program-policy Q&A unrelated to listings.

Fixes listing problems that surface as reported issues on a listing — missing or invalid attributes, and suppressions tied to an issue. Reads the listing's issues (severity + enforcement), prioritizes by impact, and previews every fix before it goes live. Triggers on: listing issues, listing errors, fix my listing, attribute errors, suppressed because of an issue, "what's wrong with this listing". Do NOT use for: why a listing isn't buyable when there's no issue (use listing-buyability), search visibility / optimization (use listing-searchability), creating new listings, inventory / stockout, advertising, or orders.

Diagnoses why a seller's listing isn't found in search and helps make it more discoverable. Checks whether the listing is discoverable at all, then optimizes the content shoppers search on — title, description, bullet points, and generic keywords — with the seller's approval. Triggers on: not showing up in search, can't be found, not discoverable, improve ranking, search visibility, optimize my listing, SEO. Do NOT use for: not-buyable (use listing-buyability) or fixing reported issues (use listing-issues).

Top-level entry point for any "something's wrong with my listing" question. Does a quick scan to read the listing's status and issues, identifies the symptom, and routes the seller to the right specialist skill — issue-fixing, buyability, searchability, or compliance. Triggers on: something's wrong with my listing, troubleshoot my listing, my product has a problem, listing not working, where do I start, "can I list this", "what do I need to sell X". Routes to: listing-issues, listing-buyability, listing-searchability, listing-compliance.

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.

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。

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.