Skip to content

xonika9/agent-skills / skills/x9-wb-product-search

x9-wb-product-search

Verified

Подбирает и сравнивает товары на Wildberries/WB, проверяет карточки, отзывы, продавцов и варианты товара перед покупкой. Не применяется к другим магазинам и общим вопросам о товарах без намерения выбрать или проверить их на WB. В Claude Code требует текущую сессию Opus.

FileKindSize
SKILL.mdskill md23.3 KB
agents/openai.yamlconfig291 B
references/onboarding.jsonconfig1.5 KB
references/review-audit.mdmarkdown11.4 KB

references/onboarding.json

View on GitHub
{
  "version": 1,
  "requirements": [
    {
      "id": "current-opus-session",
      "runtimes": ["claude"],
      "kind": "user-action",
      "level": "required",
      "needed_for": "Running the main Wildberries workflow in the current Claude Code session on Opus.",
      "check": {"type": "manual"},
      "guidance_id": "complete-user-action"
    },
    {
      "id": "browser-session",
      "kind": "skill",
      "level": "required",
      "needed_for": "Searching Wildberries in a real browser.",
      "check": {"type": "skill-present", "target_skill": "x9-browser-session"},
      "guidance_id": "install-skill"
    },
    {
      "id": "authenticated-wildberries-session",
      "group": "wildberries-access-route",
      "kind": "user-action",
      "level": "required",
      "needed_for": "Checking Wildberries through the authenticated browser route.",
      "check": {"type": "manual"},
      "guidance_id": "complete-user-action"
    },
    {
      "id": "sessionless-fallback-permission",
      "group": "wildberries-access-route",
      "kind": "user-action",
      "level": "required",
      "needed_for": "Authorizing the sessionless browser fallback.",
      "check": {"type": "manual"},
      "guidance_id": "complete-user-action"
    },
    {
      "id": "native-subagents",
      "kind": "runtime-feature",
      "level": "optional",
      "needed_for": "Independently verifying high-risk product finalists.",
      "check": {"type": "runtime-feature", "feature_id": "native-subagents"},
      "guidance_id": "enable-runtime-feature"
    }
  ]
}
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall