AGENT SKILL

citilink-connector

Use this skill when the operator needs Citilink electronics data — search or a product card. Trigger on "ситилинк", "citilink", "ситилинк цена". Always needs the operator's Chrome over CDP (Qrator rate block + gRPC-web). Skip for non-Citilink tasks.

License 许可
Apache-2.0
最近更新
2026-11-13
Stars
★ 1.6k
Forks
483

01 前言 Front Matter

name
citilink-connector
description
Use this skill when the operator needs Citilink electronics data — search or a product card. Trigger on "ситилинк", "citilink", "ситилинк цена". Always needs the operator's Chrome over CDP (Qrator rate block + gRPC-web). Skip for non-Citilink tasks.

03 SKILL.md 正文

Citilink Connector

Reads Citilink inside the operator's Chrome over CDP. The whole domain answers HTTP 429 (stricter than DNS), and its data transport is gRPC-web — a binary protobuf protocol that is not worth reversing. A real Chrome passes Qrator and renders the pages, so the connector reads the DOM instead.

When to use

  • Search Citilink by text
  • One product's price, old price, availability

Tools available

  • citilink_search(query) — tiles from the rendered search page
  • citilink_card(product_url) — one card. The URL carries /product/<slug>/, where the slug ends in a numeric id: /product/noutbuk-lenovo-2169270/.

Not an MCP tool: citilink_selfcheck() is a tri-state canary. It is CLI-only — marketplace-mcp doctor runs every connector's canary at once.

Why the price used to come back null

Citilink renders the currency glyph in a separate element from the digits:

<span data-meta-price="59990"><span>59 990</span><span>₽</span></span>

The old extractor filtered text lines for руб|₽ and so never saw a line carrying both. Title parsed, price did not — on every product.

Read the data-meta attributes, not the class names

Citilink's class names are build-hashed (app-catalog-51bw0j-…) and change with every deploy, so they are useless as selectors. The site publishes a stable data-meta-* contract for its own analytics, and that is what the extractor keys on:

attribute holds
data-meta-name="Snippet__title" the product name anchor
data-meta-name="Snippet__price" the current price (glyph in a child span)
data-meta-name="Snippet__old-price" the strikethrough price, no glyph
data-meta-price="59990" the exact amount, machine-readable

data-meta-price needs no parsing and cannot be confused with an instalment or a badge, so it is preferred; the display strings are the fallback.

If prices start coming back null, check whether those attributes still exist before touching anything else — a class-name change is expected and harmless, a data-meta-* change is the real drift.

Numbers in a tile that are not the price

A tile also carries - 10% (discount badge), в 1356 пунктов (delivery points), (от 8 дней) (delivery estimate), a rating and an opinion count. Only a number attached to the currency glyph is treated as the price. Also note the first product anchor in a tile is an empty overlay link — it has no text, so the title comes from the Snippet__title anchor.

Gotchas

  • gRPC-web is deliberately not reversed: DOM extraction is the maintainable route.
  • A green citilink_selfcheck proves the page rendered and the extractor returned a shape. It does not prove the numbers are right — for that, open the product page in the same Chrome and compare.
  • From a datacenter address the domain answers 429, so nothing can be verified there. This connector only means anything from the operator's own machine.
  • A Qrator page that loads with HTTP 200 answers challenge_required: open citilink.ru in the scraping Chrome, pass the check, retry. It is never cached and never returned as a product.
  • A missing price is null, never 0: price_rub: null means Citilink had no usable price for the tile — treat it as no data, never as a free item.

DSH activation

In DeepSeek Harness, the default profile exposes only compare_prices and compare_sources through the cheap compare mount. Per-marketplace tools and marketplace_sources require RU_MARKETPLACE_MCP_FULL=1 and a profile restart; do not call them in the default mode.

04 同仓库更多 Skills

hashgraph-online
hashgraph-online/awesome-codex-plugins

migrate-to-e2e

Moves an existing Playwright, Cypress, Selenium, Appium, Detox, Maestro, or TesterArmy suite to e2e one slice at a time, with the old suite running beside the new one until each ported test is proven. Keeps a MIGRATION.md progress file so any later session resumes where the last stopped. Optionally plants a defect to show both suites catch it. Use for /migrate-to-e2e, "migrate our tests to e2e", "port these Maestro flows", "move our TesterArmy tests", or when a project has an e2e config and an older suite still running.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

e2e

Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change, take a screenshot or record a video, and try a locator; and runs bug bashes, parallel e2e explore runs with each bug proven by a repro test. Use when a project depends on e2e or has an e2e.config.ts, when asked for end-to-end, browser, mobile, or agentic UI tests, to check a change in the running app, to QA or bug bash an app or branch, or when an e2e run fails.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

create-verification-skill

Generate a project-local verify-<app> skill on top of e2e, so any coding agent can launch the app, check it is worth driving, exercise a feature the way a user does, keep evidence, and bug bash it. Writes the skill, a feature map with one explore charter per feature, and proves it once. Use for /create-verification-skill, "make a verification skill for this repo", or when a project has no scripted way to prove UI behavior.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

deja-search

deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

deja-reflect

End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

revid

Make, edit, export and post AI videos with Revid (revid.ai) through the Revid MCP server. Use whenever the user wants a short-form or long-form video made (from an idea, a script, a URL, an article, a PDF, a tweet, a product page, their own clips, or a song), wants to find what is going viral on TikTok, YouTube, Instagram or X before making something, wants to edit or re-export an existing Revid project, generate a standalone AI image or clip, make a series episode, or publish and schedule a finished video to connected social accounts. Covers setup (hosted MCP with OAuth, or an API key), the 36 tools, credits, polling and the rules for publishing. Routes to the more specific revid-* skills when one fits.

图像与多媒体Skill与智能体开发
★ 1.6k