Scrape Plan
Plan a web scrape and author a validated extraction spec — explore a detail page, discover fields, confirm the schema, then validate it with more pages, HTML-variant comparison, extracted values, and an optional browser review, and present the plan for approval.
Install
/plugin marketplace add zytedata/claude-skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add zytedata/claude-skills --skill scrape-plangit clone --depth 1 https://github.com/zytedata/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/skills/scrape-plan ~/.claude/skills/scrape-planPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
This file is 543 lines long; read all of them.
You are planning a web scrape. Download 1 detail page, discover fields, confirm
the schema in the terminal, then validate the spec by downloading more pages,
comparing HTML variants, and extracting values — and finally present the
finalized plan for approval.
This skill can be invoked directly by the user (to plan a scraper/spider for a
site) or by the `/scrape` orchestrator as its planning + validation stage.
Read `${CLAUDE_SKILL_DIR}/../scrape/references/python-environments.md` and
`${CLAUDE_SKILL_DIR}/../scrape/references/extraction-spec.md`.
Your output is twofold:
1. **Persisted spec files** under `.scrape/{site_name}/` — schema, pages,
values, and a navigation data type, ready for building the spider.
2. **A plain-text final message** carrying the resolved plan parameters
(the Finalization phase) — the `/scrape` orchestrator parses this to drive
the remaining stages.
Several steps below run a skill in a **subagent**, so that page HTML never enters this context. Delegate with the `Agent` tool: the quoted text as `prompt`, a short `description`, and `general-purpose` as `subagent_type`.
Several steps below **ask the user** to choose between options. When asking is unavailable, take the fallback stated with the question instead, and say so in your final answer. Ask with the `AskUserQuestion` tool, one question per call, each option a short label plus a one-line description.Details
- Skill name
scrape-plan- Repository
- zytedata/claude-skills
- Path
skills/scrape-plan/SKILL.md- Repo updated
- 26 October 2026
FAQ
What does the Scrape Plan skill do?
Plan a web scrape and author a validated extraction spec — explore a detail page, discover fields, confirm the schema, then validate it with more pages, HTML-variant comparison, extracted values, and an optional browser review, and present the plan for approval.
How do I install the Scrape Plan skill?
Claude Code plugin: /plugin marketplace add zytedata/claude-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Scrape Plan popular?
It lives in zytedata/claude-skills, which has 33 GitHub stars and 5 forks.
Related skills
Scrape
33zytedata/claude-skills
Build a full-site or multi-page Scrapy spider to get structured data from a website, in a new project or added to an existing one. Do not use for analyzing locally saved HTML, fixing or debugging an existing spider, schema-only or existing-spec work, Scrapy Cloud operations, or advisory questions.
Scrape Analyze Page
33zytedata/claude-skills
Extract structured data (all available fields with values) from a page saved locally as an HTML file, optionally following a schema. Do not invoke when the user provides a URL. When invoking, pass the user's full request verbatim as args — do not pre-parse file paths and don't rephrase it.
Scrapy Extra
33zytedata/claude-skills
Read this BEFORE writing, modifying, debugging, or explaining any Scrapy or web-poet code — spiders, page objects, pipelines, settings, selectors — down to a one-line fix, or scaffolding/configuring a Scrapy project, scrapy-poet, scrapy-zyte-api, or browser rendering. These libraries moved on since your training cutoff; invoke this FIRST. NOT for building a scraper for a given site (scrape), a saved HTML file (scrape-analyze-page), or Scrapy Cloud deploy/jobs (zyte).
Add Analytics Instrumentation
48amplitude/mcp-marketplace
End-to-end analytics instrumentation workflow for a PR, branch, file, directory, or feature. Reads the code, discovers what events should be tracked, and produces a concrete instrumentation plan — all in one shot. Use this skill whenever a user wants to add analytics to a PR, asks "instrument this PR", "add tracking to this branch", "what analytics does this file need", "instrument the checkout flow", "run the full instrumentation workflow", or any request that implies going from code changes to a tracking plan. Also trigger when the user gives you a PR link, branch name, file path, or feature
Analyze Chart
48amplitude/mcp-marketplace
Performs deep analysis of a specific Amplitude chart to explain trends, anomalies, and likely drivers. Use when a metric looks unusual, investigating a spike or drop, or understanding the "why" behind numbers.
Employment Law Dashboard
43bstevescherer/heycounsel-community
Build a single-file HTML dashboard for any area of US employment law, modeled after the AI Employment Laws Dashboard. Use this skill any time the user wants to create, build, generate, or update a dashboard, tracker, comparison page, or visual brief covering an employment-law topic across US jurisdictions. Triggers include phrases like "make a dashboard for [topic]", "build a tracker for [employment topic]", "state-by-state comparison page for [topic]", "visualize the legal landscape for [topic]", "create a dashboard like the AI one but for [topic]". The dashboard always includes a masthead, T
Browse the most popular Claude skills, all data & analytics skills, or write your own with the skills generator.