site-extraction-authoring

Authors and validates site-specific product page extraction rules with terms-of-use compliance checks.

Updated Jul 17, 2026
One-click install
npx skills add https://github.com/Huruikagi/pc-build-planner --skill site-extraction-authoring-huruikagi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: site-extraction-authoring
Source: https://github.com/Huruikagi/pc-build-planner/tree/main/.agents/skills/site-extraction-authoring
Command: npx skills add https://github.com/Huruikagi/pc-build-planner --skill site-extraction-authoring-huruikagi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Adding site-specific product extraction to a Chrome extension requires checking each site's terms of use, recording compliance decisions, building extraction candidates, and verifying them against saved pages and real-extension E2E tests. This Skill orchestrates that entire workflow safely, ensuring no page content, product values, or credentials leak into the repository or decision records. ## Core Features & Use Cases - Terms-of-use gating: Explores the target site's official terms before any work, records findings in a decision log, and stops only on explicit prohibitions rather than ambiguity. - Isolated work units: Creates timestamped, Git-ignored work units under /.site-extraction-work/ with separate decision, candidate, and verification records, never overwriting prior runs. - Staged candidate validation: Builds extraction candidates restricted to existing categories and attribute keys, verifies them against saved page material, then hands off to real-extension E2E and pnpm validate before proposing registration. - Use Case: A developer wants to add extraction support for a new PC parts retailer. Provide the representative product page URL, and the Skill records the terms review, drafts selectors for allowed fields, verifies them, and proposes a registration diff only after all checks pass. ## Quick Start Start site-specific extraction authoring for the product page at this representative URL and record the terms-of-use review before creating any candidates.

Frequently Asked Questions about site-extraction-authoring

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I add site-specific extraction for a new product page?▼

Provide a valid representative URL for the target product page. The Skill first explores the site's official terms of use, records the decision, then builds extraction candidates limited to existing categories and attribute keys before any registration is proposed.

What happens if a site's terms of use cannot be found?▼

Missing, unreadable, or ambiguous terms do not stop the workflow. The Skill records the unexplored facts and open questions in decision.md and continues, stopping only when an explicit prohibition applies to the specific work being done.

Which product attributes can site-specific extraction rules capture?▼

Only common fields (name, manufacturer, model, category, price, URL) plus existing CATEGORY_ATTRIBUTES keys such as socket, memoryStandard, and formFactor for defined category pairs. Unsupported attributes or unlisted values cause the whole candidate to be rejected.

Does this Skill save the actual product page HTML?▼

Saving page material is optional and separate from browsing. If storage conditions cannot be confirmed, the Skill records that fact, skips page.html, and continues with self-authored rules and fictional fixtures instead.

When is a candidate allowed to be registered?▼

Only after saved-material comparison, the page-capture-owned real-extension E2E, existing generic scenarios, and pnpm validate all pass. Any failure keeps existing registrations intact and blocks registration or update proposals.