blocked-page-fallback
Recover when a web page is thin, blocked, JS-heavy, region-limited, or fetch-incompatible by switching to lawful fallback paths instead of stopping early.
Best use case
blocked-page-fallback is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Recover when a web page is thin, blocked, JS-heavy, region-limited, or fetch-incompatible by switching to lawful fallback paths instead of stopping early.
Teams using blocked-page-fallback should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/blocked-page-fallback/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How blocked-page-fallback Compares
| Feature / Agent | blocked-page-fallback | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Recover when a web page is thin, blocked, JS-heavy, region-limited, or fetch-incompatible by switching to lawful fallback paths instead of stopping early.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
SKILL.md Source
# Blocked Page Fallback Use this skill when normal web fetch/search is not enough, but the goal may still be reachable through alternate lawful paths. ## Do Not Do - do not bypass login - do not evade anti-bot or access controls - do not brute-force endpoints ## Fallback Ladder ### 1. Broaden discovery - search multiple engines - use site-specific search - try alternate titles, aliases, slugs, and locale variants ### 2. Switch transport - if plain fetch is thin, use a browser-rendered path - if browser path is noisy, pivot back to targeted fetch on discovered links ### 3. Pivot source types Try allowed alternatives: - official docs or help centers - official API or export surfaces - feeds, sitemaps, changelogs, or release notes - search-engine cached snippets where available - public mirrors or archive copies that are openly reachable - reputable secondary databases ### 4. Use structural clues If the exact page is blocked, search by: - page title fragments - quoted snippets - IDs, handles, usernames, product codes, or canonical names - internal link labels and breadcrumb terms ### 5. Keep going until confidence is earned Do not stop after: - one blocked fetch - one empty browser render - one weak search pass Stop when: - authoritative or converging sources answer the question - the remaining blocker is concrete and real - additional paths are now duplicative ## Output Pattern Return: 1. primary path that failed 2. fallback paths attempted 3. which fallback produced signal 4. best answer now available 5. what would require user-authorized login or a first-party API
Related Skills
model-fallback
Multi-model automatic fallback system. Monitors model availability and automatically falls back to backup models when the primary model fails. Supports MiniMax, Kimi, Zhipu and other OpenAI-compatible APIs. Use when: (1) Primary model API is unavailable, (2) Model response time is too slow, (3) Rate limit exceeded, (4) Need to optimize costs by using cheaper models for simple tasks.
Facebook Page & Group Scraper
> Part of **[ScrapeClaw](https://www.scrapeclaw.cc/)** — a suite of production-ready, agentic social media scrapers for Instagram, YouTube, X/Twitter, and Facebook built with Python & Playwright, no API keys required.
one-page-cv
Generate professionally tailored, one-page LaTeX/PDF resumes customized for specific job applications. Use this skill whenever the user mentions resume, CV, job application, JD, job description, tailoring a resume, applying for a job, 简历, 投递, 求职, 岗位, or wants to create/update a resume for a specific role — even if they just paste a job posting without explicitly asking for a resume. Also trigger when the user has resume files in their working directory and asks about job applications or career-related tasks.
deepagents-implementation
Implements agents using Deep Agents. Use when building agents with create_deep_agent, configuring backends, defining subagents, adding middleware, or setting up human-in-the-loop workflows.
deepagents-code-review
Reviews Deep Agents code for bugs, anti-patterns, and improvements. Use when reviewing code that uses create_deep_agent, backends, subagents, middleware, or human-in-the-loop patterns. Catches common configuration and usage mistakes.
deepagents-architecture
Guides architectural decisions for Deep Agents applications. Use when deciding between Deep Agents vs alternatives, choosing backend strategies, designing subagent systems, or selecting middleware approaches.
Page CRO Skill
## Trigger
landing-page-generator
Generates high-converting landing pages as complete Next.js/React (TSX) components with Tailwind CSS. Creates hero sections, feature grids, pricing tables, FAQ accordions, testimonial blocks, and CTA sections using proven copy frameworks (PAS, AIDA, BAB). Outputs SEO meta tags, structured data, and performance-optimised code targeting Core Web Vitals (LCP < 1s, CLS < 0.1). Use when the user asks to create a landing page, marketing page, homepage, single-page site, lead capture page, campaign page, promo page, or conversion-optimised web page — or when they want to A/B test landing page variants or replace a static page with one designed to convert.
page-cro
When the user wants to optimize, improve, or increase conversions on any marketing page — including homepage, landing pages, pricing pages, feature pages, or blog posts. Also use when the user says "CRO," "conversion rate optimization," "this page isn't converting," "improve conversions," or "why isn't this page working." For signup/registration flows, see signup-flow-cro. For post-signup activation, see onboarding-cro. For forms outside of signup, see form-cro. For popups/modals, see popup-cro.
nocobase-page-building
Guide AI to build NocoBase pages — menus, tables, forms, popups, KPIs, JS blocks, outlines, event flows
on-page-seo-auditor
On-page SEO audit: analyze titles, headers, images, internal links, and content quality with scored report, EEAT checks, and prioritized fix list. Part of a 20-skill SEO & GEO workflow suite. 页面SEO审计/排名诊断/站内优化/网页优化/搜索引擎优化
fb-page-poster
Publish posts to a Facebook Page via the Meta Graph API. Use when the user says "post to Facebook", "FB post", "粉專發文", "社群貼文", "幫我發文", "schedule post", "排程發文", or provides content and says "post this" or "publish this". Supports text-only, image, link-in-comment, scheduled posts, and multilingual translation (ZH↔EN) with a review step before publishing.