meta-search
Recovers web content when searches fail with 403, 429, 422 errors, blocked sites, or empty results. Runs bundled Tavily/Jina extraction scripts, then falls back to manual strategies.
What this skill does
# Meta Search
Recover web content when standard tools fail. Orchestrates multi-service extraction via bundled scripts (Tavily, Jina.ai, free services), with manual fallback strategies.
## Recovery workflow
### Step 1: Run the recovery script
```bash
node "${CLAUDE_SKILL_DIR}/scripts/search.mjs" <query-or-url> 2>/dev/null
```
The script tries Tavily API → Jina.ai API → Jina.ai Public Reader with automatic error handling, retries, and service rotation. Output is the recovered content.
If the script succeeds, use the output directly. If it fails (no API keys, network issues, or all services down), proceed to Step 2.
### Step 2: Manual recovery with built-in tools
Apply the strategy matching the error type:
**403 Forbidden**
1. Retry with `web_fetch` using the URL directly
2. Search for the page title or key terms instead
3. Try cache URLs: `https://webcache.googleusercontent.com/search?q=cache:<URL>` or `https://web.archive.org/web/2/<URL>`
**429 Rate Limited**
1. Wait briefly, then retry
2. Simplify the query to essential keywords
3. Switch approach: if searching, try fetching a known URL instead
**422 Validation / "Did 0 searches..."**
1. Remove special characters and quotes from the query
2. Shorten to essential keywords only
3. Split compound queries into separate searches
**451 SecurityCompromise**
1. Search with domain exclusion: `"<query> -site:<blocked-domain>"`
2. Search for alternatives: `"<query>" alternative OR mirror`
**ECONNREFUSED / Timeout**
1. Retry after a brief pause
2. Try `web_fetch` with a different URL for the same content
**Empty Results**
1. Broaden the query — remove restrictive terms
2. Try different phrasing or synonyms
### Step 3: Report results
- On success: return the recovered content
- On partial success: return what was found, note what remains inaccessible
- On failure: report which strategies were tried and why they failed
## Sandbox compatibility
The extraction script makes outbound requests to external services. If Claude Code's sandbox is enabled, these domains must be in the `allowedDomains` list:
```jsonc
// ~/.claude/settings.json
{
"sandbox": {
"network": {
"allowedDomains": [
"api.tavily.com",
"api.search.brave.com",
"api.exa.ai",
"s.jina.ai",
"r.jina.ai",
"api.jina.ai"
]
}
}
}
```
Without these, all extraction services will fail with `fetch failed` and the script will fall through to Step 2 (manual recovery).
Free fallback services (Jina.ai Public Reader) use `r.jina.ai` which is already in the allowedDomains list above.
## Limitations
- Cannot bypass CAPTCHA or advanced bot protection
- Some paywalled content remains inaccessible
- Cache/archive services may have stale content
- PostToolUse hook does not intercept tool-level exceptions (PostToolUseFailure)
- Web search requires at least one API key (SEARCH_PLUS_TAVILY_API_KEY or SEARCH_PLUS_JINA_API_KEY)
Related in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.