# Firecrawl Research Patterns

> Programmatic Firecrawl usage, self-hosted operations, academic paper routing, recursive deep research, and raw corpus persistence.

- **Type:** Skill
- **Install:** `agentstack add skill-terrylica-cc-skills-firecrawl-research-patterns`
- **Verified:** Pending review
- **Seller:** [terrylica](https://agentstack.voostack.com/s/terrylica)
- **Installs:** 0
- **Category:** [Databases](https://agentstack.voostack.com/c/databases)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [terrylica](https://github.com/terrylica)
- **Source:** https://github.com/terrylica/cc-skills/tree/main/plugins/devops-tools/skills/firecrawl-research-patterns

## Install

```sh
agentstack add skill-terrylica-cc-skills-firecrawl-research-patterns
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Firecrawl Research Patterns

Programmatic patterns for using self-hosted Firecrawl in research workflows — search, scrape, route academic papers, run recursive deep research, and persist raw results for future re-analysis. Also covers self-hosted deployment, health checks, and recovery.

For archiving AI chat conversations (ChatGPT/Gemini shares), see `Skill(gh-tools:research-archival)`.

---

> **Self-Evolving Skill**: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues.

## FIRST — TodoWrite Task Templates

**MANDATORY**: Select and load the appropriate template before any research work.

### Intent routing — AI chat share URLs (chatgpt / gemini / claude)

AI chat share URLs (`chatgpt.com/share/*`, `chat.openai.com/share/*`, `gemini.google.com/share/*`, `g.co/gemini/share/*`, `claude.ai/share/*`, `claude.ai/chat/*`) can be processed by **either** this skill or `Skill(gh-tools:research-archival)`. Pick by **intent**, not URL pattern:

| Your intent                                                                        | Skill                               | Output                                                                         |
| ---------------------------------------------------------------------------------- | ----------------------------------- | ------------------------------------------------------------------------------ |
| One-off read / extract conversation text for analysis                              | **This skill** — port 3003 (Sec. 5) | Markdown file on Caddy; no frontmatter, no Issue, no provenance.               |
| Long-term archive with identity verification, frontmatter, GitHub Issue cross-link | `Skill(gh-tools:research-archival)` | `docs/research/YYYY-MM-DD-{slug}-{type}.md` + issue with Discovery Provenance. |
| Already have the file, just need to scrape extra content into the same corpus file | **This skill**                      | Append-mode workflow under your control.                                       |

> **Both paths share the same Firecrawl backend.** `research-archival` calls Firecrawl too — it adds an archival layer on top. There is no scraping capability gap between the two; the difference is what happens to the bytes after they come back.

**WebFetch limitation, regardless of intent**: Claude Code hard-blocks `WebFetch` against `chatgpt.com`. Use Firecrawl (this skill, any port) or Jina Reader instead. Verified 2026-05-27.

**Empirical note** (2026-05-27): port 3003 successfully scrapes ChatGPT shares — `curl :3003/scrape?url=...&name=...` returned a 75 KB / 1,734-line markdown for a real ChatGPT share via the Caddy two-step pattern (see Section 5). Earlier guidance that said "route AI chat shares out" was overcautious and contradicted Section 5's port table.

### Template A — Single Firecrawl Search + Persist

```
1. Health check — GET http://littleblack.tail0f299b.ts.net:3002/ (expect 200 + {"message":"Firecrawl API",...}; NEVER use /v1/health — it 404s)
2. Execute search — POST /v1/search with query, limit, scrapeOptions
3. Persist raw results — save each result page to docs/research/corpus/ with frontmatter
4. Update corpus index — append entries to docs/research/corpus-index.jsonl
5. Extract findings — summarize key learnings from raw corpus files
```

### Template B — Academic Paper Retrieval + Persist

```
1. Identify source — classify URL/DOI per academic-paper-routing.md decision tree
2. Route to scraper — arxiv direct HTML, Semantic Scholar API, Firecrawl, or Jina Reader
3. Scrape content — execute fetch with appropriate method and timeout
4. Persist raw result — save to docs/research/corpus/ with academic-specific frontmatter
5. Update corpus index — append entry to corpus-index.jsonl
6. Summarize paper — extract key claims, methods, results from raw corpus file
```

### Template C — Full Recursive Deep Research with Corpus

```
1. Health check — GET http://littleblack.tail0f299b.ts.net:3002/ (expect 200 + Firecrawl banner; NEVER /v1/health — it 404s)
2. Initialize parameters — set breadth (default 4), depth (default 2), concurrency (default 2)
3. Generate search queries — LLM generates N queries from topic + prior learnings
4. Execute searches — Firecrawl /v1/search for each query via p-limit(concurrency)
5. Persist raw results — save ALL scraped pages to docs/research/corpus/ with provenance
6. Extract learnings — LLM extracts key findings + follow-up questions per result set
7. Recurse — for each follow-up, recurse with breadth=ceil(breadth/2), depth=depth-1
8. Base case — depth=0, return accumulated learnings
9. Synthesize report — LLM generates final markdown from all learnings
10. Write session report — save to docs/research/sessions/ with corpus file references
11. Update corpus index — append all new entries to corpus-index.jsonl
```

### Template D — Corpus Review / Re-Analysis

```
1. Inventory corpus — read docs/research/corpus-index.jsonl, filter by session/topic/date
2. Read raw files — load matching corpus files from docs/research/corpus/
3. Re-analyze — extract new insights with current context/questions
4. Update session report — amend or create new session report in docs/research/sessions/
```

### Template E — Image-Rich Paper with Inline Figures

Use when paper contains architecture diagrams, result plots, attention maps, or any critical visual content.

```
1. Scrape text — use port 3003 (preferred, preserves absolute image URLs) or Jina fallback
2. Detect figures — scan scraped markdown for  patterns with .png/.jpg/.svg
3. Extract figure URLs — for arXiv: probe https://arxiv.org/html/{id}v{n}/x{N}.png until 404
4. Keep URLs inline — DO NOT rewrite to local relative paths (breaks GitHub rendering)
5. Ensure inline embedding — markdown body must have  for each figure
6. Catalog in frontmatter — add figure_count and figure_urls list (all absolute URLs)
7. Save corpus file — GFM markdown with inline absolute URLs renders on GitHub without hosting
8. Update corpus-index.jsonl — include has_figures: true, figure_count, figure_urls
```

---

## Section 1 — Programmatic Firecrawl Usage

**Instance**: Self-hosted on **littleblack** — Debian 12 (bookworm), kernel 6.1.0-31, hostname `kab`, login user `yca`, RTX 2080 Ti, 62 GiB RAM. No API key required for any Firecrawl endpoint.

| Access path        | URL base                                    | When to use                                                                                  |
| ------------------ | ------------------------------------------- | -------------------------------------------------------------------------------------------- |
| Tailscale FQDN     | `http://littleblack.tail0f299b.ts.net:3002` | **Preferred.** Works on every tailnet-attached client regardless of MagicDNS resolver state. |
| Tailscale IP       | `http://100.78.106.112:3002`                | Bypasses DNS entirely; stable while the tailnet device exists.                               |
| Tailscale MagicDNS | `http://littleblack:3002`                   | Conditional — only when bare-name resolution works (see preflight below).                    |
| Same-LAN direct    | `http://192.168.1.67:3002`                  | Only when the client is on the Telus PureFibre LAN (`eno1` interface).                       |
| Legacy ZeroTier    | `http://172.25.236.1:3002`                  | Fragile fallback (`ztksetviym` interface). Prefer Tailscale.                                 |

**MagicDNS preflight** (run before relying on bare `littleblack`):

```bash
# macOS — does the OS resolver know about the bare name?
dscacheutil -q host -a name littleblack | grep -q '^ip_address'  && echo OK || echo MISSING

# Cross-platform — does any path resolve?
getent hosts littleblack 2>/dev/null || ping -c1 -W1 littleblack 2>&1 | head -1
```

If preflight returns `MISSING` / "cannot resolve", **use the FQDN row.** SSH happens to work because `~/.ssh/config` hard-codes the FQDN under the `Host littleblack` alias — that's an SSH-only shortcut, not a system-wide DNS facility. Bare `littleblack` over HTTP fails silently as `HTTP 000` when the resolver doesn't have it; the failure mode is invisible without `ping`/`dscacheutil`. Confirmed broken on `m3max` (this Mac) as of 2026-05-27.

SSH (for ops, not API calls): `ssh littleblack` — defined in `~/.ssh/config` as `HostName littleblack.tail0f299b.ts.net`, `User yca`, `IdentityFile ~/.ssh/id_ed25519_zerotier_np`.

### Why `fetch()` Instead of `@mendable/firecrawl-js` SDK

The official SDK uses `jiti` for dynamic imports, which is incompatible with Bun's module resolution. Direct `fetch()` calls are simpler, more reliable, and have zero dependencies.

### Two Endpoints

| Endpoint          | Purpose               | When to Use                                       |
| ----------------- | --------------------- | ------------------------------------------------- |
| `POST /v1/search` | Search + scrape combo | Research queries — returns multiple scraped pages |
| `POST /v1/scrape` | Single URL scrape     | Known URL — extract markdown from one page        |

See [api-endpoint-reference.md](./references/api-endpoint-reference.md) for full request/response contracts.

### Quick Examples

Use the FQDN base URL — works on every tailnet-attached client regardless of MagicDNS resolver state. Pull from `$FIRECRAWL_BASE` env var if your project sets one, otherwise hard-code the FQDN:

```typescript
const FIRECRAWL_BASE =
  process.env.FIRECRAWL_BASE ?? "http://littleblack.tail0f299b.ts.net:3002";
```

**Search** (returns multiple results with markdown):

```typescript
const res = await fetch(`${FIRECRAWL_BASE}/v1/search`, {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    query: "mixture of experts scaling laws",
    limit: 5,
    scrapeOptions: { formats: ["markdown"] },
  }),
});
const { data } = await res.json(); // data: [{ url, markdown, metadata }]
```

**Scrape** (single URL):

```typescript
const res = await fetch(`${FIRECRAWL_BASE}/v1/scrape`, {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    url: "https://arxiv.org/abs/2401.12345",
    formats: ["markdown"],
    waitFor: 3000, // ms — for JS-heavy pages
  }),
});
const { data } = await res.json(); // data: { markdown, metadata }
```

### Error Handling

```typescript
// Always set a timeout
const controller = new AbortController();
const timeoutId = setTimeout(() => controller.abort(), 15_000);

try {
  const res = await fetch(url, { ...opts, signal: controller.signal });
  if (!res.ok) throw new Error(`Firecrawl: ${res.status} ${res.statusText}`);
  const json = await res.json();
  if (!json.data || (Array.isArray(json.data) && json.data.length === 0)) {
    // Empty results — not an error, but no content to process
  }
} finally {
  clearTimeout(timeoutId);
}
```

### Health Check

> **There is no `/v1/health` endpoint on this Firecrawl build.** Probing it returns HTTP 404 (Express's HTML error page), which looks like a service-down signal but isn't. Use the root `/` endpoint, which returns HTTP 200 with `{"message":"Firecrawl API","documentation_url":"https://docs.firecrawl.dev"}`. Confirmed 2026-05-27 against ports 3002 / FQDN / IP.

```typescript
// Quick health check before starting a research session.
// Uses the Tailscale FQDN — works regardless of MagicDNS resolver state.
const FIRECRAWL_BASE = "http://littleblack.tail0f299b.ts.net:3002";
const res = await fetch(`${FIRECRAWL_BASE}/`);
if (!res.ok) {
  throw new Error(
    `Firecrawl unreachable (${res.status}) — see self-hosted-operations.md and self-hosted-troubleshooting.md`,
  );
}
const banner = await res.json();
if (banner.message !== "Firecrawl API") {
  throw new Error(
    `Unexpected root response: ${JSON.stringify(banner).slice(0, 200)}`,
  );
}
```

For a true end-to-end probe (proves the full search/scrape stack works, not just the HTTP listener), `POST /v1/scrape` against `https://example.com` and check `success: true`:

```bash
curl -s --max-time 15 -X POST \
  "http://littleblack.tail0f299b.ts.net:3002/v1/scrape" \
  -H 'Content-Type: application/json' \
  -d '{"url":"https://example.com","formats":["markdown"]}' \
  | python3 -c "import sys, json; d=json.load(sys.stdin); print('OK' if d.get('success') else 'FAIL')"
```

---

## Section 2 — Academic Paper Routing

Route paper retrieval to the most effective method based on source. Full decision tree in [academic-paper-routing.md](./references/academic-paper-routing.md).

### Quick Reference

| Source            | Best Method                           | Fallback                  |
| ----------------- | ------------------------------------- | ------------------------- |
| arxiv.org         | Direct HTML (`/html/ID`)              | Firecrawl `/v1/scrape`    |
| Semantic Scholar  | API (`api.semanticscholar.org`)       | Firecrawl search by title |
| ACL Anthology     | Firecrawl `/v1/scrape`                | Direct PDF download       |
| NeurIPS/ICML/ICLR | Firecrawl `/v1/scrape` with `waitFor` | Search by title           |
| IEEE Xplore       | Firecrawl with `waitFor: 3000`        | Author's website          |
| ACM DL            | Firecrawl with `waitFor: 3000`        | Author's website          |
| Author blogs      | Jina Reader (`r.jina.ai`)             | Firecrawl `/v1/scrape`    |
| Google Scholar    | Firecrawl `/v1/search`                | Direct search query       |

### DOI Resolution

```typescript
// DOI → publisher URL → route to appropriate scraper
const res = await fetch(`https://doi.org/${doi}`, { redirect: "follow" });
const publisherUrl = res.url; // e.g., https://dl.acm.org/doi/10.1145/...
// Then route publisherUrl through the decision tree above
```

---

## Section 3 — Recursive Research Protocol

The iterative search → extract → recurse → synthesize pattern. Full step-by-step protocol in [recursive-research-protocol.md](./references/recursive-research-protocol.md).

### Algorithm Overview

```
deepResearch(topic, breadth=4, depth=2, concurrency=2):
   1. Generate N search queries (N = breadth) from topic + prior learnings
   2. For each query (via p-limit concurrency):
      a. Firecrawl /v1/search → get results
      b. PERSIST each raw result to docs/research/corpus/
      c. Extract learnings + follow-up questions
   3. For each follow-up question:
      → Recurse with breadth=ceil(breadth/2), depth=depth-1
   4. Base case: depth=0 → return accumulated learnings
   5. Synthesize final report from all learnings
   6. Write session report to docs/research/sessions/
```

### Default Parameters (from working implementation)

| Parameter     | Default | Max | Rationale                                               |
| ------------- | ------- | --- | ------------------------------------------------------- |
| `breadth`     | 4       | —   | Number of parallel search queries per level             |
| `depth`       | 2       | 5   | Recursion levels (depth > 5 yields diminishing returns) |
| `concurrency` | 2       | —   | Parallel Firecrawl requests (self-hosted, be gentle)    |
| `limit`       | 5       | —   | Results per search query                                |
| `timeout`     | 15000ms | —   | Per-search timeout                                      |

### Token Budget

Each search returns up to 5 pages. Trim each page to ~25,000 tokens before LLM processing:

```typescript
function trimToTokenLimit(text: string, maxTokens: number): string {
  if (!text) return "";
  const estimatedTokens = Math.ceil(text.length / 3.5);
  if (estimatedTokens "          # or any JS-rendered page
NAME="chatgpt-metric-stack-2026-05-27"        # slug — NO whitespace or special chars

# URL-encode the target (avoid Python's trailing newline — use end='')
ENC=$(python3 -c "import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1], safe=''), end='')" "$URL

…

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [terrylica](https://github.com/terrylica)
- **Source:** [terrylica/cc-skills](https://github.com/terrylica/cc-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** yes
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** yes
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: flagged — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-terrylica-cc-skills-firecrawl-research-patterns
- Seller: https://agentstack.voostack.com/s/terrylica
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.