How do I install the Ivx Cf Firecrawl skill?

Run npx skillmds@latest add intelli-verse-x/ivx-cf-firecrawl in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Ivx Cf Firecrawl safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: makes network calls, reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Ivx Cf Firecrawl?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Ivx Cf Firecrawl free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Ivx Cf Firecrawl?

intelli-verse-x (@intelli-verse-x) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Ivx Cf Firecrawl by intelli-verse-x

Name: Ivx Cf Firecrawl
Rating: 4.2 (5 reviews)
Author: intelli-verse-x

Ivx Cf Firecrawl

Firecrawl gives agents and pipelines fast, reliable web context with strong search, scraping, and page-interaction tools. Umbrella skill that routes to firecrawl-search, firecrawl-scrape, and firecrawl-research, and documents install, credentials, and the keyless fallback.

intelli-verse-x Updated Aug 19, 2026 0 repo stars

File contents

/firecrawl

Firecrawl helps agents search first, scrape clean content, interact with live pages when plain extraction is not enough, and produce finished deliverables from web data.

In this repo Firecrawl is available three ways:

Admin portal — /contentx/skills lists every skill and includes a runnable Firecrawl playground (search + scrape) backed by POST /api/skills/firecrawl/search and POST /api/skills/firecrawl/scrape.
Python tool — tools/research/firecrawl_research.py::FirecrawlResearcher (used by concept_to_curriculum and the learning pipelines).
CLI — the official Firecrawl CLI for live web work in a terminal session.

Install (CLI + skills + browser auth)

One command installs the Firecrawl CLI, the build skills, and the workflow skills, and opens browser auth so a human can sign in or create an account:

npx -y firecrawl-cli@latest init --all --browser

Verify the install before doing real work:

mkdir -p .firecrawl
firecrawl --status
firecrawl scrape "https://firecrawl.dev" -o .firecrawl/install-check.md

Note: .firecrawl/ is git-ignored run-local output — never commit it (see .cursor/ANTI_PATTERNS.md).

Credentials

Set FIRECRAWL_API_KEY=fc-... in the environment (or the API pod's secret). The Python SDK (firecrawl-py, already in requirements.txt) and the portal endpoints pick it up automatically.
No key? Search/scrape still work on the keyless free tier (rate-limited): the REST API at https://api.firecrawl.dev/v2 accepts /search, /scrape, and /interact without an Authorization header. Crawl/map/agent require a key.
To have a human authorize a key, send them to https://www.firecrawl.dev/signin?view=signup&source=agent-suggested or run the CLI auth flow above.

Choose your path

Need	Use
Web discovery by query	`/firecrawl-search` (skills/firecrawl/search)
Clean markdown from a known URL	`/firecrawl-scrape` (skills/firecrawl/scrape)
Citation-grade research bundle for a pipeline	`/firecrawl-research` (skills/firecrawl/research)
Clicks/forms/login on a live page	`firecrawl interact` via the CLI
Bulk extraction / URL discovery	`firecrawl crawl` / `firecrawl map` via the CLI (needs API key)
Diagnose a failing Firecrawl job	`firecrawl ask --job <jobId>` or `POST /support/ask`

Default flow for live web work: search → scrape → interact only when the page needs clicks/forms/login. If a call fails, pass the failing jobId to firecrawl ask instead of guessing.

REST quick reference (no install needed)

Base URL https://api.firecrawl.dev/v2, auth header Authorization: Bearer fc-YOUR_API_KEY (optional on the free tier):

POST /search — discover pages by query
POST /scrape — clean markdown from a single URL
POST /interact — browser actions on live pages
POST /support/ask — diagnose a failing call ({ question, jobId? })
POST /support/docs-search — "how do I…" answers grounded in Firecrawl docs

MCP: point any MCP client at https://mcp.firecrawl.dev/v2/mcp (keyless OK).

Implementation

Portal/API: api/routes/skills.py (/api/skills/firecrawl/*)
Pipeline tool: tools/research/firecrawl_research.py
Portal UI: frontend/src/views/vimax/SkillsView.vue (/contentx/skills)

---name: ivx-cf-firecrawldescription: Firecrawl gives agents and pipelines fast, reliable web context with strong search, scraping, and page-interaction tools. Umbrella skill that routes to firecrawl-search, firecrawl-scrape, and firecrawl-research, and documents install, credentials, and the keyless fallback.---# /firecrawlFirecrawl helps agents search first, scrape clean content, interact with livepages when plain extraction is not enough, and produce finished deliverablesfrom web data.In this repo Firecrawl is available three ways:1. **Admin portal** — `/contentx/skills` lists every skill and includes a runnable Firecrawl playground (search + scrape) backed by `POST /api/skills/firecrawl/search` and `POST /api/skills/firecrawl/scrape`.2. **Python tool** — `tools/research/firecrawl_research.py::FirecrawlResearcher` (used by `concept_to_curriculum` and the learning pipelines).3. **CLI** — the official Firecrawl CLI for live web work in a terminal session.## Install (CLI + skills + browser auth)One command installs the Firecrawl CLI, the build skills, and the workflowskills, and opens browser auth so a human can sign in or create an account:```bashnpx -y firecrawl-cli@latest init --all --browser```Verify the install before doing real work:```bashmkdir -p .firecrawlfirecrawl --statusfirecrawl scrape "https://firecrawl.dev" -o .firecrawl/install-check.md```Note: `.firecrawl/` is git-ignored run-local output — never commit it(see `.cursor/ANTI_PATTERNS.md`).## Credentials- Set `FIRECRAWL_API_KEY=fc-...` in the environment (or the API pod's secret). The Python SDK (`firecrawl-py`, already in `requirements.txt`) and the portal endpoints pick it up automatically.- No key? Search/scrape still work on the **keyless free tier** (rate-limited): the REST API at `https://api.firecrawl.dev/v2` accepts `/search`, `/scrape`, and `/interact` without an `Authorization` header. Crawl/map/agent require a key.- To have a human authorize a key, send them to https://www.firecrawl.dev/signin?view=signup&source=agent-suggested or run the CLI auth flow above.## Choose your path| Need | Use ||------|-----|| Web discovery by query | `/firecrawl-search` (skills/firecrawl/search) || Clean markdown from a known URL | `/firecrawl-scrape` (skills/firecrawl/scrape) || Citation-grade research bundle for a pipeline | `/firecrawl-research` (skills/firecrawl/research) || Clicks/forms/login on a live page | `firecrawl interact` via the CLI || Bulk extraction / URL discovery | `firecrawl crawl` / `firecrawl map` via the CLI (needs API key) || Diagnose a failing Firecrawl job | `firecrawl ask --job <jobId>` or `POST /support/ask` |Default flow for live web work: search → scrape → interact only when the pageneeds clicks/forms/login. If a call fails, pass the failing `jobId` to`firecrawl ask` instead of guessing.## REST quick reference (no install needed)Base URL `https://api.firecrawl.dev/v2`, auth header`Authorization: Bearer fc-YOUR_API_KEY` (optional on the free tier):- `POST /search` — discover pages by query- `POST /scrape` — clean markdown from a single URL- `POST /interact` — browser actions on live pages- `POST /support/ask` — diagnose a failing call (`{ question, jobId? }`)- `POST /support/docs-search` — "how do I…" answers grounded in Firecrawl docsMCP: point any MCP client at `https://mcp.firecrawl.dev/v2/mcp` (keyless OK).## Implementation- Portal/API: `api/routes/skills.py` (`/api/skills/firecrawl/*`)- Pipeline tool: `tools/research/firecrawl_research.py`- Portal UI: `frontend/src/views/vimax/SkillsView.vue` (`/contentx/skills`)

Frequently asked questions