Skip to main content
skill CX Codex

firecrawl-migration-deep-dive — Claude Code skill: install

The firecrawl-migration-deep-dive skill guides a move from Puppeteer, Playwright, Cheerio, or another scraper to Firecrawl v2, with checks for parity, policy, spend, and rollback.

MIT 1 installs ★ 2,935 updated 2026-10-29

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add jeremylongshore/tons-of-skills-marketplace --skill firecrawl-migration-deep-dive -a claude-code
Open on GitHub

What firecrawl-migration-deep-dive does

The skill inventories the existing acquisition path: sources, login sessions, selectors, actions, formats, parsers, retries, proxies, schedules, storage, compliance controls, and operating metrics. It then maps those requirements to Firecrawl v2 capabilities, flags Cloud-only or self-hosted dependencies, and defines an adapter contract with a golden synthetic corpus.

The replacement path is placed behind a feature flag while the legacy adapter remains available for shadow comparison. The workflow checks content, metadata, latency, cost, security, load, and rollback gates before traffic moves in stages. It uses Read, Glob, Grep, Write, and Edit; it does not call Firecrawl, rotate keys, change account settings, or deploy on its own. Firecrawl Cloud work requires network access, and authenticated operations need FIRECRAWL_API_KEY supplied through an approved secret manager.

What it helps with

  • map a legacy scraper to Firecrawl v2 capabilities
  • define adapter parity and acceptance gates
  • compare shadow outputs without duplicate downstream writes
  • plan staged traffic migration with rollback evidence
  • identify requirements Firecrawl cannot replace

Example prompts for the agent

  • Migrate the scraper in <repository-path> from <legacy-adapter> to Firecrawl and document the parity gates.
  • Replace our Playwright acquisition path with Firecrawl v2, then build the capability map and golden corpus.
  • Compare the legacy and Firecrawl paths, estimate cost and risk, and prepare a staged rollout with rollback evidence.

How to install firecrawl-migration-deep-dive

1Skills CLI (Vercel)

npx skills add jeremylongshore/tons-of-skills-marketplace --skill firecrawl-migration-deep-dive -a claude-code

2Manually: put the files in place

~/.claude/skills/firecrawl-migration-deep-dive/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/firecrawl-migration-deep-dive/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about firecrawl-migration-deep-dive

How do I install firecrawl-migration-deep-dive in Claude Code?

Run npx skills add jeremylongshore/tons-of-skills-marketplace --skill firecrawl-migration-deep-dive -a claude-code, then check ~/.claude/skills/firecrawl-migration-deep-dive/SKILL.md.

What does firecrawl-migration-deep-dive do?

It helps replace an existing scraping workload with Firecrawl v2. The skill maps capabilities, defines parity tests, compares both paths in shadow mode, and lays out staged rollout and rollback evidence.

What is required for a Firecrawl Cloud migration?

The workload needs network access to Firecrawl Cloud. Authenticated operations use FIRECRAWL_API_KEY from an approved secret manager rather than a URL or committed code.

Source text

SKILL.md · MIT
---
name: firecrawl-migration-deep-dive
description: >-
  Migrate a custom Puppeteer, Playwright, Cheerio, or third-party scraping workload to Firecrawl v2 with parity, policy, cost, and rollback evidence. Use when replacing an existing acquisition system. Trigger with "migrate to Firecrawl", "replace Playwright scraping", or "Firecrawl adoption".
allowed-tools: Read,Glob,Grep,Write,Edit
argument-hint: "<repository-path> <legacy-adapter>"
version: 1.12.0
license: MIT
author: Jeremy Longshore <[email protected]>
tags: [saas, firecrawl, migration, architecture]
model: inherit
effort: high
compatibility: "Designed for Claude Code; Firecrawl Cloud work requires network access"
---
# Firecrawl Workload Migration

## Overview

Replace a scraper only after defining observable equivalence. Preserve the old adapter until the new path meets content, policy, performance, and recovery gates.

## Prerequisites

- The target repository or integration path and the requested operator outcome.
- The source authorization, data classification, and environment policy.
- Current Firecrawl documentation, credentials only when needed, and an owner for approvals.

## Current Contract

Firecrawl can replace rendering, crawl discovery, mapping, search, parsing, and typed extraction, but one endpoint is not equivalent to every legacy workflow. Scrape, crawl, map, batch, parse, JSON extraction, actions, Browser, and Cloud/self-hosted capabilities have different contracts and costs.

## Authentication

For authenticated Cloud operations, inject FIRECRAWL_API_KEY from an approved
secret manager. REST requests use Authorization: Bearer with the key. Never print,
commit, transmit, or place a key in a URL. Keyless access is suitable only where
the current documentation explicitly allows it and the workload accepts its
limits; production workflows should make identity and team ownership explicit.

## Instructions

1. Inventory legacy sources, login/session behavior, selectors/actions, discovery rules, formats, parsers, retries, proxies, schedules, storage, compliance controls, metrics, and operating cost.
2. Create a source-to-Firecrawl capability map. Mark unsupported, Cloud-only, self-host-dependent, behavior-changing, and policy-sensitive requirements.
3. Define an adapter contract and golden synthetic corpus with provenance, normalized content hashes, required-field coverage, latency, cost, and accepted variance.
4. Implement the smallest v2 path behind a feature flag. Keep target authorization, explicit scope/limits, cache/retention, cancellation, and error typing visible.
5. Shadow both paths on approved canaries, compare content and metadata without duplicating downstream writes, and investigate meaningful differences.
6. Shift traffic in stages only after parity, security, spend, load, and rollback gates pass. Keep the old path available through the observation window.
7. Remove legacy code and secrets only after rollback expiry, archive the decision and evidence, and verify dependency and data cleanup.

## Tool Discipline

Use Read, Glob, and Grep to inspect code, configuration, tests, and evidence. Use
Write/Edit only for approved implementation or documentation changes. Do not call
Firecrawl, rotate keys, change account settings, scrape a target, or deploy merely
because this skill was invoked.

## Approval Boundaries

Require approval before replaying authenticated sessions, changing target behavior or proxies, enabling Cloud-only processing, increasing spend, shifting traffic, or deleting the legacy path.

## Output

Return the capability matrix, parity definition, adapter design, golden corpus, shadow results, cost and risk comparison, staged rollout, rollback evidence, and deferred gaps.

## Error Handling

- Required behavior has no Firecrawl equivalent: retain that legacy component or redesign explicitly.
- Shadow outputs contain sensitive differences: quarantine the comparison and use content-free metrics.
- Parity cannot be measured: block migration rather than accepting visual inspection alone.

## Examples

- "Replace our docs crawler" maps discovery, rendering, filters, retries, and indexing before shadowing.
- "Delete Playwright first" is rejected until Firecrawl parity and rollback are proven.

## Resources

Read [official Firecrawl evidence](references/official-docs.md) before relying on
an endpoint, SDK method, plan limit, price, retention option, or self-hosted release.

© Jeremy Longshore · MIT · jeremylongshore/tons-of-skills-marketplace

Similar skills

All skills for Browser and scraping →

From the same set139

The whole set →
klingai-usage-analytics klingai-usage-analytics tracks Kling AI video generation runs, errors, and credit spending using JSONL logs. Builds daily summaries and cost projections. CX Codex +1 1installs cursor-usage-analytics cursor-usage-analytics analyzes aggregated Cursor usage across requests, models, spend, and team adoption. Use it to prepare reports and review quota signals. CX Codex +1 1installs customerio-cost-tuning customerio-cost-tuning audits a Customer.io workspace for wasted spend: which profiles inflate the bill, which accounts can go, where duplicate events pile up. CX Codex +1 1installs apollo-core-workflow-a apollo-core-workflow-a builds an Apollo.io lead generation pipeline in Claude Code to search prospects and enrich qualified contacts with verified emails and phone numbers. CX Codex +1 1installs vercel-webhooks-events vercel-webhooks-events — a skill for Claude Code, Codex, Cursor and other platforms that processes Vercel deployment events with HMAC signature verification. CX Codex +1 1installs vercel-reference-architecture vercel-reference-architecture sets up a layered Vercel architecture for Next.js applications. Helps structure edge middleware, serverless API routes, and environment validation. CX Codex +1 1installs vercel-policy-guardrails The vercel-policy-guardrails skill adds Vercel project checks for secret exposure, CI policy violations, Edge Runtime imports, and protected routes. CX Codex +1 1installs gcs-lifecycle-policy gcs-lifecycle-policy — a skill that handles lifecycle policy work in Google Cloud Storage. It activates on its own when a request mentions gcs or lifecycle policy. CX Codex +1 1installs

Project sponsors

Companies that keep this analytics open