技能库智客分类：Agent 工作流 firecrawl-competitive-intel

Firecrawl 竞争性英特尔

监控竞争对手的定价,特性,更改日志,仪表板,以及与Firecrawl的产品变化. 用于经常性的竞争智能,定价分级提取,特征变化跟踪,或结构化的竞争者提示.

31238 安装量

官方网址：作者主页

技能介绍

先看中文介绍；官方 description 原文单独保留，不改写 SKILL.md。

做什么

监控竞争对手的定价,特性,更改日志,仪表板,以及与Firecrawl的产品变化. 用于经常性的竞争智能,定价分级提取,特征变化跟踪,或结构化的竞争者提示.

何时用

官方 description 未单独写出 Use when。按规范，代理会在用户任务与这段 description 的关键词匹配时激活本技能。

代理如何加载

按 Agent Skills 渐进披露：启动时只加载 name 与 description（约 100 token）；任务匹配后才读入整份 SKILL.md 正文；scripts/、references/、assets/ 仅在需要时再读。本文件正文结构：Firecrawl Competitive Intel、Onboarding Interview、Firecrawl Collection Plan、Parallel Work、Final Deliverable、Competitive Intel: [Competitors]。

文件分析

文件分析：这是一份仅含 SKILL.md 的指令型技能，代理激活后整份正文进入上下文。

官方 description（原文）

Monitor competitor pricing, features, changelogs, dashboards, and product changes with Firecrawl. Use for recurring competitive intelligence, pricing tier extraction, feature change tracking, or structured competitor alerts.

Firecrawl Competitive IntelOnboarding InterviewFirecrawl Collection PlanParallel WorkFinal DeliverableCompetitive Intel: [Competitors]AlertsPer-Competitor BreakdownCross-Competitor ComparisonSuggested Follow-UpsSourcesRerun Inputs

· 许可：ISC

来源分类：skills.sh agent-skill

来源与网址

市场来源：skills.sh

GitHub 完整包

开源榜 Skill 分类

SKILL.md 与 Agent 调用

官方规范 ↗

name: firecrawl-competitive-intel
description: Monitor competitor pricing, features, changelogs, dashboards, and product changes with Firecrawl. Use for recurring competitive intelligence, pricing tier extraction, feature change tracking, or structured competitor alerts.
许可: ISC

发现技能客户端向 Agent 提供名称与描述目录。
匹配与调用用户指定或任务匹配后，载入 SKILL.md 指令。
按需加载按步骤读取参考文档、使用脚本与素材。

具体调用语法与可用工具以目标 Agent 客户端为准。查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围，保留技能包的附属文件，安装后检查客户端能否发现该技能。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理，确认其中的目标目录与客户端匹配。

把 Agent Skill「firecrawl-competitive-intel」安装到我的项目：SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-e5460fbf43b51f09-Firecrawl-%E7%AB%9E%E4%BA%89%E6%80%A7%E8%8B%B1%E7%89%B9%E5%B0%94.html
请存为 .cursor/skills/firecrawl-competitive-intel/SKILL.md 或 .claude/skills/firecrawl-competitive-intel/SKILL.md，frontmatter 的 name 与 description 保持原样，不要改写。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表，确认实际名称。

npx skills add 'https://github.com/firecrawl/firecrawl-workflows' --list

npx skills add 'https://github.com/firecrawl/firecrawl-workflows' --skill 'firecrawl-competitive-intel'

CLI 会交互选择目标 Agent，默认安装到项目；用户级安装使用 -g。先通过查看命令核对仓库内容，再用 npx skills list 检查已安装技能。

SKILL.md 原文可复制，不会改动源文件

---
name: firecrawl-competitive-intel
description: Monitor competitor pricing, features, changelogs, dashboards, and product changes with Firecrawl. Use for recurring competitive intelligence, pricing tier extraction, feature change tracking, or structured competitor alerts.
license: ISC
metadata:
  author: firecrawl
  version: "0.1.0"
  homepage: https://www.firecrawl.dev
  source: https://github.com/firecrawl/firecrawl-workflows
inputs:
  - name: FIRECRAWL_API_KEY
    description: Firecrawl API key for hosted Firecrawl requests.
    required: true
---

# Firecrawl Competitive Intel

Use this for monitoring competitors over time. This is not the broad competitor analysis workflow.

## Onboarding Interview

Infer competitors, focus, cadence, and output format from context. If competitors are clear, proceed immediately.

Ask at most 1-3 concise questions only if blocked, such as the competitor list, focus area, or whether authenticated pages/profiles are required.

## Firecrawl Collection Plan

For each competitor, use Firecrawl scrape or browser as needed:

- pricing pages, annual/monthly toggles, expanded feature tables
- feature and product pages
- changelogs, blogs, release notes, docs updates
- authenticated dashboards only when the user has legitimate access

## Parallel Work

If appropriate, use sub-agents or equivalent parallel task runners. A natural split is one competitor per researcher or one focus area per researcher.

Each researcher should return pricing tiers, features, recent changes, source URLs, and confidence notes.

## Final Deliverable

```markdown
# Competitive Intel: [Competitors]

## Alerts
[Notable pricing, feature, or positioning changes]

## Per-Competitor Breakdown
[Pricing tiers, feature inventory, recent changes]

## Cross-Competitor Comparison
[Pricing table, feature matrix, key differentiators]

## Suggested Follow-Ups
[What to monitor next]

## Sources
[URLs visited]

## Rerun Inputs
workflow: firecrawl-competitive-intel
competitors: [list]
focus: [all/pricing/features/changelog]
cadence: [one-off/weekly/monthly]
```

## JSON Shape

When structured output is requested, include `generatedAt`, `competitors`, `pricing`, `recentChanges`, `features`, and `sources`.

## Quality Bar

- Extract real plan names, limits, and dates when available.
- Note contact-sales or gated details instead of guessing.
- Preserve sources for diffing future runs.

阅读排版

name: firecrawl-competitive-intel description: Monitor competitor pricing, features, changelogs, dashboards, and product changes with Firecrawl. Use for recurring competitive intelligence, pricing tier extraction, feature change tracking, or structured competitor alerts. license: ISC metadata: author: firecrawl version: "0.1.0" homepage: https://www.firecrawl.dev source: https://github.com/firecrawl/firecrawl-workflows inputs:

name: FIRECRAWL_API_KEY description: Firecrawl API key for hosted Firecrawl requests. required: true

Firecrawl Competitive Intel

Use this for monitoring competitors over time. This is not the broad competitor analysis workflow.

Onboarding Interview

Infer competitors, focus, cadence, and output format from context. If competitors are clear, proceed immediately.

Ask at most 1-3 concise questions only if blocked, such as the competitor list, focus area, or whether authenticated pages/profiles are required.

Firecrawl Collection Plan

For each competitor, use Firecrawl scrape or browser as needed:

pricing pages, annual/monthly toggles, expanded feature tables
feature and product pages
changelogs, blogs, release notes, docs updates
authenticated dashboards only when the user has legitimate access

Parallel Work

If appropriate, use sub-agents or equivalent parallel task runners. A natural split is one competitor per researcher or one focus area per researcher.

Each researcher should return pricing tiers, features, recent changes, source URLs, and confidence notes.

Final Deliverable

# Competitive Intel: [Competitors]

## Alerts
[Notable pricing, feature, or positioning changes]

## Per-Competitor Breakdown
[Pricing tiers, feature inventory, recent changes]

## Cross-Competitor Comparison
[Pricing table, feature matrix, key differentiators]

## Suggested Follow-Ups
[What to monitor next]

## Sources
[URLs visited]

## Rerun Inputs
workflow: firecrawl-competitive-intel
competitors: [list]
focus: [all/pricing/features/changelog]
cadence: [one-off/weekly/monthly]

JSON Shape

When structured output is requested, include generatedAt, competitors, pricing, recentChanges, features, and sources.

Quality Bar

Extract real plan names, limits, and dates when available.
Note contact-sales or gated details instead of guessing.
Preserve sources for diffing future runs.