gr-competitor

gr-competitor is a skill for Claude Code, Codex from Gingiris/gingiris-skills. It costs 99 tokens per session (1,325 once invoked), scanned A, original, MIT.

A competitor-research workflow that collects information from rival websites, including landing pages, pricing, blogs, and past changes. A landing page is the main page designed to introduce and sell a product; Wayback is an archive of older website versions.

In plain words
What is it for?
Use it to scan competitor sites, collect fields such as titles and calls to action, compare pricing, review recent blog content, and examine archived changes.
Why use it?
It reduces the manual work of opening many sites and comparing their messaging, prices, content, and history.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/gingiris/gingiris-skills/gr-competitor
Any agent
npx skills add Gingiris/gingiris-skills --skill gr-competitor
Clone the repo
git clone --depth 1 https://github.com/Gingiris/gingiris-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for gr-competitor

README.md
[![agentmods](https://agentmods.dev/badge/skills/gingiris/gingiris-skills/gr-competitor.svg)](https://agentmods.dev/skills/gingiris/gingiris-skills/gr-competitor)
Your own site
<a href="https://agentmods.dev/skills/gingiris/gingiris-skills/gr-competitor"><img src="https://agentmods.dev/badge/skills/gingiris/gingiris-skills/gr-competitor.svg" alt="Measured on agentmods" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,325 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00099 $0.01325
Opus 5 $0.00049 $0.00662
Sonnet 5 $0.00020 $0.00265
Haiku 4.5 $0.00010 $0.00133

Measured 3d ago against content hash 6153b5de3444, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gr-competitor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/gr-competitor/SKILL.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

gr-competitor — 竞品扫描

什么时候用

  • "帮我分析一下 10 个对手的落地页"
  • "看一下 XX 的定价模式"
  • "这 5 个竞品博客最近 30 天发了什么"
  • "对标一下产品的 features"

底层:actionbook

这个 skill 是 orchestrator —— 真正干活的是 actionbook。 它能:

  • 10x 快(直接调一方 API,跳过 DOM 解析)
  • 省 90% token(返回结构化数据而非 DOM 快照)
  • 30 tab 并发(一次扫完 top 30)

安装 actionbook(首次使用)

# macOS / Linux
npm install -g @actionbookdev/cli

# 或用 npx 临时跑
npx @actionbookdev/cli browser start

Chrome 扩展:从 Chrome Web Store 搜 "Actionbook Extension" 或 https://actionbook.dev

验证可用

actionbook --version  # 应输出 0.x.x
actionbook browser start  # 启动 local browser server

调用流程(4 步)

Step 1:search action manual

对每个目标站点,先查 actionbook 是否已有 manual:

actionbook search "product hunt"
actionbook search "crunchbase"

有 manual → 跳 Step 3 无 manual → Step 2

Step 2:fallback 到通用 extract

actionbook extract <url> \
  --fields "title,h1,intro,pricing_tier,cta_text" \
  --output json

actionbook 会:

  • 用通用 selector 探测
  • 产出 JSON + 可复跑的 Playwright 脚本

Step 3:并发扫描

# 30 个对手一起扫
for url in "${urls[@]}"; do
  actionbook extract "$url" --fields "..." --session scan1 &
done
wait

Step 4:合成报告

Claude 把 30 个 JSON 合成:

  • Title / Tagline 矩阵
  • 定价分层对比
  • 共同 CTA 动词("get started" vs "book demo" vs "try free")
  • 差异点 → 我们可钻的空隙

常用 prompt 模板

模板 1:产品落地页扫描

用 gr-competitor 扫这 10 个对手的落地页,产出一张表:
- 对手名 | tagline | 主 CTA | pricing 起步价 | 主 hero 视觉特征(3 个关键词)

对手:
1. https://...
2. ...

输出:markdown 表格 + 3 条"我们可以差异化"的建议

模板 2:博客内容对比

用 gr-competitor 抓这 5 个对手博客 index 页的 title 列表(top 10 最新):
- https://a.com/blog
- https://b.com/blog
...

然后告诉我:
1. 重叠主题(我们已写过)
2. 他们写我们没写的(我们的选题机会)
3. 他们写得不好的(我们可以超越的)

模板 3:定价页审计

用 gr-competitor 抓这 8 家 SaaS 定价页:
- 分层数量
- 最低价 / 企业价
- Annual 折扣
- Free tier 限制

汇总成对比表,标出"市场中位数"和"我们的相对位置"

级联推荐

  • 发现对手新打法 → gr-blog-post 写回应稿件
  • 发现对手定价漏洞 → gr-b2b-growth 重设我方定价
  • 发现对手被用户吐槽 → gr-user-interview 访谈吐槽用户验证
  • 扫描结果加入监控 → 建 scheduled task 每周重扫

Read the full file on GitHub · 171 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 171 lines · 99 tokens per session scan A 6153b5de3444

Subscribe to this mod's changes

gr-competitor is a skill published in the GitHub repository Gingiris/gingiris-skills (23 stars, last pushed 3mo ago), licensed MIT. It adds 99 tokens to every session and 1,325 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens