competitive-analysis
Skill82 starsChanged yesterdayMITView on GitHub
对一个产品想法或现有产品做竞品与开源调研:GitHub 多关键词交叉,加 Product Hunt、AlternativeTo 等商业产品,加间接竞品,输出带 A/B/C 证据分级、待核实清单和"确认对标集合"的竞品分析报告,AI 轨道时含评测种子,支持快速、标准、深度三档。当用户说"帮我做个竞品分析"、"调研一下 X 有哪些同类产品"、"这个想法有没有人做过"、"帮我看看竞品或对标"时使用。正处于 Vibe_helper 全流程时按该流程走,无需单独触发。English: competitive and open-source research across GitHub, commercial directories and indirect alternatives, producing an evidence-graded report with a user-confirmed benchmark set and evaluation seeds for AI products. Use when the user asks for a "competitive analysis", "who else builds this", or "look into rivals and benchmarks"; inside the Vibe_helper pipeline it runs as part of that flow.
55 other projects use a version of this.
Adopted by
Most recently taken up by
- miguelclavel/ux-research-skillstheir own version, first seen Nov 8, 2026
- insight68/Skillstheir own version, first seen Nov 8, 2026
- AgnesAI-Labs/agnet-skills-cntheir own version, first seen Nov 1, 2026
- jaskirat1616/grok-skillstheir own version, first seen Nov 1, 2026
- codeApe-7/ai-agent-workflowGrouptheir own version, first seen Nov 1, 2026
- vijaysuperpositionist/skillstheir own version, first seen Nov 1, 2026
Used with
Projects with it also use usability-test-plan, onboarding-flow and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
launchapp-devSkillusability-test-plan
Design a usability test plan with tasks, success metrics, participant criteria, and facilitation guide. Use when planning moderated or unmoderated usability testing sessions.
Also in 3 projects that use this
Dragoon0xSkillonboarding-flow
Design first-run experiences that create the aha moment fast. Reduces time-to-value by sequencing actions, progressive disclosure, and contextual guidance. Use when building signup flows, product tours, or empty states.
Also in 3 projects that use this
shawnpangSkilllead-scoring
When a founder needs to qualify inbound leads, define their ICP, build a lead scoring model, set MQL criteria, or route prospects through pipeline stages. Activate when the user mentions lead scoring, ICP, MQL, SQL, lead qualification, inbound leads, or pipeline design.
Also in 3 projects that use this
nicepkgSkilluser-research-synthesis
Synthesize qualitative and quantitative user research into structured insights and opportunity areas. Use when analyzing interview notes, survey responses, support tickets, or behavioral data to identify themes, build personas, or prioritize opportunities.
Also in 4 projects that use this
JayRHaSkilllanguage-tutor
Acts as a personalized foreign-language tutor — assessing level, running graded conversation practice, teaching vocabulary and grammar in context, correcting errors gently, and building a spaced-repetition study plan toward a concrete goal. Use this skill when a user asks to "help me learn/practice X language", "be my language tutor", "practice Spanish/French/German conversation", "correct my writing in X", "teach me phrases for travel", or wants a structured language-learning plan.
Also in 3 projects that use this
walternateSkillgo-to-market
Build a go-to-market (GTM) strategy for launching a product or entering a new market. Use when planning how to reach customers, position your product, choose channels, set pricing, and execute launch. Covers market entry strategy, customer segmentation, positioning, channel strategy, and GTM execution plan. Trigger on "go-to-market", "GTM strategy", "market entry", "launch strategy", "how to reach customers", "GTM plan".
Also in 3 projects that use this
Other versions55 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 55
- anthropics/financial-services-plugins★ 41ksame name
- anthropics/financial-services★ 41ksame name
- claude-office-skills/skills★ 433same name
- shawnpang/startup-founder-skills★ 331same name
- mverab/eGEOagents★ 218same name
- Fokkyp/claude-skills★ 211same name
- aakashg/pm-claude-code-setup★ 152same name
- nahid-sparktales/agent-dispatcher★ 59same name
- agencia-conversion/agentic-seo-skills★ 51same name
- launchapp-dev/animus-cli★ 39same name
45 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository5 other files it gives its agents.
- product-briefSkill
- requirements-layeringSkill
- tech-frameworkSkill
- user-voiceSkill
- Vibe_helperSkill
The file
Files
Competitive Analysis:竞品与开源调研
语言规则:全程跟随用户语言。汇报与 03-竞品分析.md 正文用用户的语言;编号文件名与小节标题保持模板原样。
回答三个问题:这个赛道里有什么?它们做得怎么样?我们的位置在哪? 产出一份每个论断都有证据等级、每个链接都真实打开过的竞品分析报告。
在 Vibe_helper 全流程中对应 Stage 3;单独使用时本 skill 独立完成。
输入
- 最好有
02-brief.md,或一段产品描述:做什么、给谁、核心功能;已有00-状态.md时先读它的定位与约束,避免重问用户 - 什么都没有则先问 3 个问题:产品一句话定位、目标用户、核心功能。不要求完整 Brief,拿到就能开工
- 用户点名要查的竞品优先深查,其余自己补
深度档位,开场确认,默认标准
| 档位 | 竞品数 | 范围 |
| 快速 | ~5 | GitHub top 3 加商业 2,够回答"有没有人做过" |
| 标准,默认 | 10–15 | 直接竞品、开源项目加间接竞品 |
| 深度 | 20+ | 标准范围,加间接竞品专章、中英双语检索、定价对比 |
步骤
- 多组搜索:策略见
references/competitive-analysis.md,覆盖直接关键词、GitHub 按 stars 浏览、Product Hunt 与 AlternativeTo、awesome 列表、间接竞品即解决同一问题的不同路径。不要只搜一次 - 每个竞品实际打开主页、README、官网看,当场核对 stars 与最近 commit。记录字段与好、坏记录对照见同文件
- 写报告
03-竞品分析.md:第一屏决策面板,然后概览、直接竞品、开源参考、间接竞品、对本产品的启发含可借用、要避的坑、差异化位置,再加评测种子,AI 轨道时,竞品被骂的失败模式即未来评测集的对抗用例类别,最后待核实清单,盲区与 C 级推测各附去向 - 对标选择点:报告落盘不等于调研结束。向用户汇报:一,参照竞品总表,真实打开过的;二,重点对标推荐 2–3 个,理由只能是用户重叠最高、形态最接近、最值得借鉴,另列不推荐及原因,推荐主要依据含 C 级必须声明,此为信心洗白禁令;三,问用户:"你有没有要补的竞品?想换重点对标的直接说;不想管就说'你定'。"
- 用户增删则补查新增竞品、更新报告再确认一轮;确认后把最终集合写进"确认对标集合"小节。这是后续功能对比和差异化的锚
证据分级与幻觉显性化纪律
全文遵守 references/anti-hallucination.md:每条论断标 A 即有证据、B 即证据加推理链、C 即模型推测并进待核实清单;链接必须本轮真实打开,落盘前随机抽 5 个溯源复核;数字当场核对,取不到写"未获取";C 级不超过三分之一;禁止自我评价词;末尾强制"待核实清单"。幻觉不可能为零,猜测不是违规,藏起来才是;编造链接或数据则该段作废重做。
Common Pitfalls
- 搜索摘要当看过:没打开页面的竞品不许进"参照竞品总表"
- stars 与维护状态凭印象填:当场核对,取不到就写"未获取"
- 堆数量显得勤奋:30 个只看过标题的竞品不如 10 个真打开看透的
- 跳过对标选择点:报告落盘就直接结束。没有"确认对标集合"等于没交货
- 只查直接竞品:用户现在拿什么凑合,如 Excel、微信群、人肉,往往才是真对手
- 只搜中文或只搜英文:两边生态不同,交叉才全,深度档强制双语
- AI 轨道漏标评测种子:竞品被骂的失败模式是评测集对抗用例的最佳来源,漏了则 Stage 6 评测方案只能靠想象
- 修改已确认报告不更新版本:补查或修改 03 必须版本加 1 并加变更行,版本头规则见报告模板顶部
- 语言不跟用户:调研汇报与文档正文要用用户的语言
输出物
03-竞品分析.md,带版本头;含"确认对标集合"小节,用户拍板后
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

