Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计提醒

competitive-analysis竞争分析

Agent Skill

competitive-analysis 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

648

周安装

27

GitHub Stars

3

下载量

216
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:competitive-analysis(竞争分析)
来源仓库:https://github.com/oldwinter/skills
仓库路径:skills/competitive-analysis
安装命令:
npx skills add https://github.com/oldwinter/skills --skill competitive-analysis
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/oldwinter/skills --skill competitive-analysis

简介

competitive-analysis 用于查找、检索和筛选相关信息。

  • 适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词快速定位候选结果。
  • 通过 npx skills add 命令从指定仓库安装并使用。
  • 使用前需确认权限范围、维护状态,避免触发联网或文件读写操作。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Competitive Analysis

Scope

Covers

  • Mapping competitive alternatives (status quo, workarounds, analog/non-consumption, direct + indirect competitors)
  • Building a competitor landscape grounded in customer decision criteria
  • Turning analysis into actionable artifacts: positioning hypotheses, win themes, battlecards, and a monitoring plan

When to use

  • “Do a competitive analysis / competitor landscape for our product.”
  • “Why are we losing deals to?”
  • “What are the real alternatives if we didn’t exist?”
  • “Help us differentiate and position vs competitors.”
  • “Create sales battlecards and win/loss takeaways.”

When NOT to use

  • You need market sizing / TAM/SAM/SOM as the primary output (different workflow)
  • You don’t know the target customer, core use case, or the decision this analysis should support
  • You only need a quick list of competitors (no synthesis, no artifacts)
  • You’re seeking confidential or non-public competitor information (do not attempt)

Inputs

Minimum required

  • Product + target customer segment + core use case (what job is being done)
  • The decision to support (e.g., positioning, sales enablement, roadmap bets, pricing, market entry)
  • 3–10 known competitors/alternatives (or “unknown—please map them”)
  • Any available evidence (links, win/loss notes, call transcripts, customer quotes, pricing pages, reviews)
  • Constraints: geography, ICP, price band, compliance/regulation (if relevant), time box

Missing-info strategy

  • Ask up to 5 questions from references/INTAKE.md.
  • If answers aren’t available, proceed with explicit assumptions and label unknowns. Provide 2–3 plausible alternative scopes (narrow vs broad).

Outputs (deliverables)

Produce a Competitive Analysis Pack in Markdown (in-chat; or as files if requested):

  1. Context snapshot (decision, ICP, use case, constraints, time box)
  2. Competitive alternatives map (direct/indirect/status quo/workarounds/analog)
  3. Competitor landscape table (top 5–10) with evidence links + confidence
  4. Customer decision criteria + comparison matrix (customer POV)
  5. Differentiation & positioning hypotheses (why win, why lose, proof points)
  6. Win themes + loss risks (objections, landmines, traps)
  7. Battlecards (3–5 priority competitors)
  8. Monitoring plan (signals, cadence, owners, update triggers)
  9. Risks / Open questions / Next steps (always included)

Templates: references/TEMPLATES.md

Workflow (8 steps)

1) Intake + decision framing

  • Inputs: User context; references/INTAKE.md.
  • Actions: Confirm the decision, ICP, use case, geography, and time box. Define what “good” looks like (who will use this and for what).
  • Outputs: Context snapshot.
  • Checks: A stakeholder can answer: “What decision will this analysis change?”

2) Map competitive alternatives (not just logos)

  • Inputs: Use case + customer job.
  • Actions: List what customers do *instead*: status quo, internal build, manual workaround, analog tools, agencies/outsourcing, and direct/indirect competitors. Identify the “true competitor” for the deal.
  • Outputs: Competitive alternatives map + short notes per alternative.
  • Checks: At least 1–2 non-obvious alternatives appear (workarounds / analog / non-consumption).

3) Select the focus set + collect evidence (time-boxed)

  • Inputs: Alternatives map; available sources.
  • Actions: Pick 5–10 focus alternatives (by frequency/impact). Gather publicly available facts (positioning, features, pricing, distribution, target ICP) and internal learnings (win/loss, sales notes). Track confidence and unknowns.
  • Outputs: Evidence log + initial landscape table.
  • Checks: Each competitor row has at least 2 evidence points (link/quote/data) or is explicitly labeled “low confidence”.

4) Build the comparison from the customer’s perspective

  • Inputs: Focus set + evidence.
  • Actions: Define 6–10 customer decision criteria (JTBD outcomes, constraints, trust, time-to-value, switching cost, price, ecosystem fit). Compare alternatives on criteria and surface “why they win”.
  • Outputs: Decision criteria list + comparison matrix.
  • Checks: Criteria are framed as customer outcomes/risks (not internal feature checklists).

5) Derive differentiation + positioning hypotheses

  • Inputs: Matrix + wins/losses.
  • Actions: Write 2–3 positioning hypotheses: (a) who we’re for, (b) the value we deliver, (c) why we’re different vs the true alternative, (d) proof points, (e) tradeoffs/non-goals.
  • Outputs: Differentiation & positioning section.
  • Checks: Each hypothesis names the competitive alternative it’s positioning against.

6) Translate into win themes + battlecards

  • Inputs: Positioning hypotheses + competitor notes.
  • Actions: Create 3–5 win themes and 3–5 loss risks. Produce battlecards for priority competitors (how to win, landmines, objection handling, traps to avoid).
  • Outputs: Win/loss section + battlecards.
  • Checks: Battlecards contain do/don’t talk tracks and are usable in a live sales call.

7) Recommend actions (product, messaging, GTM)

  • Inputs: Findings.
  • Actions: Propose 5–10 actions: product bets, messaging changes, pricing/packaging, distribution, partnerships, and “stop doing” items. Tie each action to a win theme or loss risk.
  • Outputs: Recommendations list with rationale and owners (if known).
  • Checks: Each recommendation is specific enough to execute next week/month.

8) Monitoring + quality gate + finalize

  • Inputs: Draft pack.
  • Actions: Define monitoring signals, cadence, and update triggers. Run references/CHECKLISTS.md and score with references/RUBRIC.md. Add Risks/Open questions/Next steps.
  • Outputs: Final Competitive Analysis Pack.
  • Checks: Pack is shareable as-is; assumptions and confidence levels are explicit.

Quality gate (required)

Examples

Example 1 (B2B SaaS): “We keep losing deals to Competitor X. Build a competitive alternatives map and a battlecard for X.” Expected: alternatives map (incl. status quo), decision criteria, X battlecard, win themes/loss risks, and a monitoring plan.

Example 2 (Consumer subscription): “We’re repositioning for a new segment. Analyze alternatives and propose 2 positioning hypotheses.” Expected: comparison matrix by customer criteria and two clear positioning options with proof points and tradeoffs.

Boundary example: “List every competitor in our industry worldwide.” Response: narrow scope (ICP, geography, category) and propose a focused set + monitoring plan; otherwise output becomes a low-signal directory of logos.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

35.44%
按下载量换算77

Claude

28.58%
按下载量换算62

Cursor

19.15%
按下载量换算41

Gemini CLI

9.51%
按下载量换算21

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills