MCPInstall

competitive-analysis

Use when performing a structured teardown of a specific competitor's activity system, moat, or vulnerability profile—requires at least one named rival to analyze.

Installs
41
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/joellewis/skill-library --skill competitive-analysis
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads competitive-analysis automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Overview

Competitive analysis is not a list of features; it is a forensic audit of a rival's "Activity System" to find where their internal logic is brittle. This skill prevents the "Arrogance Trap" identified in the GE and Boeing collapses by forcing an evidence-based assessment of moats and vulnerabilities.

Iron Law

NO COMPETITIVE CLAIM WITHOUT EVIDENCE FROM AT LEAST TWO INDEPENDENT SOURCES

Unverified claims about being "10x better" or having "no competitors" are the primary signals of impending strategic failure.

State Machine

digraph competitive_analysis_flow {
    "Start" [shape=doublecircle];
    "Step 1: Activity Mapping" [shape=box];
    "Gate: Moat Audit" [shape=diamond];
    "Step 3: Vulnerability Check" [shape=box];
    "Step 4: Evidence Gate" [shape=diamond];
    "Done" [shape=doublecircle];

    "Start" -> "Step 1: Activity Mapping";
    "Step 1: Activity Mapping" -> "Gate: Moat Audit";
    "Gate: Moat Audit" -> "Step 3: Vulnerability Check" [label="moat verified"];
    "Gate: Moat Audit" -> "Step 1: Activity Mapping" [label="unclear value"];
    "Step 3: Vulnerability Check" -> "Step 4: Evidence Gate";
    "Step 4: Evidence Gate" -> "Done" [label="2+ sources found"];
    "Step 4: Evidence Gate" -> "Step 3: Vulnerability Check" [label="hearsay only"];
}

When to Use This Skill

  • When drafting a PRD or Business Case that claims a "unique advantage."
  • When a new rival enters the market with a "modular" or "platform" approach.
  • When an incumbent appears "invincible" but shows signs of arrogance or bloat.
  • During a "Devil's Advocate" stress test of a proposed strategy.

When NOT to Use This Skill

  • For pure internal process optimization that does not affect the customer.
  • In a "Zero-to-One" phase where no direct competitors exist (use problem-framing instead).

Core Process

Step 1: Map the Activity System

Do not compare features. Compare the system of reinforcing activities. (Source: Lafley, Playing to Win, Ch. 5)

  1. Identify the "Winning Aspiration": Are they playing to win or playing to play?
  2. Deconstruct the Reinforcing Loop: How do their activities (e.g., low cost + high volume + limited SKUs) make it harder for you to copy them without breaking your own model?
  3. Identify the "Limiting Step": What is the one thing they cannot change without destroying their current profitability?

Step 2: Perform the Moat Audit

Assess whether the competitor (or you) has a durable power source. Use Helmer's 7 Powers as the primary taxonomy, with Thiel's 10x test as the threshold bar. (Source: Helmer, 7 Powers; Thiel, Zero to One, Ch. 5)

  1. Scale Economies: Does unit cost decline with volume in a way that locks out smaller rivals?
  2. Network Economies: Does the product get more valuable with each user, creating a flywheel?
  3. Counter-Positioning: Would responding to this competitor require us to cannibalize our own business model?
  4. Switching Costs: Are customers locked in by financial, procedural, or data-migration costs?
  5. Branding: Does the brand command a premium that persists when features are matched?
  6. Cornered Resource: Do they have preferential access to talent, IP, data, or regulatory position?
  7. Process Power: Do embedded organizational processes deliver superior outcomes that are opaque to outsiders?

For each power source identified, apply Thiel's threshold: is it 10x better on a dimension that matters to the customer, or is it a marginal advantage that can be competed away?

Step 3: Audit the "Operating System"

Assess the rival's execution discipline. (Source: Davis, Lessons from the Titans, Ch. 12)

  1. The Arrogance Check: Is the rival focused on "Big Ideas" and "Celebrity CEOs" (Immelt-era GE) or "Continuous Improvement" (Welch-era GE)?
  2. The 1% Trap: Have they defined the market so broadly (e.g., "1% of $100B") that they have no actual foothold?
  3. The Capital Allocation Test: Are they overpaying for "hot" assets or investing in the core? (Source: Gramm, Dear Chairman)

Step 4: Verify with Independent Evidence (The Iron Law)

For every claim (e.g., "We are faster"), you must cite:

  1. Source A: External data (e.g., user reviews, teardowns, financial filings).
  2. Source B: Independent verification (e.g., customer interviews, third-party benchmarks).

Cross-Skill Invocations

  • REQUIRED SUB-SKILL: problem-framing — You cannot analyze competitors without knowing the "Job-to-be-Done."
  • RECOMMENDED SUB-SKILL: devils-advocate — Use this to find the flaws in your own competitive claims.
  • RECOMMENDED SUB-SKILL: strategy-clarity — To ensure your "How to Win" is distinct from the rival's activity system.

Rationalization Table

ThoughtReality
"We have no competitors."You are defining the market too narrowly. Anything the customer uses to solve the problem is a competitor.
"Our tech is 10x better."Unless it's 10x better on an unmeasurable consumer attribute (UX), it's a "modular" target.
"They are just a copycat.""Me-too" competitors with lower overhead or a "modular" stack often win on price (Modular Disruption).
"We don't need evidence for common knowledge."Common knowledge is often "arrogance in disguise." Verification is the only defense.
"They can't respond without destroying their business."Verify the direction: Counter-Positioning only applies when their response requires self-harm. If you can't respond to them, you're the one being Counter-Positioned.
"We have no competitors."Anything the customer uses to solve the job — including doing nothing — is a competitor. You defined the market wrong. (Source: Thiel, Zero to One, Ch. 5)

Red Flags

These thoughts mean STOP — you are about to shortcut:

  • "They are too old/slow to catch us." → Arrogance (Source: Boeing 737MAX failure).
  • "We have 1% of a massive market." → The 1% Trap (Source: Thiel).
  • "Our brand is our moat." → Branding is a result of a system, not a standalone moat (Source: Lafley).
  • "Their moat is just branding." → Branding without an underlying power source (Scale, Network, Switching Costs) is a logo, not a moat. (Source: Helmer, 7 Powers, Ch. 8)
  • "We have switching costs, they can't leave." → Competitors invest in migration tools to erode switching costs. Assess where switching costs will be in 2 years, not where they are today. (Source: Helmer, 7 Powers, Ch. 6)
  • "We can't figure out how they do it." → If results consistently exceed what visible inputs explain, suspect Process Power. Flag it as an unknown rather than dismissing it. (Source: Helmer, 7 Powers, Ch. 9)

Diagnostic Checklist

  • Have we mapped the competitor's reinforcing activities, not just their features?
  • Have we identified which of the 7 Powers the competitor holds (if any)?
  • Is our claimed advantage verified by two independent, non-internal sources?
  • Have we checked whether our advantage is a durable power source or a temporary feature lead?
  • Have we identified the "Job-to-be-Done" that the competitor is solving?
  • Did we check for Counter-Positioning in both directions (theirs against us AND ours against them)?
  • Have we identified the "Limiting Step" in the competitor's activity system?

Sources

  • Lafley, Playing to Win, Ch. 5 — Activity Systems and Capability Gaps.
  • Thiel, Zero to One, Ch. 5 — Monopoly Characteristics and Power Law.
  • Kaufman, The Personal MBA, Ch. 3 — Competitive Forces and Substitutes.
  • Davis, Lessons from the Titans, Ch. 12 — Industrial Business Systems and Arrogance.
  • Gramm, Dear Chairman, Ch. 1 & 5 — Intrinsic Value and Ownership Boards.
  • Helmer, 7 Powers, Ch. 3, 6, 8, 9 — Counter-Positioning, Switching Costs, Branding, Process Power.
  • Stratechery, "Aggregation Theory" — Demand aggregation vs. Supply control.

FAQ

What does the competitive-analysis skill do?

Use when performing a structured teardown of a specific competitor's activity system, moat, or vulnerability profile—requires at least one named rival to analyze.

How do I install competitive-analysis?

Run npx skills add https://github.com/joellewis/skill-library --skill competitive-analysis in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/competitive-analysis/ (personal) or .claude/skills/competitive-analysis/ (project).

Which AI agents can use competitive-analysis?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is competitive-analysis safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains competitive-analysis?

It is published by joellewis in joellewis/skill-library. It has 41 recorded installs.

More from joellewis/skill-library

View all →

fiction-architect

joellewis/skill-library

Open the skill to read its SKILL.md instructions.

55 installs

dialogue-craft

joellewis/skill-library

Open the skill to read its SKILL.md instructions.

53 installs

world-building-logic

joellewis/skill-library

Open the skill to read its SKILL.md instructions.

53 installs

character-vulnerability

joellewis/skill-library

Open the skill to read its SKILL.md instructions.

Security47 installs

one-pager

joellewis/skill-library

Open the skill to read its SKILL.md instructions.

47 installs

problem-framing

joellewis/skill-library

Use when beginning analytical or strategic tasks, facing undefined problems, or facing analysis paralysis—requires explicit problem definition before proceeding.

47 installs

Popular security skills

View category →

azure-compliance

microsoft/azure-skills

Run Azure compliance and security audits with azqr plus Key Vault expiration checks. Covers best-practice assessment, resource review, policy/compliance validation, and security posture checks. WHEN: compliance scan, security audit, BEFORE running azqr (compliance cli tool), Azure best practices, Key Vault expiration check, expired certificates, expiring secrets, orphaned resources, compliance assessment.

OfficialSecurity567K installs

minimal-run-and-audit

lllllllama/rigorpilot-skills

Rigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized reprooutputs/ files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target selection, hidden scientific-meaning changes, or end-to-end orchestration by itself.

Security477.4K installs

seo-audit

coreyhaines31/marketingskills

When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," "SEO health check," "my traffic dropped," "lost rankings," "not showing up in Google," "site isn't ranking," "Google update hit me," "page speed," "core web vitals," "crawl errors," "indexing issues," "stuck on page 2," "striking distance keywords," "title tag rewrite," "low CTR," "local SEO," "Google Business Profile," or "map pack." Use this even if the user just says something vague like "my SEO is bad" or "help with SEO" — start with an audit. For building pages at scale to target keywords, see programmatic-seo. For adding structured data, see schema. For AI search optimization, see ai-seo.

Security238.7K installs

firebase-security-rules-auditor

firebase/agent-skills

Audits Firebase (Firestore, Cloud Storage) security rules for vulnerabilities, privilege escalation, role bypasses, create vs update inconsistencies, resource exhaustion, type safety, size limits, and hasOnly ownership checks. Use when auditing/reviewing rules, running red-team rule assessments, or scoring against auditor checklists. Don't use for Firebase CLI (login, deploy), Auth, Crashlytics, Remote Config, or database queries.

OfficialSecurity139.1K installs

audit

pbakaus/impeccable

Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality review.

Security81.9K installs

competitors

coreyhaines31/marketingskills

When the user wants to create competitor comparison or alternative pages for SEO and buyer-facing use. Also use when the user mentions 'alternative page,' 'vs page,' 'competitor comparison,' 'comparison page,' '[Product] vs [Product],' '[Product] alternative,' 'competitive landing pages,' 'how do we compare to X,' 'competitor teardown,' 'audit our competitor pages,' 'are our comparison pages out of date,' or 'competitive asset audit.' Use this for any content that positions your product against competitors. Covers four formats: singular alternative, plural alternatives, you vs competitor, and competitor vs competitor. For auditing existing claims (not researching competitors from scratch, which is competitor-profiling; not technical SEO on these pages, which is seo-audit), use the asset audit here. For internal battle cards and sales-specific competitor docs, see sales-enablement.

Security79.3K installs