competitive-analysis

competitive-analysis is a skill for Claude Code, Codex from aakashg/pm-claude-code-setup. It costs 0 tokens per session (510 once invoked), scanned A, original, MIT.

A guided process for comparing your product with a competitor. It examines what the competitor built, what works well, what is weak, and what those findings mean for your product.

In plain words
What is it for?
Analyzing a competitor's features, target users, advantages, gaps, and possible ideas to copy, avoid, or improve.
Why use it?
It turns a vague competitor review into specific observations and decisions. It also asks for the product and feature being compared before starting.

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/aakashg/pm-claude-code-setup/competitive-analysis
Any agent
npx skills add aakashg/pm-claude-code-setup --skill competitive-analysis
Clone the repo
git clone --depth 1 https://github.com/aakashg/pm-claude-code-setup

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 competitive-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/aakashg/pm-claude-code-setup/competitive-analysis.svg)](https://agentmods.dev/skills/aakashg/pm-claude-code-setup/competitive-analysis)
Your own site
<a href="https://agentmods.dev/skills/aakashg/pm-claude-code-setup/competitive-analysis"><img src="https://agentmods.dev/badge/skills/aakashg/pm-claude-code-setup/competitive-analysis.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 510 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 $0.00000 $0.00510
Opus 5 $0.00000 $0.00255
Sonnet 5 $0.00000 $0.00102
Haiku 4.5 $0.00000 $0.00051

Measured 5d ago against content hash 8a13dee54949, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

competitive-analysis 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 5d 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.

.claude/skills/competitive-analysis/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Competitive Analysis

Trigger

Activate on "analyze competitor", "competitive analysis", "compare us to [company]".

Behavior

Step 1: Get Context

Ask:

  1. Which competitor?
  2. Which product or feature to analyze?
  3. What's our product for comparison?

Step 2: Analyze

What They Built

  • Core functionality
  • Target user
  • Key differentiator

What's Smart

  • 3 decisions they nailed and why

What's Weak

  • 3 gaps or missed opportunities

Implications for Us

  • What to copy, what to avoid, where to differentiate

Example

Bad analysis (vague, no evidence):

What's Smart:
- They have a good product
- Nice onboarding
- Growing fast

What's Weak:
- Some features are missing
- Could be cheaper

Good analysis (specific, actionable):

What's Smart:
1. Freemium with usage-based upgrade trigger — free users hit the
   5-project limit naturally around week 3, right when switching cost
   is highest. Conversion to paid: ~8% (industry avg: 3-5%).
2. API-first architecture — 400+ integrations in marketplace. This
   creates lock-in that pure UX improvements can't match.
3. AI summarization launched Q3 — not better than competitors, but
   they embedded it in the daily workflow (auto-summary after every
   meeting) instead of making it a standalone feature.

What's Weak:
1. Enterprise pricing is opaque — requires "contact sales" for teams
   over 50. Mid-market buyers (our sweet spot) hate this. Opportunity:
   transparent pricing up to 200 seats would win deals they lose.
2. Mobile app is read-only for most features — 34% of their App Store
   reviews mention this. Their mobile MAU/DAU ratio is 0.3 vs. 0.6 on
   desktop. Opportunity: mobile-first editing.
3. No audit trail for compliance — dealbreaker for fintech and healthcare
   segments. They lose these verticals entirely.

Rules

  • Be specific. "Great UX" is useless. Name the interaction that works and why.
  • Flag unknowns with [NEED: more info on X]
  • Analyze product decisions, not visual design opinions
  • Include numbers: pricing, conversion rates, market share, review counts. Data beats opinion.

Read the full file on GitHub · 72 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. 5d ago First seen · 72 lines · 0 tokens per session scan A 8a13dee54949

Subscribe to this mod's changes

competitive-analysis is a skill published in the GitHub repository aakashg/pm-claude-code-setup (152 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 510 tokens. 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.