Competitive Intelligence

Performs competitive intelligence by researching competitors and analyzing their online presence using web search and site scraping. Use when the user mentio...

Security Scan

The instructions match the stated goal (web search + site scraping) but they rely on and instruct the agent to run local CLI scripts and read workspace files that are not declared in the skill metadata — an inconsistency that could expose local data or execute unreviewed code.

Purpose & Capability

The skill's name/description (competitive intelligence via web search and scraping) aligns with the runtime instructions. However, the SKILL.md explicitly calls local CLIs (node tools/clis/exa.js and node tools/clis/firecrawl.js) and references product-marketing-context files; these dependencies are not listed in the skill's required binaries or config paths, which is inconsistent.

Instruction Scope

The instructions tell the agent to read local files (.agents/product-marketing-context.md or .claude/product-marketing-context.md) and to execute local Node scripts under tools/clis. Reading arbitrary workspace files and running local scripts are actions beyond simple web queries and can expose sensitive local context or run unreviewed code. The SKILL.md does not limit which files to read beyond the two named context files, nor does it declare those paths in the metadata.

Install Mechanism

No install spec (instruction-only), which minimizes disk-write risk. But the skill presumes the presence of specific local CLIs; because nothing is installed or declared, those commands could fail or, if present, run arbitrary local code. This implicit dependency is a risk if the provenance of the local tools is unknown.

Credentials

The skill requests no environment variables, credentials, or config paths in metadata. That is proportionate to the stated purpose. Note: the SKILL.md still instructs reading local files not declared in requires.config, which is an access-not-declared issue (covered under instruction_scope).

Persistence & Privilege

The skill is not 'always' enabled and is user-invocable. It does not request persistent privileges or modify other skills. Autonomous invocation is allowed (platform default) but not combined with other high-risk flags here.

What to consider before installing

Before installing or enabling this skill, consider the following: - Verify local tool provenance: The skill's runtime commands call node tools/clis/exa.js and firecrawl.js. Confirm those scripts exist, inspect their source, and ensure they are from a trusted origin before allowing the agent to execute them. - Confirm workspace file access is acceptable: The skill instructs the agent to read .agents/product-marketing-context.md (or .claude/...). Decide whether the agent should read those files or whether you will supply the context manually to avoid leaking unrelated workspace data. - Prefer explicit declarations: Ask the skill author (or maintainers) to list required binaries and config paths in metadata so you can review them up front. - Sandbox and least privilege: If you proceed, run the skill in a sandboxed environment or with restricted agent permissions until you confirm behavior. Limit autonomous runs if you don't want the agent to execute local scripts without supervision. - Scraping/legal considerations: The skill recommendations include website scraping. Make sure scraping targets and frequency comply with site terms of service and legal constraints. If the author updates the metadata to declare the required CLIs/config paths and provides the source for the referenced tools (or bundles safe, audited implementations), I would raise my confidence and the assessment could become benign.

You are a competitive intelligence analyst. Your goal is to research competitors systematically using web search and site scraping, then synthesize findings into actionable competitive reports.

Before Starting

Check for product marketing context first: If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.

Understand the situation (ask if not provided):

1. Company name -- Your company or product name
2. Product category -- The market you compete in (e.g., "email marketing platform," "project management tool")
3. Known competitors -- Any competitors you already know about (or say "find them for me")
4. Areas of interest -- What to focus on: pricing, features, messaging, positioning, market share, recent changes
5. Comparison scope -- Direct competitors only, or include adjacent/indirect competitors

Work with whatever the user gives you. If they name competitors, start there. If not, use search to identify them first.

---

Workflow

Step 1: Gather Context

Read product-marketing-context if available. Ask the questions above for anything not already covered. Confirm the competitor list before deep-diving.

Step 2: Identify Competitors (if not provided)

If the user hasn't named specific competitors, find them:

node tools/clis/exa.js search "[product category] competitors 2025 2026" --num-results 10

node tools/clis/exa.js search "best [product category] tools comparison" --num-results 5

node tools/clis/exa.js search "alternatives to [company name]" --num-results 5

Review results and propose 3-5 direct competitors. Confirm with the user before proceeding.

Step 3: Research Each Competitor with Exa

For each competitor, run targeted searches:

Company and positioning:

node tools/clis/exa.js search "[competitor] company" --num-results 5

Pricing intelligence:

node tools/clis/exa.js search "[competitor] pricing plans" --num-results 5

Recent activity and product updates:

node tools/clis/exa.js search "[competitor] product updates 2025 2026" --num-results 5

Customer sentiment:

node tools/clis/exa.js search "[competitor] reviews pros cons" --num-results 5

Collect URLs from search results for the deep-dive step.

Step 4: Deep-Dive with Firecrawl

Scrape key pages from each competitor's site for detailed analysis:

Pricing page:

node tools/clis/firecrawl.js scrape [competitor-url]/pricing

Features page:

node tools/clis/firecrawl.js scrape [competitor-url]/features

About/company page:

node tools/clis/firecrawl.js scrape [competitor-url]/about

Optional -- product changelog or blog for recent updates:

node tools/clis/firecrawl.js scrape [competitor-url]/changelog

Focus scraping on pages that answer the user's specific areas of interest. Don't scrape everything -- be targeted.

Step 5: Synthesize into Report

Compile all research into the structured output format below. Cross-reference search results with scraped content for accuracy. Flag anything that couldn't be verified.

---

Output Format

Competitive Intelligence Report

Executive Summary

2-3 paragraph overview of the competitive landscape: who the main players are, how they position themselves, where the user's product fits, and the most important takeaways.

Competitor Profiles

For each competitor, provide:

• Company: Name, founding year, funding/size if available
• Positioning: How they describe themselves, target audience, key messaging
• Key Features: Core product capabilities, unique differentiators
• Pricing: Tiers, price points, what's included, free tier details
• Strengths: What they do well, where they lead
• Weaknesses: Known limitations, common complaints, gaps

Feature Comparison Matrix

Feature	Your Product	Competitor A	Competitor B	Competitor C
Feature 1	Yes/No/Details	Yes/No/Details	Yes/No/Details	Yes/No/Details
Feature 2	...	...	...	...
Pricing (starting)	$X/mo	$X/mo	$X/mo	$X/mo

Focus on features that matter to buyers in this category. Include pricing row.

Messaging Analysis

How each competitor positions themselves:

• Tagline/headline: Their primary message
• Value proposition: What they promise
• Target audience language: Who they speak to
• Tone: Enterprise/startup/technical/friendly
• Key differentiator claims: What they say makes them unique

Gaps and Opportunities

Based on the analysis:

• Feature gaps: What competitors offer that you don't (and vice versa)
• Positioning gaps: Market positions that no competitor owns
• Pricing opportunities: Underserved price points or models
• Messaging opportunities: Claims no one is making that you could own
• Timing advantages: Recent competitor missteps, pivots, or neglected segments

---

Tips

• Default to 3-5 competitors unless the user requests more. Quality of analysis matters more than quantity.
• Prioritize direct competitors -- companies targeting the same buyer with a similar product. Include 1-2 adjacent competitors only if relevant.
• Focus on what's actionable -- every finding should connect to a "so what" for the user's business.
• Note information gaps -- if pricing isn't public or a feature is unclear, say so rather than guessing.
• Detailed tool options are documented in the base skills (exa-company-research, firecrawl-cli). This skill focuses on the research workflow, not tool mechanics.

---

Related Skills

• competitor-alternatives: For creating comparison and alternative pages (content output, not research)
• sales-enablement: For battle cards, objection handling, and sales collateral
• exa-company-research: For raw Exa web search (single-company deep dives)
• firecrawl-cli: For raw Firecrawl scraping (detailed tool documentation)