SkillAgentSearch skills...

competitor-analysis

Competitor research and intelligence skill. Takes a user's company (with optional seed competitor URLs), auto-discovers additional competitors via Browserbase Search API, deeply researches each using a 4-lane pattern (marketing surface, external signal, public benchmarks, strategic diff vs the user'…

Install / Use

npx skills add browserbase/skills --skill competitor-analysis

Installs into whichever agent you are using.

About this skill
πŸ“„

SKILL.md

Installable skill definition

Quality Score

95/100

Category

Marketing

Supported Platforms

Universal

Our assessment of competitor-analysis

competitor-analysis scores 95/100 on our quality scale, 81st of 642 Marketing skills we index (top 13%).

Its SKILL.md is 31 KB long, well organised into 18 sections with 11 code examples: a thorough specification that gives an agent plenty to work with.

With 3,731 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
30/30
Structure
20/20
Description
15/15
Adoption
15/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so competitor-analysis is actively maintained.
  • Our last check on 2026-11-16 found the source still online.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 88/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit β€” read the skill file before letting an agent act on it.

Safety scan

Review

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review judged it risky: The skill instructs the agent to permanently disable future permission prompts by adding broad Bash patterns like "Bash(browse:*)", "Bash(bunx:*)", "Bash(node:*)", and "Bash(rm:*)" to ~/.claude/settings.json under permissions.allow.

AI review: risky

  • The skill instructs the agent to permanently disable future permission prompts by adding broad Bash patterns like "Bash(browse:*)", "Bash(bunx:*)", "Bash(node:*)", and "Bash(rm:*)" to ~/.claude/settings.json under permissions.allow.
  • It tells the agent to select "Yes, and don't ask again" for browse cloud fetch/search and other Bash commands, explicitly minimizing permission prompts.
  • While the overall purpose (competitor research via Browserbase) is legitimate, these instructions meaningfully weaken the agent's safeguards by auto-approving a wide set of shell operations.

AI review by kimi-k2.7-code on 2026-09-29. Automated pattern scan on 2026-09-29. It catches known dangerous patterns, not every risk β€” read a skill before letting an agent act on it.

competitor-analysis compared with similar skills

All 4 of these similar skills score higher than competitor-analysis; compare them before choosing.

SkillScoreStarsUpdatedFormat
competitor-analysis (this skill)by browserbase953.7k2mo agoSKILL.md
Agent-Reachby Panniantong100112.3k8d agoCLAUDE.md
headroomby headroomlabs-ai10079.8ktodayCLAUDE.md
Scraplingby D4Vinci100103.6k2d agoMCP Server
crawl4aiby unclecode10087.4k3d agoMCP Server

Frequently asked questions

How do I install competitor-analysis?
Run npx skills add browserbase/skills --skill competitor-analysis. The install tabs above show the steps for each supported agent.
Which AI agents does competitor-analysis work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is competitor-analysis safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review judged it risky: The skill instructs the agent to permanently disable future permission prompts by adding broad Bash patterns like "Bash(browse:*)", "Bash(bunx:*)", "Bash(node:*)", and "Bash(rm:*)" to ~/.claude/settings.json under permissions.allow. It declares no license and scores 88/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is competitor-analysis still maintained?
The repository was last updated about 2 months ago, so competitor-analysis is actively maintained.

name: competitor-analysis description: | Competitor research and intelligence skill. Takes a user's company (with optional seed competitor URLs), auto-discovers additional competitors via Browserbase Search API, deeply researches each using a 4-lane pattern (marketing surface, external signal, public benchmarks, strategic diff vs the user's company), and compiles the results into an HTML report with four views: overview, per-competitor deep dive, side-by-side feature/pricing matrix, and a chronological mentions feed (news, reviews, social, comparison pages, and public benchmarks). Use when the user wants to: (1) analyze competitors, (2) build a competitive matrix, (3) extract competitor pricing / features, (4) find comparison pages and online mentions of competitors, (5) surface public benchmarks. Triggers: "competitor analysis", "analyze competitors", "competitive intel", "competitor research", "competitor pricing", "feature comparison", "price comparison", "find comparisons", "who's comparing us", "competitor mentions", "competitor benchmarks". license: MIT compatibility: Requires the browse CLI (npm install -g browse) and BROWSERBASE_API_KEY env var allowed-tools: Bash Agent AskUserQuestion metadata: author: browserbase version: "0.2.0"

Competitor Analysis

Analyze a user's competitors. Uses Browserbase Search API for discovery and a 4-lane Plan→Research→Synthesize pattern for enrichment — outputting an HTML report with overview, per-competitor deep dives, a side-by-side feature/pricing matrix, and a chronological mentions feed.

Required: BROWSERBASE_API_KEY env var and the browse CLI installed (npm install -g browse).

First-run setup: On the first run you'll be prompted to approve browse cloud fetch, browse cloud search, cat, mkdir, sed, etc. Select "Yes, and don't ask again for: browse cloud fetch:*" (or equivalent) for each. To permanently approve, add these to your ~/.claude/settings.json under permissions.allow:

"Bash(browse:*)", "Bash(bunx:*)", "Bash(bun:*)", "Bash(node:*)",
"Bash(cat:*)", "Bash(mkdir:*)", "Bash(sed:*)", "Bash(head:*)", "Bash(tr:*)", "Bash(rm:*)"

Path rules: Always use full literal paths in Bash β€” NOT ~ or $HOME. Resolve the home directory once and use it everywhere. When building subagent prompts, replace {SKILL_DIR} with the full literal path.

Output directory: All output goes to ~/Desktop/{company_slug}_competitors_{YYYY-MM-DD}/. This directory contains one .md file per competitor plus the generated HTML views and CSV.

CRITICAL β€” Tool restrictions (applies to main agent AND all subagents):

  • All web searches: use browse cloud search. NEVER WebSearch.
  • All page fetches: use browse cloud fetch --allow-redirects (returns markdown by default; add --format raw if you need the original HTML, then pipe through sed ... | tr -s ' \n' to extract text). NEVER WebFetch. 1 MB response limit β€” fall back to browse get markdown (after browse open <url> --remote) for JS-heavy pages.
  • All research output: subagents write one markdown file per competitor to {OUTPUT_DIR}/{competitor-slug}.md using bash heredoc. NEVER use the Write tool or python3 -c. See references/example-research.md for the file format.
  • Report compilation: use node {SKILL_DIR}/scripts/compile_report.mjs {OUTPUT_DIR} --user-company "{user_company}" --open β€” generates index.html, competitors/*.html, matrix.html, mentions.html, results.csv in one step and opens overview.
  • URL deduplication: node {SKILL_DIR}/scripts/list_urls.mjs /tmp --prefix competitor.
  • Subagents must use ONLY the Bash tool.
  • Main agent NEVER reads raw discovery JSON batch files.

CRITICAL β€” Minimize permission prompts:

  • Subagents MUST batch ALL file writes into a SINGLE Bash call using chained heredocs.
  • Batch ALL searches and ALL fetches into single Bash calls via && chaining.

Pipeline Overview

Follow these 8 steps in order. Do not skip or reorder.

  1. User Company Research β€” Deeply understand the user's company, produce precise_category + category_include_keywords + exclusion_list
  2. Depth Mode + Seed Input β€” Choose depth, accept optional seed competitor URLs
  3. Discovery (3 parallel waves) β€” Wave A (alternatives), Wave B (precise category), Wave C (comparison-page graph via "X vs Y" title parsing)
  4. Gate β€” scripts/gate_candidates.mjs fetches each candidate's hero text (via browse cloud fetch) and drops wrong-category URLs
  5. Confirm enrichment set with the user β€” Present PASS / UNKNOWN / rejected-brand-matches via AskUserQuestion. User ticks the real ones, adds any the discovery missed. Skipping this step is wasteful because enrichment is expensive (25 subagents Γ— depth budget) and the gate is imperfect (JS-heavy homepages, Cloudflare challenges, semantic-variant taglines)
  6. Deep Enrichment (5 subagents per competitor in deep/deeper modes) β€” Marketing, Discussion, Social, News, Technical β€” each lane a separate subagent writing to partials/; then merge_partials.mjs consolidates. In deep/deeper modes, Step 5d adds a 6th Battle Card synthesis lane AFTER Step 5c fact-check completes β€” produces per-competitor Landmines / Objection Handlers / Talk Tracks grounded in cited evidence.
  7. Screenshots β€” capture_screenshots.mjs via the browse CLI captures a 1280Γ—800 homepage hero per competitor
  8. HTML Report β€” Overview + per-competitor (with embedded hero screenshot + Battle Card card) + matrix + mentions views

Step 0: Setup Output Directory

OUTPUT_DIR=~/Desktop/{company_slug}_competitors_{YYYY-MM-DD}
mkdir -p "$OUTPUT_DIR"

Replace {company_slug} with the user's company name (lowercase, hyphenated) and {YYYY-MM-DD} with today's date. Pass {OUTPUT_DIR} as a full literal path to every subagent.

Clean up discovery batch files from prior runs:

rm -f /tmp/competitor_discovery_batch_*.json

Re-runs must start from a clean $OUTPUT_DIR. compile_report.mjs ingests every {slug}.md in the directory, and merge_partials.mjs only overwrites the slugs in the current set β€” it never deletes ones dropped from a new enrichment set. Since the directory is keyed by date, a same-day re-run with a different competitor set would leave stale competitors in the overview, matrix, CSV, and screenshots. Either use a fresh directory or clear the prior per-competitor files first:

rm -f "$OUTPUT_DIR"/*.md && rm -rf "$OUTPUT_DIR"/partials "$OUTPUT_DIR"/screenshots

Step 1: User Company Research

This step sets the baseline for what "competitor" means AND produces the verified data the Step 5b matrix will use for the userCompany row.

Rule: The user's company gets the same 5-lane research depth as competitors. Do NOT fill userCompany in matrix.json from memory β€” it will ship false claims to the user's own team. On a search-API run (user company Exa, 2026-04-23), skipping this step produced a matrix that claimed Exa had a "published uptime SLA" (there is no numeric public SLA β€” only a status page) and marked its MIT-licensed Python SDK as open-source: false (the repo is github.com/exa-labs/exa-py, LICENSE confirmed MIT). Both errors would have surfaced in the "Where you're winning" card as fabricated moats.

Process:

  1. Ask the user for their company name or URL.

  2. Check for an existing profile at {SKILL_DIR}/profiles/{company-slug}.json. If it exists, load it and confirm with the user: "I have your profile from {researched_at}. Still accurate?" β€” if yes, skip to Step 2 BUT still run the partial-lane enrichment below so matrix synthesis has fresh feature evidence. The profile format is shared with company-research (same shape). If a user already has a profile saved under company-research/profiles/, you may copy it into this skill's profiles directory rather than re-researching.

  3. Run the full 5-lane enrichment on the user's company β€” identical to the competitor pattern in Step 5. For each lane, spawn a Bash-only subagent that writes to {OUTPUT_DIR}/partials/{user-slug}.{lane}.md:

    • marketing β€” tagline, positioning, pricing tiers, features, integrations, open-source components (SDK repos + licenses), regions offered, compliance (SOC 2 / HIPAA / trust portal URL)
    • technical β€” REST + streaming API support (with docs URLs), SDK languages, MCP server URL, neural vs keyword retrieval modes, reranking / highlights / live-crawl specifics, published uptime SLA (actual %, not status page), third-party retrieval-quality benchmarks
    • discussion, social, news β€” optional in quick mode, recommended in deep+ See references/research-patterns.md β†’ "Self-Research" for sub-questions. Each finding MUST cite a URL.
  4. Run merge_partials.mjs on the user's partials too β€” produces {OUTPUT_DIR}/{user-slug}.md, the canonical source Step 5b reads from for userCompany flags.

  5. Synthesize into a profile: Company, Product, Existing Customers, Competitors (seed list), Use Cases, precise_category, category_include_keywords, exclusion_list. Do NOT include ICP β€” this skill doesn't need it.

    • precise_category: one sentence describing the category. e.g., "AI web search API for agents with neural + keyword retrieval". Avoid vague words like "tools" / "platform".
    • category_include_keywords: 8-15 phrases a direct competitor's marketing would likely contain (hero or title). Include semantic variants.
    • exclusion_list: phrases that indicate a different category β€” used by the gate to reject false positives (e.g. antidetect browser, scraping api, screenshot api, residential proxy). See references/research-patterns.md β†’ "Synthesis Output" for the exact format and Exa as a worked example.
  6. Present the profile + the user-company .md to the user for confirmation. Do not proceed until confirmed.

  7. Save the confirmed profile to {SKILL_DIR}/profiles/{company-slug}.json.

Step 2: Depth Mode + Seed Input

Ask clarifying questions via AskUserQuestion with checkboxes:

  • Known competitors? Text area for URLs/names (optional β€” discovery will find more).
  • Depth mode?
    • quick β€” marketing surface only, many competitors, ~2-3 tool calls each
    • deep β€” + external signal (mentions, reviews, news), ~5-8 tool calls each
    • deeper β€” + public benchmarks + strategic diff vs user's company, ~10-15 tool calls each
  • Target count? Rough number of competitors to research (e.g., 10 / 20 / 50).

This is the ONLY user interaction. After this, execute silently until the report is ready.

| Mode | Research per competitor | Best for | |------|--------------------------|----------| | quick | Lane 1 only (homepage + pricing) | Scanning ~30-50 competitors fast | | deep | Lanes 1+2 | ~15-25 competitors with external signal | | deeper | All 4 lanes (+ benchmarks + strategic diff) | ~5-15 competitors with full intel |

Step 3: Discovery (3 parallel waves)

Formula: ceil(target_count / 20) queries per wave. Over-discover ~3x because the gate drops ~40-60%.

Evaluation on a search-API run shows all three waves are additive β€” skip any and you lose real competitors:

Wave A β€” Generic alternatives (broad; heavy aggregator noise, filtered out later)

  • "alternatives to {user_company}"
  • "{user_company} competitors"

Wave B β€” Precise category (uses precise_category from the profile)

  • "{precise_category}" verbatim
  • 2-3 queries composed from the most distinctive tokens (e.g. "web search api for ai agents", "retrieval API for LLMs")

Wave C β€” Comparison-page graph (highest precision)

  • "{user_company} vs"
  • "{seed1} vs", "{seed2} vs", "{seed3} vs" (seeds from the profile's competitors list)
  • After the searches, run scripts/extract_vs_names.mjs to parse "X vs Y" patterns from result titles β€” this uniquely surfaces competitors that don't appear as U

Truncated for display β€” read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars3.7k
CategoryMarketing
Updated2mo ago
Forks241

Languages

JavaScript

Trust signals

88/100

From repository metadata: license, adoption, age and documentation. Not a code audit β€” see the Safety scan above for what the skill file itself contains.

1 medium
competitor-analysis β€” Universal Skill: Install & Safety Check | SkillAgent