competitor-analysis
Research competitors with Browserbase discovery, enrichment lanes, screenshots, matrices, and HTML reports.
Profile →npx skills add sickn33/agentic-awesome-skills --skill competitor-analysis --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Analyzes competitors using Browserbase discovery and enrichment lanes, then outputs an HTML report with an overview, per-competitor deep dives, a side-by-side feature/pricing matrix, and a mentions feed.
How it works
- Requires the browse CLI and BROWSERBASE_API_KEY.
- Uses a 4-lane enrichment pattern after discovery: marketing, technical, discussion, social, and news.
- Produces one markdown per competitor at the output directory and then compiles an HTML report via a Node script.
- Output directory is created at your home: ~/Desktop/{company_slug}competitors{YYYY-MM-DD}/ with per-competitor .md files and generated HTML views.
- Subagents must write to {OUTPUT_DIR}/partials/{competitor-slug}.{lane}.md and then merge with merge_partials.mjs to produce canonical {OUTPUT_DIR}/{competitor-slug}.md.
- The final report is generated with: node {SKILL_DIR}/scripts/compile_report.mjs {OUTPUT_DIR} --user-company "{user_company}" --open.
- All web searches use: browse cloud search; all page fetches use: browse cloud fetch --allow-redirects. If needed, fall back to browse get markdown after browse open <url> --remote.
- URL deduplication and extraction of names are handled by list_urls.mjs and extract_vs_names.mjs respectively.
- Stepwise workflow includes user confirmation, gate filtering by category, and a final HTML report with embedded hero screenshots and Battle Card cards.
When to use it
Use when the user needs structured competitor research with discovery, enrichment lanes, screenshots, matrices, and a final HTML report. Suitable for marketing intelligence and competitive analysis workflows.
What it can touch
- Tools: Bash, Agent, AskUserQuestion, CLAUDE-CODE, CODEx, Cursor (as declared in the skill).
- Output files and directories under OUTPUT_DIR: per-competitor .md files, partials, screenshots, and HTML reports.
Caveats
- Requires BROWSERBASE_API_KEY environment variable and the browse CLI installed.
- Subagents must use ONLY the Bash tool and batch file writes; main agent should not read raw JSON batch files.
- Output is limited to one markdown file per competitor; reports are compiled into a single HTML overview.
- The workflow contains gating steps to filter candidates by category signals before enrichment; the user must confirm enrichment sets.
# Competitor Analysis ## When to Use Use when the user needs structured competitor research with Browserbase discovery, enrichment lanes, screenshots, comparison matrices, and a final HTML report. _Source: [browserbase/skills](https://github.com/browserbase/skills) (MIT)._ 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`: ```json "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
- When to Use
- Pipeline Overview
- Step 0: Setup Output Directory
- Step 1: User Company Research
- Step 2: Depth Mode + Seed Input
- Step 3: Discovery (3 parallel waves)
- Step 4: Gate (category-fit filter)
- Step 4.5: Confirm enrichment set with the user
- Step 5: Deep Enrichment
- Quick mode — single subagent per batch
- Deep / Deeper mode — 5 subagents PER competitor (parallel lane fan-out)
- Merge partials → canonical per-competitor file
- Synthesize the comparison matrix (write matrix.json)
- Fact-check the matrix — spot-check the high-stakes cells (default)
mkdir -p "$OUTPUT_DIR"
rm -f /tmp/competitor_discovery_batch_*.json
rm -f "$OUTPUT_DIR"/*.md && rm -rf "$OUTPUT_DIR"/partials "$OUTPUT_DIR"/screenshots
node {SKILL_DIR}/scripts/list_urls.mjs /tmp --prefix competitor > /tmp/competitor_urls.txt
node {SKILL_DIR}/scripts/extract_vs_names.mjs /tmp --prefix competitor \
cat /tmp/competitor_candidates.txt \
grep '"status":"PASS"' /tmp/competitor_gated.jsonl \
node {SKILL_DIR}/scripts/merge_partials.mjs {OUTPUT_DIR}
node {SKILL_DIR}/scripts/capture_screenshots.mjs {OUTPUT_DIR} --mode remote
node {SKILL_DIR}/scripts/compile_report.mjs {OUTPUT_DIR} --user-company "{user_company}" --openWhat does the competitor-analysis skill do?
Research competitors with Browserbase discovery, enrichment lanes, screenshots, matrices, and HTML reports.
How do I install it?
Run `npx skills add sickn33/agentic-awesome-skills --skill competitor-analysis --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From sickn33/agentic-awesome-skills, a repository with 44,414 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.