competitor-intel-agent — Claude Code skill: what it does and install
competitor-intel-agent monitors competitor sites, pricing models, hiring shifts, and product releases while saving snapshot history.
MIT 251 installs ★ 440 updated 2026-10-20
npx skills add OneWave-AI/claude-skills --skill competitor-intel-agent -a claude-codeWhat competitor-intel-agent does
The skill operates in setup, monitoring, or report-only mode. During initialization, it records your company profile, competitor domains, and builds the ./competitor-intel/ directory containing config.yaml. It uses WebSearch, WebFetch, Read, Write, and Bash to collect publicly available web information.
Monitoring covers six operational dimensions. Incoming data is benchmarked against older snapshots, assigning a severity score from 1 to 5 to every difference. Shifts rated 4 or 5 trigger immediate alerts in the output logs. Once three snapshots exist for a target, the agent incorporates longitudinal trend analysis into the final report.
Records older than 30 days get flagged as stale, which makes regular update runs necessary to keep signals reliable.
What it helps with
- track rival pricing updates and tier changes over time
- detect hiring patterns and product releases from public pages
- score competitor movements on a 1 to 5 magnitude scale
- generate strategic intelligence reports backed by historical snapshots
Example prompts for the agent
- Set up competitor tracking and initialize config.yaml in ./competitor-intel/
- Run a monitoring cycle against all competitors listed in config.yaml
- Generate an intelligence report from existing snapshots without fetching new data
How to install competitor-intel-agent
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill competitor-intel-agent -a claude-code2Manually: put the files in place
~/.claude/skills/competitor-intel-agent/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/competitor-intel-agent/
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill competitor-intel-agent -a codex2Manually: put the files in place
.agents/skills/competitor-intel-agent/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill competitor-intel-agent -a cursor2Manually: put the files in place
.cursor/skills/competitor-intel-agent/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install OneWave-AI/claude-skills competitor-intel-agent2Manually: put the files in place
.github/skills/competitor-intel-agent/SKILL.md1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill competitor-intel-agent -a gemini-cli2Platform CLI
gemini skills install https://github.com/OneWave-AI/claude-skills --path competitor-intel-agentManually: put the files in place
.devin/skills/competitor-intel-agent/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill competitor-intel-agent -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about competitor-intel-agent
How to install competitor-intel-agent in Claude Code?
Run npx skills add OneWave-AI/claude-skills --skill competitor-intel-agent -a claude-code in your terminal. The definition is placed in ~/.claude/skills/competitor-intel-agent/SKILL.md.
What does competitor-intel-agent do?
It tracks public competitor websites across pricing, hiring, and products, logs structured snapshots, and highlights high-impact changes.
When does trend analysis become available?
The agent adds longitudinal trend synthesis as soon as three or more dated snapshots exist for a given competitor.
Source text
SKILL.md · MIT
--- name: competitor-intel-agent description: Monitors competitor websites, pricing, content changes, hiring patterns, and product updates. Generates intelligence reports with strategic implications and trend analysis. Stores history for longitudinal tracking. tools: Read, Write, WebSearch, WebFetch, Bash model: inherit --- # Competitor Intelligence Agent Track competitor activity across multiple dimensions, detect meaningful changes, interpret the signals, and deliver actionable intelligence that builds historical context over time. Act as an analyst that connects dots, not a raw scraper. ## Contents - `references/directory-structure.md` -- tracking directory layout, `config.yaml`, and `usage-history.json` templates - `references/monitoring-dimensions.md` -- the six monitoring dimensions with per-dimension analysis frameworks, detection protocols, and snapshot output formats - `references/intel-report-format.md` -- the full intelligence report template - `references/scoring-and-rules.md` -- change-detection scoring, trend protocol, data-quality rules, execution rules, quick commands ## Workflow 1. Determine the operating mode on invocation: - Setup (no tracking directory exists): collect the user's company name and description, competitor URLs/domains, priority monitoring dimensions, and output directory (default `./competitor-intel/`). Create the directory structure and `config.yaml`. See `references/directory-structure.md`. - Monitoring run (tracking directory exists): proceed to steps 2-7. - Report only (user wants a report without new monitoring): read existing snapshots and change logs, synthesize trends, and generate strategic recommendations using `references/intel-report-format.md`. 2. Read `config.yaml` to load the competitor list and settings, then read the most recent snapshot for each competitor and dimension. 3. Execute monitoring across all configured dimensions. Apply the detection protocol for each dimension in `references/monitoring-dimensions.md`. 4. Compare new data against previous snapshots. Score every change for magnitude per `references/scoring-and-rules.md`; flag changes rated 4-5 as immediate alerts. 5. Write dated snapshots in the per-dimension output formats and log detected changes under the competitor's `changes/` folder. 6. Generate the intelligence report following `references/intel-report-format.md`. When 3 or more snapshots exist for a competitor, add longitudinal trend analysis. 7. Update `usage-history.json` with the run metadata. ## Guardrails - Never fabricate competitor data. If a fetch fails or a dimension has no data, state the gap. - Separate raw data (snapshots) from interpretation (reports). - Tag every data point with source, timestamp, and confidence; flag data older than 30 days as stale. - Recommend only legal, ethical competitive responses. Collect only publicly available professional information. Apply the detailed change-detection, trend, data-quality, and execution rules in `references/scoring-and-rules.md` throughout.
© OneWave-AI · MIT · OneWave-AI/claude-skills