Skip to content
Skills Library
Management & product · Research

competitor-intelligence

/competitor-intelligence

Use when the user wants competitive intelligence — what competitors launched, announced, raised, hired, lost or were criticised for; competitor news digests; share of voice against competitors; or ongoing competitor monitoring. Compares the user's company with its competitors using NewsCatcher company research, counts and news search.

Licence
MIT
Last repository change
12.11.2026

Assessment and security

90/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
2
Scripts
1
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 12.11.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What to check before installing
  • 1 scripts in this package. Review them before installing, as Claude may execute them.

Scripts: scripts/render-report.mjs

What it does and when to use it

Use when the user wants competitive intelligence — what competitors launched, announced, raised, hired, lost or were criticised for; competitor news digests; share of voice against competitors; or ongoing competitor monitoring. Compares the user's company with its competitors using NewsCatcher company research, counts and news search.

Original author description

Use when the user wants competitive intelligence — what competitors launched, announced, raised, hired, lost or were criticised for; competitor news digests; share of voice against competitors; or ongoing competitor monitoring. Compares the user's company with its competitors using NewsCatcher company research, counts and news search.

How it works

  1. Ask first (only what's missing)
  2. Before you run
  3. Run
  4. Report file (when exportresearch is available)
  5. Deliver
  6. Quality bar
  7. Done when
Original SKILL.md headings · 54 lines, 530 words
SKILL.md preview
---
name: competitor-intelligence
description: "Use when the user wants competitive intelligence — what competitors launched, announced, raised, hired, lost or were criticised for; competitor news digests; share of voice against competitors; or ongoing competitor monitoring. Compares the user's company with its competitors using NewsCatcher company research, counts and news search."
---

# Competitor intelligence

What each competitor did recently, how much attention they get versus you, and what it means.

Runs on the NewsCatcher MCP tools (`start_research`, `get_research`, `count_articles`, `search_news`, `create_monitor`).
If missing, see the `newscatcher` skill.

## Ask first (only what's missing)
- The user's company and 2–8 competitors, as domains.
- Window (default 30 days) and focus (launches, pricing, funding, hires, partnerships, customers, outages, legal).

## Before you run
- Window or size missing? Ask once: one multiple-choice question, recommended option first (e.g. "Last 30 days
  (Recommended)", "Fast, 50 rows (Recommended)"). Skip it when the user gave both or said "just run it".
- Standard/max, more than 20 companies or keep_updated: repeat the call with `dry_run=true` first (free) and show
  its time and cost in that question.
- Set up a monitor only when the user wants this regularly ("every week", "keep me posted"); not on one-off asks.
- While it runs, keep calling `get_research(run_id, wait_seconds=300)`; if you must stop first, say it is still
  running and ask the user to say "refresh".

## Run
1. Company news: `start_research(companies=[you, competitors…], query=<focus or omit>, lookback_days=30, wait_seconds=300)`;
   `get_research` until done. One row per story with type and importance.
2. Share of voice: `count_articles(queries=["\"You\"", "\"Rival A\"", …], from=<window start>, interval="week")`.
   Use precise boolean queries for ambiguous names (`"Notion" AND (app OR software OR workspace)`).
3. Themes across the market: `search_news(query="<category> launches OR pricing OR funding", window="30d", group="story")`.

## Report file (when export_research is available)
On a local setup build an HTML report (scoreboard, story types, share of voice, every story with its link) from saved
files; the chat answer then gives the highlights and the path. One folder, e.g. `newscatcher-exports/competitors-<date>/` (below: `<dir>`).
1. After the company run: `export_research(run_id=…, file_format="json", path="<dir>/companies.json")`.
2. The share-of-voice count with `save_as="json", path="<dir>/sov.json"` added.
3. Optional market themes: the search from Run with `save_as="json", path="<dir>/market.json"` added.
4. Write the moves that matter, the "so what" and the gaps to `<dir>/notes.md` (facts from the rows only).
5. Run `node <this skill's base directory>/scripts/render-report.mjs --title "Competitors: <you> vs <rivals>" --subtitle "<window>"
   --rows "Company news=<dir>/companies.json" --counts "Share of voice=<dir>/sov.json" --stories "Market themes=<dir>/market.json"
   --notes <dir>/notes.md --out <dir>/report.html`. If you can't write files, pass the notes on stdin instead: `--notes -` followed by a quoted heredoc (`<<'EOF'` … `EOF`).
6. In chat: the summary lines it prints and the report path; open the file. Without export_research, deliver as below.

## Deliver
- **Scoreboard**: per company — stories, top story types, share of voice %, momentum (week over week).
- **Moves that matter**: dated competitor actions with links, and a "so what" for the user.
- **Gaps and openings**: what competitors are criticised for, what they didn't do.
- If the user wants to keep watching: `create_monitor(companies=[…competitors], query=<focus>, schedule={every:"week"})`.

## Quality bar
- Show at most 25 rows inline (most important or newest first) and say how many there are; `export_research` gives the full table as a file.
- Same window and method for every company; say if a name's counts include namesakes.
- Facts from coverage only; label opinion pieces and rumours.

## Done when
The user can say what each competitor did this month and where they stand on attention, with sources.
Files in this package (2)
  • SKILL.md 4 KB
  • scripts/render-report.mjs 45 KB

Versions

RepositoryScoreLicence
This page · Newscatcher/newscatcher-mcp90MIT
Crawlora-org/crawlora-skills100MIT
Navinspire-ia/navin100AGPL-3.0
nirholas/xactions100Apache-2.0

Database snapshot: 13.11.2026 · package version cdd1bd4c5f9d (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100competitor-intel
    Searches the live web via Nimble APIs to monitor competitors and produce a structured intelligence briefing. Runs parallel searches for news, product launches, hiring signals, and funding — then compares against previous findings to highlight only what's new. Use this skill when…
  • 100competitor-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,…
  • 95anysite-competitor-intelligence
    Competitive intelligence gathering using anysite MCP server across LinkedIn, social media, Y Combinator, and the web. Track competitor activities, analyze hiring patterns, monitor content strategies, benchmark market positioning, research startup competitors, and gather…
  • 100startup-competitors
    Deep competitive intelligence for any market. Analyzes competitors' products, pricing, customer sentiment, GTM strategy, and growth signals using real web data. Produces battle cards, pricing landscape, and feature matrix. Use when the user wants to understand their competitive…
  • 90competitor-profiling
    When the user wants to research, profile, or analyze competitors from their URLs. Also use when the user mentions 'competitor profile,' 'competitor research,' 'competitor analysis,' 'profile this competitor,' 'analyze competitor,' 'competitive intelligence,' 'competitor deep…
  • 90competitor-profiling
    When the user wants to research, profile, or analyze competitors from their URLs. Also use when the user mentions 'competitor profile,' 'competitor research,' 'competitor analysis,' 'profile this competitor,' 'analyze competitor,' 'competitive intelligence,' 'competitor deep…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.