Competitive intel

Skill K95M65/AI_ONBOARD/skills/competitive-intel

Run an ethical competitive-intelligence cycle — scope a question, gather market and competitor data, analyze it with structured frameworks, and communicate findings for a decision. Use when researching competitors, a market, or a strategic question. Coordinates the market-research, analytical-frameworks, and data-storytelling skills.From its SKILL.md

Install

npx -y skills add K95M65/AI_ONBOARD --skill competitive-intel

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

26 days oldThe repository was created 26 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.1 KB, 400 tokens by cl100k_base, as published. Nobody here has run it

Competitive intelligence

The umbrella methodology. It orchestrates the specialists: market-research to gather, analytical-frameworks to analyze, and data-storytelling + dataviz to communicate — all under an ethics constraint throughout.

When to use

Answering a competitive or market question that informs a real decision.

The cycle

Scope. What decision does this inform? Write the key intelligence question(s). Vague questions produce vague intel — "should we enter market X?" beats "tell me about market X."
Collect. Gather from ethical, lawful, public sources (market-research). Record source, date, and a credibility note for every data point.
Analyze. Apply the fitting framework(s) (analytical-frameworks). Separate observation from inference; attach a confidence level.
Synthesize. The "so what?" — implications and options for the decision, not a data dump.
Communicate. Lead with the answer; support with evidence and visuals (data-storytelling).

Ethics — non-negotiable

Public, lawfully obtained information only. No pretexting, no impersonation, no inducing anyone to breach an NDA or confidentiality.
Respect IP, privacy, and terms of service. Don't scrape or access what you're forbidden to.
Fact vs. inference. Never fabricate, and never launder a guess as a finding.
The publish test: if a collection method would embarrass you if it were made public, don't use it.

Rules

Decision-first. Intel with no decision attached is trivia.
Date and cite everything — markets move; stale intel misleads.
Flag confidence and gaps explicitly; a known unknown is more useful than false certainty.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most research analysis skills give in 400 tokens

Counted across 1,063 of the 1,754 authors here whose files we hold, read 2026-08-07

Generate a markdown reportin 32 of 1063, across 23 files
Cite each claim's sourcein 30 of 1063, across 15 files
Define the ideal customer profilein 20 of 1063, across 2 files
Search for companies matching the criteriain 20 of 1063, across 2 files
Assign a fit score from one to tenin 20 of 1063, across 2 files
Analyze the codebase to understand the productin 19 of 1063, across 1 file
Ask clarifying questions about the value propositionin 19 of 1063, across 1 file
Look for signals of immediate needin 19 of 1063, across 1 file
Identify the target decision maker rolein 19 of 1063, across 1 file
Suggest a personalized contact strategyin 19 of 1063, across 1 file
Provide conversation starters for outreachin 19 of 1063, across 1 file
Format results in a scannable markdown templatein 19 of 1063, across 1 file

Said here and by no other author read

write key intelligence questions tied to a decision
gather from public, lawful sources only
record source, date, and credibility for each data point
apply fitting analytical frameworks
state implications and options for the decision
lead with the answer

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.