agentleFS
VodouAIVodouAI/OS/skills/catalog/execdesk-action-competitor-monitor/SKILL.md

execdesk-action-competitor-monitor

Skill1 starsChanged 4 months agoApache-2.0View on GitHub

CEO synthesizes the week's competitor signals from existing growth-hack watchers. Outputs 3 bullets the founder should know about.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every bullet ends with "why it matters to us" — pure observation isn't useful

    line 57

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Competitor Monitor — CEO weekly digest (v1.0)

The CEO's weekly read of competitor activity. Pulls from existing growth-hack watchers (growth-hack-hn-watcher, growth-hack-social-bot, etc.) and outputs a tight 3-bullet digest — NOT a full competitor newsletter.

This pairs with the CMO's competitor-positioning scan (which is messaging-focused). This one is signal-focused: who launched what, who raised, who hired, who pivoted.

Output schema (locked v1.0)

# Competitor Signals — week of <date>

## What I'd actually flag
- **<Competitor>:** [What they did + why it matters to us. 1-2 sentences.]
- **<Competitor>:** [What + why it matters.]
- **<Competitor>:** [What + why it matters.]

## What I noticed but isn't worth reacting to
- [1-2 lines of "this happened but stay the course"]

## What I'd test in response (or NOT)
[Either: 1 specific test we should run because of these signals — OR — explicit "stay the course, no reaction needed."]

—
*[1-line: the most important signal in one phrase.]*

Voice + grounding rules

  • Maximum 3 flagged competitors. More = noise.
  • Every bullet ends with "why it matters to us" — pure observation isn't useful
  • "Not worth reacting to" section forces signal/noise discipline
  • Final test recommendation is ONE thing or explicit no-action

Failure modes

  • ❌ Listing every competitor move (newsletter, not digest)
  • ❌ "Why it matters" sections that don't connect to the brief
  • ❌ Multiple test recommendations
  • ❌ Inventing competitor activity not actually surfaced by the watchers

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.