agentleFS
JustinTSmithJustinTSmith/ai-operator-skills/market-pulse/SKILL.md

market-pulse

Skill0 starsChanged 4 months agoMITView on GitHub

Answer "what are people saying about X" with a cited, synthesized briefing from live web and social search under an explicit query budget. Use when the user asks what the internet, market, or community thinks about a topic, product, company, or announcement.

7 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 3

    Distinctive

    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:

    No quote walls. Synthesize.

    line 53
  2. Distinctive:

    Never present one loud thread as consensus.

    line 54
  3. Distinctive:

    If the honest answer is "almost nobody is talking about this", say exactly that.

    line 56

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “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

Market Pulse

A bounded research sweep that answers one question: what is being said about this topic right now, and what does it mean for the user.

Distilled from a tiered X/Twitter research tool whose design constraint was cost: decompose the question, spend a fixed query budget where it matters, synthesize once.

Workflow

  1. Decompose the topic into 3-5 sub-queries before searching anything. A good decomposition covers: the announcement or thing itself, praise, criticism, comparisons to alternatives, and operator/practitioner experience. Bad decomposition is five rephrasings of the same query.
  2. Set the budget and say it: default 8 searches, 15 sources read. The user can say "go deeper" to double it. Never exceed the budget silently.
  3. Sweep using the session's available tools (web search, X/Twitter search if connected). Prioritize: primary sources first, practitioners over press releases, recent over canonical. Note the date on every source; discard anything older than the question implies.
  4. Synthesize once at the end, not incrementally. Group by signal, not by source.

Output format

# Pulse: <topic> - <date>

**The read in one line:** <the single most defensible takeaway>

## What people are saying
- <signal 1, with 1-2 inline source links>
- <signal 2 ...>

## Disagreement
<where sources genuinely conflict, stated as a live question>

## What it means for you
<2-4 sentences tied to the user's context if known>

Budget used: <n> searches, <m> sources.

Anti-patterns

  • No quote walls. Synthesize; link the sources.
  • Never present one loud thread as consensus. Two independent sources minimum for any claim stated as a trend.
  • If the honest answer is "almost nobody is talking about this", say exactly that. Silence is a finding.

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.