agentleFS
Sign inStart free
pendo-iopendo-io/Product-Loop/pulse/SKILL.md

pulse

Skill0 starsChanged 14 days agoMITView on GitHub

A quick read on how a product area is doing right now, with visitors, accounts, feedback, and frustration signals in one view and no dashboard required. Compares the last 7 days with the prior 7, clusters recent feedback into themes, surfaces rage clicks, errors, and u-turns, and ends with one thing to watch. Use Monday morning before planning or standup, for a quick check before a leadership conversation, or after a quiet period when you want to know what moved. Trigger on "/pulse" or "/pulse <product area>".

21 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ant, artistic and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • bergsideSkill

    ant

    Structured, enterprise-focused design system emphasizing clarity, consistency, and efficiency for data-dense web applications.

    Also in 3 projects that use this

  • bergsideSkill

    artistic

    High-contrast, expressive style with creative typography and bold color choices for visually striking interfaces.

    Also in 3 projects that use this

  • +10 more from bergside

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 5 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After a quiet period when you want to know what moved

    line 19
  2. Distinctive:

    If no product area is given, ask the user which area to focus on before proceeding.

    line 28
  3. Very specific:

    Use searchEntities to find pages and features related to the product area:

    line 42
  4. Distinctive:

    Keep the top 5 pages and top 5 features by relevance.

    line 51
  5. Very specific:

    If there are 5 or more items, run generateFeedbackTopics to cluster them.

    line 76
  6. Distinctive:

    If fewer than 5 items, list them individually with a one-line summary of each.

    line 78
  7. Very specific:

    If no tracked issues exist, call sessionReplayList with rage_click or error filters and surface the top 3 sessions by severity.

    line 90
  8. Distinctive:

    Keep it tight. The whole digest should be readable in under 2 minutes.

    line 96

“Common” is measured: kept by at least 6 in 10 of the 18 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

pulse

A quick read on how a product area is doing right now. Visitors, accounts, feedback, and frustration signals — all in one view, no dashboard required.

When to use

  • Monday morning before planning or standup
  • Quick check before a leadership conversation
  • After a quiet period when you want to know what moved

Usage

/pulse
/pulse <product area>

If no product area is given, ask the user which area to focus on before proceeding.

Workflow

Step 1: Get app context

Use listAllApplications to get subId and appId

Step 2: Find the relevant pages and features

Use searchEntities to find pages and features related to the product area:

searchEntities:
  itemType: "Page" then "Feature"
  query: <product area>
  limit: 10 each

Keep the top 5 pages and top 5 features by relevance.

Step 3: Visitors and accounts — last 7 days vs prior 7 days

For each of the top pages and features, call entityUsage twice — once for the current period and once for the prior period:

entityUsage:
  period 1: today minus 7 days → today
  period 2: today minus 14 days → today minus 7 days
  metrics: visitors, accounts, totalEvents

Calculate the delta (absolute and percentage) for visitors and accounts between the two periods.

Flag anything that moved more than 10% in either direction.

Step 4: Recent feedback

getFeedbackItems:
  dateRange: last 7 days
  limit: 20

If there are 5 or more items, run generateFeedbackTopics to cluster them. Surface the top 3 themes with a count of how many items fall into each.

If fewer than 5 items, list them individually with a one-line summary of each.

Step 5: Frustration signals

listTrackedIssues:
  filter: rage clicks, errors, u-turns
  dateRange: last 7 days

Surface any issues that appear more than twice. For each, note the page or feature it's on and the number of affected visitors.

If no tracked issues exist, call sessionReplayList with rage_click or error filters and surface the top 3 sessions by severity.

Output format

Keep it tight. The whole digest should be readable in under 2 minutes.

## Pulse — [Product Area] — [Date]

### Usage (last 7 days vs prior 7 days)
- Visitors: X (▲/▼ Y%)
- Accounts: X (▲/▼ Y%)
- Notable movements: [any page/feature that moved >10%]

### Feedback themes
1. [Theme] — X mentions
2. [Theme] — X mentions
3. [Theme] — X mentions

### Frustration signals
- [Issue type] on [page/feature] — X visitors affected
- [Issue type] on [page/feature] — X visitors affected

### One thing to watch
[One sentence — the most important signal from this pulse that warrants a closer look]

End with a one-sentence "one thing to watch" — the signal most likely to need action this week.

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.

Reviews can't be read right now.

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.

Check your setup, free