Independent guide to useful Bots · Across platforms
Bot Cabinet
Back to The Cabinet
Illustration for Pulse in The Cabinet’s Hermes Bot collectionThe Cabinet · Bot starter
Planning and client work

Pulse

Growth management assistant

Turns a growth goal and approved data into a clear baseline, prioritized experiments, and a recurring results brief.

Best for: Small teams trying to attract customers, help them get started, keep them coming back or increase revenue.

Choose where to use it

Hermes archive import checked; a full task run is still pending. Read the test status

Choose where to use it

Use Pulse on your platform

Choose your app for setup instructions and test results.

Hermes AgentArchive import passed

Import the profile, review its files, choose the access it needs, and run the first assignment. The archive imported successfully and its Skill was present in an isolated Hermes Agent 0.21.0 installation. Its task results have not been tested.

Download the profile Read the files

Keep track of your first Hermes run

Your Bot workbench

Continue after the download

Pack 2.0.0

Task checks: 0 of 2. Setup: 0 of 3. Check only steps you completed. After running a task, review its result and tell us whether it helped. These are your confirmations, not independent Cabinet verification. Progress stays in this browser.

Set up once
Check each real run
View all my active Bots
ChatGPT Workspace AgentSetup guide · test pending

Build the same job as a Workspace Agent, add its Agent Skill, then choose the files, apps, approvals and sharing rules it needs. This setup has not yet been installed or task-tested for Pulse.

Set up Pulse in ChatGPT
ClaudeSetup guide · test pending

Use a Cowork plugin or Skill for a general work role. Use Claude Code only when the job involves code or a local project. This setup has not yet been installed or task-tested for Pulse.

Follow the Claude setup
Grok BotPrepared · test pending

Copy the job into a Grok Bot profile, try one task, and review the result before adding a Skill or Routine. This Bot has not been tested in Grok.

Follow the guided setup Download the full recipe Grok Bot setup help
Download files for another app

Portable Bot Pack

Download the instructions, Bot Passport and setup notes as Markdown or JSON. The Agent Skill is a SKILL.md file. Check your app’s requirements and test it there; results can differ between apps.

Download Markdown Download JSON Download the Agent Skill

Review the instructions and permissions, then run a test in your chosen app before relying on the result.

First task

Try one small job

Use one approved data export to define the baseline. Identify one gap. Propose two measurable experiments.

BringThe growth goal and customer stage

Look forA baseline metric and funnel brief

Read the job, safety rules, files, and test record

Customize this Bot in Bot Lab

Job and limits

What this Bot is responsible for

Its job

Turns a growth goal and approved data into a clear baseline, prioritized experiments, and a recurring results brief.

Outside its job

  • A person approves targeting, spending, public claims, customer outreach, and account changes.
  • The Bot does not change campaigns or tracking, collect new personal data, or treat a small sample as a reliable result.

Information it relies on

  • Growth goal and customer stage
  • Approved data and metric definitions
  • Channels, budget, and available capacity
  • Privacy and brand constraints

Ask you before

  • Ask before changing campaigns, tracking, or accounts
  • Ask before spending money or contacting customers
  • Do not collect new personal data or publish claims

When it runs

Run when I supply a current data export. Add a recurring review only after one manual report is approved.

What it produces

  • A baseline metric and funnel brief
  • A prioritized experiment list with one primary metric for each test
  • A weekly report separating observations, hypotheses, and decisions
Bot Pack 2.0

Put Pulse to work

Get the setup files, try the first task, and check the result. The pack also includes a reusable Skill and a plan for a Routine.

First assignment

Use one approved data export to define the baseline. Identify one gap. Propose two measurable experiments.

Check the result

Pause for a person to review these deliverables: A baseline metric and funnel brief; A prioritized experiment list with one primary metric for each test; A weekly report separating observations, hypotheses, and decisions. Wait for approval before the Bot sends, publishes, schedules, purchases, deletes, deploys, or changes an outside account.

Prepared · test pending

Reusable Skill

Pulse core Skill

Run when I supply a current data export. Add a recurring review only after one manual report is approved.

Produces
  • A baseline metric and funnel brief
  • A prioritized experiment list with one primary metric for each test
  • A weekly report separating observations, hypotheses, and decisions
Download this Skill
Manual test required

Planned Routine

Pulse primary Routine

Run when I supply a current data export. Add a recurring review only after one manual report is approved.

Before scheduling

Stop, preserve the completed work, and report the failure before trying again or changing access.

The Skill and Routine have not been task-tested. Try them with sample material and approve the results before adding a schedule or outside access.

Try asking

  • Map this signup funnel and show where the largest verified drop-off occurs.
  • Prioritize these six growth ideas by evidence, effort, and learning value.
  • Prepare a weekly growth brief from this dashboard export and explain any anomaly.

What it should produce

  • A baseline metric and funnel brief
  • A prioritized experiment list with one primary metric for each test
  • A weekly report separating observations, hypotheses, and decisions

What you provide

  • The growth goal and customer stage
  • Approved data and metric definitions
  • Channels, budget, capacity, and privacy or brand constraints

Decisions you make

  • A person approves targeting, spending, public claims, customer outreach, and account changes.
  • The Bot does not change campaigns or tracking, collect new personal data, or treat a small sample as a reliable result.

Bot Passport · version 2

Access and approval record

Elevated planned risk

Review this record before setup. Update it whenever the Bot's job, tools, accounts, schedule, or authority changes.

May read
  • The growth goal and customer stage
  • Approved data and metric definitions
  • Channels, budget, capacity, and privacy or brand constraints
May create
  • A baseline metric and funnel brief
  • A prioritized experiment list with one primary metric for each test
  • A weekly report separating observations, hypotheses, and decisions
May do without approval
  • Analyze material supplied in its conversation
  • Draft the listed deliverables for a person to review
  • Identify missing information and ask questions
Must ask first
  • Ask before changing campaigns, tracking, or accounts
  • Ask before spending money or contacting customers
  • A person approves targeting, spending, public claims, customer outreach, and account changes
Must not do
  • Collecting new personal data or publishing claims
  • Changing campaigns or tracking, or treating a small sample as a reliable result
Tools and access requested

Read-only analytics exports · Approved customer or campaign research · Spreadsheet access for calculations

How to stop it

Disable its schedule, remove outside-service connections, and revoke or rotate any dedicated credentials.

What these rules can and cannot prevent
    Download this Bot Passport (Markdown)
    Set it up in Hermes Desktop

    Import the profile and run one small test

    The Hermes download contains its manifests, role instructions, Bot Passport, setup guide, license, and included Skills. The ZIP contains the same files for inspection.

    1. 1
      Download the Hermes profile.

      Import the .tar.gz archive from the Profiles screen, or copy the terminal command above.

    2. 2
      Review the imported profile.

      Read README.md and SOUL.md, then confirm the name, description, and standing instructions.

    3. 3
      Choose the access it needs.

      Add only the skills, tools, and connections required for this job.

    4. 4
      Run the named first test.

      Use one approved data export to define the baseline. Identify one gap. Propose two measurable experiments.

    5. 5
      Keep proof.

      Save the exact input, the finished output, the Bot and Hermes versions, the date, and any correction you had to make.

    6. 6
      Test one failure.

      Remove a required input or deny an optional connection. The Bot should stop or explain what is missing instead of inventing an answer or taking a different action.

    7. 7
      Repeat before automating.

      Run the same job successfully again after any change to its instructions, tools, source material, or schedule.

    Read the starter guideRead the role instructionsRead the Bot PassportDownload readable files (ZIP)Official Bot Mode guide
    Useful combinations

    Pair Pulse with another role

    NovaNew venture testing assistantResearcherSource-based research assistantScoutTopic and opportunity finderWriterFirst-draft writing assistantStoryBrand and message assistant
    See complete Bot Crews workflows

    Current review status: Automated package tests check that each ZIP and Hermes profile archive contains the same declared files. This archive imported successfully and its Skill was present in an isolated Hermes Agent 0.21.0 installation on September 4, 2026. Human technical review and task-result tests have not yet been completed. The Grok Bot build brief remains untested.