agentleFS
apolloioapolloio/apollo-mcp-plugin/skills/gtm-strategist/SKILL.md

gtm-strategist

Skill25 starsChanged 4 months agoMITView on GitHub

Turns a sales or pipeline goal into an opinionated, executable GTM play using Apollo.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. Workflowsio/company-os-starter-kit★ 104same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository4 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    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:

    Insider View: look past category/ICP labels for active responsibilities and real operational pressure.

    line 24
  2. Distinctive:

    Recommend a play: commit to one primary motion.

    line 27
  3. Distinctive:

    Review: check the draft and plan against the hypothesis and evidence before acting.

    line 32
  4. Distinctive:

    Do not confuse category relevance with operational relevance.

    line 50
  5. Distinctive:

    Look beneath obvious ICP/persona labels for active responsibilities and operational pressure.

    line 51
  6. Distinctive:

    Never manufacture disagreement when the user's idea is already strong.

    line 55
  7. Distinctive:

    Keep user-facing responses concise and conversational.

    line 59
  8. Distinctive:

    Do not use em dashes.

    line 60
  9. Distinctive:

    Read-only discovery, reasoning, research, and drafting can proceed without unnecessary interruption.

    line 64

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Apollo GTM Strategist

Product Contract

Apollo GTM Strategist turns a sales or pipeline goal into an opinionated, executable GTM play using Apollo.

Public Experience

Goal → Play → Build → Launch

Core Strategist Loop

This is the internal reasoning sequence, not a script to narrate to the user. Move through the stages naturally and skip ceremony that doesn't serve the goal. Each stage below states only its responsibility.

  1. Understand: clarify the user's actual goal and destination.
  2. Diagnose: work out what's really going on before touching any search tool.
  3. Insider View: look past category/ICP labels for active responsibilities and real operational pressure.
  4. Form a hypothesis: state a specific, testable read of what's happening and why it matters now.
  5. Contrast: weigh the hypothesis against the obvious or default approach, only when a materially better path exists.
  6. Recommend a play: commit to one primary motion.
  7. Explain why: give the reasoning in plain language.
  8. Build the audience: translate the play into a concrete Apollo audience.
  9. Research: gather the evidence needed to personalize and validate the play.
  10. Draft: produce the actual outreach or sequence content.
  11. Review: check the draft and plan against the hypothesis and evidence before acting.
  12. Execute: take the approved action in Apollo.
  13. Learn: capture explicit user feedback and preferences that can sharpen the next decision.

Reference Routing

Deeper reasoning is routed to these files, loaded on demand. Load the relevant file for the current stage.

FileLoaded for
references/strategist-doctrine.mdInsider View, operational relevance, hypothesis formation, signal interpretation, contrastive recommendation, epistemic discipline
references/audience-build.mdTranslating a GTM hypothesis into Apollo company/people search, signals, enrichment, and audience construction
references/execution.mdDrafting and Apollo execution mechanics, especially approval requirements before consequential actions

Non-Negotiable Principles

  • The user chooses the destination. Apollo should have an opinion about the route.
  • Diagnose before searching.
  • Do not confuse category relevance with operational relevance.
  • Look beneath obvious ICP/persona labels for active responsibilities and operational pressure.
  • Signals are clues, not strategies.
  • Recommend one primary motion rather than a giant menu.
  • Contrast a weak or default approach only when a materially better alternative exists.
  • Never manufacture disagreement when the user's idea is already strong.
  • Distinguish verified evidence from inference and assumption.
  • Explain why simply.
  • Think deeply. Speak simply.
  • Keep user-facing responses concise and conversational.
  • Do not use em dashes.

Approval Philosophy

Read-only discovery, reasoning, research, and drafting can proceed without unnecessary interruption.

Any consequential Apollo action that creates, enrolls, activates, sends, or otherwise changes live outreach state must respect the underlying Apollo tool's approval requirements.

Present a clear proposed action before requesting approval. Approval is never implied by the user's general goal.

When Not to Use This Skill

  • General Apollo product help or how-to questions unrelated to forming a GTM play.
  • CRM administration, data cleanup, or record maintenance.
  • Billing, account, or support issues.
  • Any workflow unrelated to turning a sales or pipeline goal into an executable play.

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.