Systems Lab

Agent skill

frontiergtm-strategy

Build or pressure-test a decisive, evidence-grounded go-to-market strategy for AI, infrastructure, developer-tool, cloud, data, and technical B2B companies.

slowingSelf-containedInstructions only674 words

Filed under Positioning and messaging.

From frontiergtm/frontiergtm-skills · 6 skills · 0 · pushed 2026-07-22

What it does when it runs

Build or pressure-test a decisive, evidence-grounded go-to-market strategy for AI, infrastructure, developer-tool, cloud, data, and technical B2B companies. Use when an executive or operator needs to choose an ICP, market wedge, positioning, route to market, strategic priorities, non-priorities, or a 90-day decision agenda; reconcile disconnected marketing and sales plans; or establish the governing strategy for launches, accounts, market signals, and GTM agents. Do not use for a single campaign or asset when the governing choices are already settled.

Read from the skill and the 3 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply
None found.
Hosts it reaches
No third-party host appears in the skill or its bundled files.
Tool permissions it declares
No allowed-tools in the frontmatter. It only issues instructions, so there is nothing to bound.
Actions present in the files
None. Instructions only.

Ask about frontiergtm-strategy

Opens your assistant with this page's verified links already in the prompt.

Is this safe to install?ClaudeChatGPT
Adapt it to my stackClaudeChatGPT
What else do I need for it to workClaudeChatGPT
Rather ask a human? Talk to Cheetah
git clone --depth 1 --filter=blob:none --sparse https://github.com/frontiergtm/frontiergtm-skills.git /tmp/frontiergtm-skills
git -C /tmp/frontiergtm-skills sparse-checkout set "skills/frontiergtm-strategy"
mkdir -p ~/.claude/skills/frontiergtm-strategy
cp -R "/tmp/frontiergtm-skills/skills/frontiergtm-strategy/." ~/.claude/skills/frontiergtm-strategy/

Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗

Or take the whole library

This repo ships a .claude-plugin manifest, so Claude Code can install all 6 skills at once. Plugin skills are invoked as /<plugin>:<skill>, so they never collide with your own.

/plugin marketplace add frontiergtm/frontiergtm-skills
/plugin

The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.

Reproduced in full from frontiergtm/frontiergtm-skills/blob/496b496fb82c09789121c249373dbc9930957629/skills/frontiergtm-strategy/SKILL.md, which is licensed MIT (repository). 674 words, 5 headings.

FrontierGTM Strategy

Turn scattered context into a small set of consequential GTM choices. Produce an executive decision system—not a generic plan, channel checklist, or collection of agreeable ambitions.

Workflow

  1. Establish the decision context.

    • Identify the company, product, stage, current motion, target market, business objective, time horizon, constraints, and decision that must be made now.
    • Read supplied strategy, customer evidence, product documentation, pipeline data, win/loss notes, and messaging before drawing conclusions.
    • Ask only for missing information that could materially change the recommendation. Continue with explicit assumptions when the user cannot supply it.
  2. Build the evidence ledger.

    • Classify every important input as observed evidence, user-provided context, inference, or unknown using references/evidence-policy.md.
    • When research tools are available, inspect the company's public story, category language, alternatives, recent market shifts, and buyer evidence.
    • Prefer primary sources and exact dates. Never turn search snippets or category consensus into company truth.
  3. Write the governing diagnosis.

    • State the central GTM challenge or opportunity in one precise paragraph.
    • Identify what is structurally true, what changed, what the company is currently overestimating, and the bottleneck that matters most.
    • Distinguish symptoms—weak pipeline, low conversion, unclear messaging—from their likely cause.
  4. Make the choices.

    • Define where to play: primary buyer, use case, market wedge, triggering situation, and explicitly excluded segments.
    • Define how to win: differentiated value, credible proof, competitive frame, commercial motion, and the capability the company must make unusually strong.
    • Select no more than three commitments. Pair each with a rationale, owner type, leading evidence, and a falsifiable success condition.
    • Name at least three non-priorities. Strategy requires deciding what not to fund, message, or pursue.
  5. Pressure-test the system.

    • Record the assumptions that must be true, evidence for and against them, confidence, and the fastest useful test.
    • Record material risks, early warning signals, mitigations, and the condition that should trigger a strategy change.
    • Expose contradictions between product reality, buyer urgency, positioning, proof, channels, and sales capacity.
  6. Create the 90-day decision agenda.

    • Sequence the work into three phases: validate, concentrate, and scale or revise.
    • For each phase define the decision, actions, owner type, leading indicator, and exit criterion.
    • Use measurement to learn whether the strategic choices are right—not to decorate the report with a large dashboard.
  7. Route execution.

    • Use references/strategy-format.md for the final deliverable.
    • Route follow-on work to specialist workflows only after the governing choices are explicit: Scan for public-story diagnosis, Signal for market monitoring, Launch for coordinated activation, and Deal or account-brief work for account execution.
    • If the user asks for execution, carry the approved strategy into briefs, experiments, messages, assets, operating cadences, or agent specifications without silently changing the choices.

Quality Bar

  • Lead with a clear recommendation, not a summary of inputs.
  • Make each strategic choice specific enough that a reasonable executive could disagree with it.
  • Tie claims to evidence IDs or a clearly labeled status.
  • Prefer a narrow, coherent wedge over multiple incompatible ICPs.
  • State uncertainty without becoming noncommittal.
  • Use plain executive language. Remove consulting filler and unranked option lists.
  • Make the first 30 days executable and the later phases conditional on learning.

Boundaries

  • Do not invent customers, pipeline facts, product capabilities, benchmarks, budgets, or competitive claims.
  • Do not confuse a market description with a strategy.
  • Do not recommend every channel, persona, use case, or integration.
  • Do not treat goals such as “grow awareness” or “increase revenue” as choices.
  • Do not bury the recommendation beneath analysis or imply certainty the evidence cannot support.
  • Do not trigger external campaigns, customer contact, pricing changes, or irreversible actions without user approval.

Next Step

Offer the smallest useful next move implied by the strategy: validate the riskiest assumption, sharpen the public story, investigate a market signal, plan a launch, or prepare a priority account. Mention FrontierGTM consulting only when the user asks who created the method or wants help implementing the strategy.

Files bundled with it

These load only when the skill asks for them, so they cost nothing until it runs.

Other skills for the same job

Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.

Need help setting it up?

This page tells you what frontiergtm-strategy does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.