agentleFS
link7373link7373/agentic-sales-marketing/.claude/skills/plan-strategy/SKILL.md

plan-strategy

Skill1 starsChanged 3 months agoMITView on GitHub

Assemble the master go-to-market strategy — channel selection, budget allocation, targets, and the 90-day execution plan. Operator approval of this plan is the gate that unlocks autonomous execution. Run after research, offer, and positioning exist.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    All three files; approval to knowledge/approvals-log.md (the master entry).

    line 41

≈ “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

/plan-strategy — The Plan That Unlocks the Team

Inputs: knowledge/business-context.md, knowledge/audience-profiles.md, knowledge/offer.md, knowledge/positioning.md. Agents: Head of Growth leads; all strategists contribute; growth-analyst sets targets. Method: knowledge/methods/digital-channel-strategy.md, knowledge/methods/funnel-and-measurement.md.

Steps

  1. Verify foundations. Research, offer, and positioning exist and agree with each other. Contradictions get resolved before planning, not papered over.
  2. Pick 1–2 channels, not five. From the audience's ranked channels: where can this business, at this budget, with this operator's time, realistically earn attention? Small businesses win by concentration. Name the channels NOT chosen and why — that list prevents future drift.
  3. Design the funnel path. For each chosen channel: traffic source → destination → conversion → follow-up. B2B default: outreach/content → conversation → proposal → close. B2C default: content/marketplace presence → page/listing → purchase → post-purchase flow.
  4. Set the budget. Tools, ads (only if organic proof exists or the plan explicitly tests paid), production costs. Monthly cap and per-campaign allocations, recorded in knowledge/budget.md (approved vs spent vs return per channel — /measure maintains it weekly). $0 budgets get a $0 plan — organic channels and free tiers.
  5. Set targets with dates. Work backward from the first-sale milestone: sales needed ← conversations/conversions needed ← traffic needed. Honest math at realistic conversion rates (growth-analyst provides ranges). Then the 90-day week-by-week plan: what launches when, owned by which skill.
  6. Define "working" and "not working." Per channel: the metric, the checkpoint date, and the pivot trigger. Pre-committing to kill criteria prevents sunk-cost drift.
  7. Write the tool plan. Which tool categories the plan requires → queue /connect-tools for each before its first campaign.
  8. Present for approval. The strategy on one page: who / what we sell / where / how much / targets / what happens weeks 1–4. Walk the operator through in plain language. Their approval is THE gate — record it with scope and duration.

Before you start

  1. Required inputs: knowledge/business-context.md, knowledge/audience-profiles.md, knowledge/offer.md, knowledge/positioning.md all at seeded+ — if any is a stub, run its producing skill first (this is the one skill that hard-requires the full foundation).
  2. Scan knowledge/decision-log.md for tags channel, budget — prior channel rejections were recorded for a reason; reopening one requires naming what changed.
  3. Gate check: step 8's operator approval is the master gate — nothing executes autonomously without it.

If things go wrong

  • Foundations contradict each other → resolve in step 1 with the operator; a strategy built on contradictions fails silently later.
  • Operator rejects the plan → capture why, revise once with their input, re-present; log both versions' differences in the decision log.
  • Operator unavailable → park the one-pager in knowledge/pending.md; the team stays in strategy-pending mode (research and drafting allowed, no execution).

Outputs

knowledge/strategy.md (approved) + knowledge/channel-plan.md (per-channel detail) + knowledge/budget.md (allocations); queued next actions. Close with the report per templates/skill-report.md.

Writeback

All three files; approval to knowledge/approvals-log.md (the master entry); decisions + rejected alternatives (tags: channel, budget) to knowledge/decision-log.md.

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.