agentleFS
link7373link7373/agentic-sales-marketing/.claude/skills/run-partnerships/SKILL.md

run-partnerships

Skill1 starsChanged 3 months agoMITView on GitHub

Build earned-audience relationships — PR pitches, co-marketing partnerships, influencer collaborations, and webinars or events — from target list through outreach, terms, activation, and measurement. Run when strategy calls for credibility or reach the business can't build alone.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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. Distinctive:

    Agree terms: Start at cross-promotion with any new partner.

    line 19
  2. Very specific:

    Activate and follow through: Run the collaboration (co-marketing campaigns route to /launch-campaign.

    line 21
  3. Distinctive:

    No replies across the whole list → diagnose like outbound: the targets are wrong, or the angle leads with us rather than their audience.

    line 32

≈ “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

/run-partnerships — Borrow the Audience, Earn the Trust

Inputs: knowledge/strategy.md (earned channels must be chosen), knowledge/positioning.md, knowledge/audience-profiles.md, knowledge/partners.md, knowledge/competitors.md (who else serves this customer), knowledge/research/social-proof.md. Agents: partnerships-manager leads; copywriter writes pitches; market-researcher helps build the target list; campaign-manager runs any co-marketing campaign that results; tools-operator sets up tracking links. Method: knowledge/methods/partnerships-and-pr.md.

Steps

  1. Name what's scarce. Credibility → PR. Reach → partnerships. Desire → creators. Explanation depth → events. Pick one to run properly rather than four badly; each has a different playbook and a different failure mode.
  2. Build the target list. For partnerships: who else serves this customer at a different moment, doesn't compete, and is roughly our size? For PR: named journalists and outlets who cover this beat, with three recent pieces read per person. For creators: candidates vetted on audience fit and comment quality, never follower count. For events: the gatherings this audience already attends.
  3. Find the angle per target. What does their audience get? For PR this means finding the actual story — original data from our own customers or operations is the most reliable asset available. If no genuine angle exists for a target, remove them; a pitch without one wastes a relationship that can only be spent once.
  4. Approval gate. Operator approves the target list and the pitch templates in one batch (outbound gate). The sequence then runs autonomously including follow-ups — one follow-up per target, then stop.
  5. Reach out and give first. Where possible, do something useful for the target before pitching: share their work genuinely, send them a customer, mention them. Then the pitch: what their audience gets, why us, a small concrete proposal, and how much of the work we'll do.
  6. Agree terms. Start at cross-promotion with any new partner. Anything involving money (paid placement, revenue share, sponsorship, a stand) is a money gate — escalate with a recommendation and a budget line before committing. Record terms and the approval ref in knowledge/partners.md.
  7. Set up tracking before activation. A unique link or discount code per partner, always, at setup — it's free now and impossible to add later. Without it this channel can't be measured at all.
  8. Activate and follow through. Run the collaboration (co-marketing campaigns route to /launch-campaign; webinars follow method §5 — promote three weeks out, teach 60–70%, offer clearly, follow up within 24 hours). Deliver more than promised; the second collaboration is the one that pays.
  9. Measure and record. Per partner: reach, traffic, sales attributed, effort invested, whether it's repeatable. Judge PR in quarters, events on 90-day pipeline, creators against paid CPA. Log what's genuinely unattributable as unattributable.

Before you start

  1. Required inputs: knowledge/strategy.md approved with earned channels chosen; knowledge/positioning.md at seeded+ (a partner needs to know what we're the obvious choice for).
  2. Scan knowledge/decision-log.md for tag partnership — a partner previously declined or a relationship that ended badly is recorded history, not a fresh opportunity.
  3. Gate check: outreach = outbound gate (list + templates approved once). Any payment = money gate. Co-created public content = publishing gate. Disclosure obligations under standards/compliance.md rule 9 apply to everything paid or gifted.

If things go wrong

  • No replies across the whole list → diagnose like outbound: the targets are wrong, or the angle leads with us rather than their audience. Fix the angle before sending more.
  • A partner over-promises and under-delivers → record it honestly in knowledge/partners.md, complete our side properly anyway, and don't repeat. Reputation in a small industry travels.
  • Operator wants to exhibit at an expensive event → present the honest arithmetic (method §5): stand cost vs. a quarter's budget vs. attending deliberately without one. Recommend, then respect their call and log it.
  • A creator's audience turns out to be inflated or their content misaligned → end it before activation; a mismatched association costs more than the placement is worth.

Outputs

Live partner relationships with terms, tracking, and dated next actions; PR placements or a documented pitch cycle; webinar or event outcomes. Close with the report per templates/skill-report.md.

Writeback

knowledge/partners.md (the living record); campaigns to knowledge/campaigns/YYYY-MM-<slug>.md; results to knowledge/results-history.md; paid terms to knowledge/approvals-log.md and knowledge/budget.md; partnership decisions (tag: partnership) to knowledge/decision-log.md; a learning line to knowledge/methods/partnerships-and-pr.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.