agentleFS
sami2919sami2919/SignalForce/skills/resource-offer/SKILL.md

resource-offer

Skill9 starsChanged 3 months agoMITView on GitHub

Use when generating blueprint-first outreach that offers a free resource instead of asking for a meeting, when targeting technical buyers who respond better to value-add than demo requests, or when implementing the resource-before-demo funnel strategy

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. Very specific:

    Use config/templates/email-sequences/resource-offer-signal.md.

    line 28
  2. Distinctive:

    Run each email through these passes before output:

    line 31
  3. Distinctive:

    Before output, check each email:

    line 42

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Resource Offer

Why Resource-First

Technical buyers — domain researchers, ML leads, senior engineers — route unsolicited demo asks to the trash. They respond to peers sharing useful knowledge. Offering a free, relevant resource before asking for anything converts at 50% reply rate vs. 8-15% for demo asks. Default to this for ICP Tier 1 and Tier 3 accounts.

Input

  • Signal type: github | arxiv | hiring | funding | huggingface
  • Signal payload: specific repo / paper / job title / round (be precise)
  • Contact: name, title, company
  • Company research from prospect-researcher

Workflow

Step 1 — Select the resource. Match signal type to resource using the table in config/templates/email-sequences/resource-offer-signal.md. The resource must be relevant to the specific signal, not generic.

Step 2 — Extract a concrete insight. Identify one specific, non-obvious takeaway from the resource that applies to this prospect's situation. This becomes the Email 2 payload. Vague insights fail. Specific, quantified ones work.

Step 3 — Generate the sequence. Use config/templates/email-sequences/resource-offer-signal.md. Write all three variants (Problem-Focused, Outcome-Focused, Social-Proof-Focused). Fill every placeholder with signal-specific content — no generic substitutions.

Step 4 — Seven Sweeps copy review. Run each email through these passes before output:

  1. Clarity — Can the reader understand every sentence? Flag jargon, buried points.
  2. Voice — Does it sound like a peer, not a vendor? Read it aloud.
  3. So What? — Does every claim answer "why should I care?" Add "which means..." bridges from features to benefits.
  4. Prove It — Is every claim substantiated? No vague social proof ("trusted by thousands"). Use specific numbers.
  5. Specificity — Replace vague language with numbers and timeframes. "Save time" → "Save 4 hours/week."
  6. Emotion — Does the copy make the reader feel something? Paint the "before" state vividly.
  7. Zero Risk — Have we removed every barrier? Near CTAs, check for unanswered objections.

Step 5 — Final verify. Before output, check each email:

  • Email 1 and 2 contain zero meeting asks
  • Email 3 offers only a resource walkthrough, not a demo
  • First sentence references the exact signal
  • No banned phrases (see config/gtm-context.md)
  • 4 sentences max per email
  • Subject line is 2-4 words, lowercase, no punctuation
  • Passed all seven sweeps

Output

Present all 3 variants with their 3-email sequences. End with:

Recommended pick: [Variant X] — [one-sentence rationale tied to their ICP tier and signal type]

Resource selected: [Resource title] — [one sentence on why this resource fits this signal]

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.