agentleFS
Sign inStart free
aryaminusaryaminus/socials-assistant/skills/brand-outreach/SKILL.md

brand-outreach

Skill0 starsChanged 3 months agoMITView on GitHub

Drafts brand-pitch and collaboration outreach emails using the creator's real verified vault analytics, selects target brands, and manages the outreach pipeline. Use when the user wants to pitch brands, find sponsorship contacts, reply to brand inquiries, negotiate rates, or track outreach status. Draft-first by design — never sends without explicit human approval.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 3 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Draft-first: Always produce a draft for human review.

    line 11
  2. Very specific:

    Call socials-mcp:profile_get first: niche, audience summary, brand_categories, rate_floor, past_collaborations drive targeting and pricing.

    line 18
  3. Very specific:

    Call socials-mcp:media_kit_data.

    line 24
  4. Distinctive:

    Use the template in assets/pitch-template.md — ≤150 words, plain text, one link, numbers with windows, one clear CTA.

    line 27
  5. Very specific:

    Check socials-mcp:outreach_log_list for drafts 5–7 days old with no reply → draft a 2-line bump.

    line 33
  6. Distinctive:

    Always define: usage rights (organic vs paid amplification), exclusivity window, deliverable count, timeline, payment terms (50% upfront …

    line 39
  7. Very specific:

    When the user sends themselves: send from a custom subdomain with SPF+DKIM+DMARC, ≤25 cold emails/day after 3–4 week warmup, plain-text …

    line 43

≈ “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

brand-outreach — pitch with real numbers

Hard rules

  1. Draft-first. Always produce a draft for human review. Never send, schedule, or promise sending without the user's explicit go-ahead.
  2. Real numbers only — from socials-mcp:media_kit_data, socials-mcp:top_content, socials-mcp:compare_periods. Cite the time window of every number ("last 30 days"). If the vault lacks data, run socials-mcp:snapshot first; don't guess.
  3. Log every draft with socials-mcp:outreach_log_add; update status with socials-mcp:outreach_log_update.

Pipeline

0. Read the creator profile

Call socials-mcp:profile_get first: niche, audience summary, brand_categories, rate_floor, past_collaborations drive targeting and pricing. If empty, build it with the user (audience facts auto-fill from socials-mcp:audience_overview).

1. Target selection (help the user think)

Rank targets by audience–product fit: brands whose customers look like the creator's audience demographics (country/age from socials-mcp:audience_overview + profile brand_categories). Prefer profile.past_collaborations categories — repeat sponsors convert best. Research each brand's marketing contact name before drafting — never "Dear Sir/Madam".

2. Pull verified numbers

Call socials-mcp:media_kit_data. Extract: followers per platform, 30-day views, avg engagement rate, top 3 videos, audience highlights.

3. Draft

Use the template in assets/pitch-template.md — ≤150 words, plain text, one link, numbers with windows, one clear CTA. Rate guidance lives in references/rate-card.md; the user sets final rates.

4. Log it

socials-mcp:outreach_log_add with brand, contact email, subject, and a short pitch-angle note.

5. Follow-ups

Check socials-mcp:outreach_log_list for drafts 5–7 days old with no reply → draft a 2-line bump. Maximum one bump. Mark replied/rejected/closed honestly.

Negotiation quick answers

  • "What's your rate?" → range with deliverables, anchored mid-high.
  • Budget pushback → cut scope (fewer deliverables, shorter usage rights), not price below floor.
  • Always define: usage rights (organic vs paid amplification), exclusivity window, deliverable count, timeline, payment terms (50% upfront for new brands).

Deliverability

When the user sends themselves: send from a custom subdomain with SPF+DKIM+DMARC, ≤25 cold emails/day after 3–4 week warmup, plain-text style, no attachments in first contact. Full checklist: repo docs/email-deliverability.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.

Check your setup, free