agentleFS
fliqrlabsfliqrlabs/instagram-creator-skills/skills/ugc-brief/SKILL.md

ugc-brief

Skill5 starsChanged 20 days agoMITView on GitHub

Write the brief a brand sends to UGC creators or influencers, or the brief a creator asks a brand for: the product truth, the audience, 5 hook angles, must-say and never-say lines, shot list, deliverables and specs, usage rights, disclosure, timeline, and a keyword CTA wired to a comment-to-DM funnel so the brand can count responses. Use when the user says "UGC brief", "influencer brief", "creator brief", "brief for my campaign", "what should creators say about my product", "brief from the brand", or "UGC script".

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 2

    Distinctive

    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:

    Read: ../instagram-playbook/hooks.md, ../instagram-playbook/safety.md (disclosure, claims).

    line 23
  2. Distinctive:

    Every product claim must be one the brand can substantiate.

    line 52
  3. Distinctive:

    If a creator asks for this skill about a brand deal: write the questions to send the brand (usage rights, whitelisting, exclusivity, …

    line 57

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “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

ugc-brief

Bad briefs produce 20 identical "OMG I love this" videos. Good briefs give creators a clear truth and room to say it their own way. That's what makes UGC convert. This skill writes the good kind, and adds a way to measure it beyond views.

Read: ../instagram-playbook/hooks.md, ../instagram-playbook/safety.md (disclosure, claims).

The brief (one page per creator type)

CAMPAIGN      {name}  ·  goal: awareness / sales / app installs / leads  ·  live {dates}
PRODUCT TRUTH the one thing it does better, in a sentence a customer would say
              + 3 proof points (real: specs, results, reviews the brand can back up)
AUDIENCE      who's buying, their problem, the words they use
HOOK ANGLES   5 options, different formulas (problem/solution, before/after, honest review,
              "things I wish I knew", POV). Creators pick one or bring their own.
MUST SAY      product name · the one key benefit · the offer/code · the CTA
NEVER SAY     unapproved claims (medical, "guaranteed", "best in the world"), competitor names, prices that change
SHOT LIST     product in hand in the first 3s · in use · the result · the face for the CTA
SPECS         9:16, 15-45s, burned-in captions, original audio or licensed music, safe zones respected
DELIVERABLES  {n} reels + {n} story frames · raw files Y/N · {n} revisions
USAGE RIGHTS  organic repost / paid ads (whitelisting) · duration (e.g. 3 months) · regions. Priced separately.
DISCLOSURE    Paid partnership label + #ad, as required in each market (see the disclosure rules in safety.md)
CTA + FUNNEL  "Comment {KEYWORD} for {offer}". Each creator gets their own keyword or code so results can be attributed.
TIMELINE      brief → script approval → shoot → draft → revisions → post date

The funnel (the part most briefs miss)

Give each creator a unique keyword or code (GLOW1, GLOW2…). On the creator's account, a comment-to-dm automation delivers the brand's offer link and code. The creator approves it on their account, created paused and then activated. Afterwards, compare total_triggers per creator with sales per code. That shows which creator actually drove buyers.

Writing rules

  • Give creators angles, not scripts. A word-for-word script reads like an ad. Exceptions: compliance lines and the CTA wording.
  • Every product claim must be one the brand can substantiate. Flag anything regulated (skincare results, supplements, finance).
  • Hook angles must fit the creator's voice. Ask for the creator list, and tailor 1-2 angles per creator if there are fewer than 10.

Creator side

If a creator asks for this skill about a brand deal: write the questions to send the brand (usage rights, whitelisting, exclusivity, payment terms, revisions, disclosure), and then the brief back to them in this format. Pair it with brand-pitch for the rates.

<!-- brand:footer -->

Part of Instagram Creator Skills by Fliqr AI. Live Instagram data and comment-to-DM automations come from the Fliqr AI connector (fliqr.ai).

<!-- /brand:footer -->

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.