paid-social-brief
Skill417 starsChanged 3 months agoMITView on GitHub
Use when an approved social campaign needs a media-ready brief for paid distribution, creative testing, and measurement. Trigger phrases include "brief paid social", "plan this ad test", "turn this campaign into paid", "what should we test in ads?", and "make a Meta or LinkedIn ad brief". Do not use this to claim ad-account access, launch spend, bypass platform policy, or invent targeting capabilities; use campaign-brief for the source strategy, utm-campaign-plan for tracking conventions, and social-analytics-report for results interpretation.
In this repository54 other files it gives its agents.
- ab-hook-testerSkill
- agent-reachSkill
- ai-brainSkill
- analytics-readoutSkill
- audience-personasSkill
- best-time-schedulerSkill
- bio-profile-optimizerSkill
- b-roll-shot-listSkill
- campaign-briefSkill
- caption-and-hashtagsSkill
- carousel-builderSkill
- collab-outreachSkill
- comment-miningSkill
- comment-responderSkill
- community-engagement-planSkill
- competitor-positioningSkill
- competitor-teardownSkill
- content-auditSkill
- content-calendarSkill
- content-factorySkill
- content-pillar-builderSkill
- content-repurposerSkill
- content-researchSkill
- cover-thumbnail-briefSkill
- creator-outreachSkill
- cross-platform-distributionSkill
- cross-platform-reformatterSkill
- cta-writerSkill
- dm-script-writerSkill
- going-viralSkill
- hashtag-keyword-researchSkill
- hook-miningSkill
- humanizerSkill
- influencer-partnershipsSkill
- launch-retrospectiveSkill
- linkedin-thought-leadershipSkill
- on-screen-text-writerSkill
- positioning-auditSkill
- profile-conversion-auditSkill
- reel-analyzerSkill
- reel-builderSkill
- reel-scripterSkill
- series-plannerSkill
- social-analytics-reportSkill
- social-listeningSkill
- social-proof-miningSkill
- story-sequencerSkill
- trend-spotterSkill
- ugc-creator-briefSkill
- utm-campaign-planSkill
- viral-carouselSkill
- viral-hook-writerSkill
- viralitySkill
- x-thread-strategySkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Ask for the campaign objective, offer, claim boundary, landing destination, proof, audience evidence, budget range if supplied, policy …
- Distinctive: line 28
Do not claim access to ad accounts, audiences, pixels, spend, or platform features you do not have.
- Distinctive: line 29
Never target or exclude sensitive groups in a way that violates law, policy, or the approved brief.
- Distinctive: line 30
Do not use unsubstantiated performance, health, financial, or customer-result claims.
- Distinctive: line 31
Do not optimize solely for cheap clicks when the campaign's intended action is elsewhere.
- Distinctive: line 32
Keep organic and paid results labelled separately in every report.
- Distinctive: line 45
Use campaign-brief and positioning-audit before this skill.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.
Files
Paid Social Brief
Translate an approved campaign into testable paid-social decisions without pretending media execution or platform access exists.
1. Confirm the approved foundation
Ask for the campaign objective, offer, claim boundary, landing destination, proof, audience evidence, budget range if supplied, policy constraints, and the owner who can actually configure the platform. If the offer or landing page is unapproved, do not write ads around it.
2. Define the test, not a prediction
State the hypothesis, audience context, creative angle, desired action, measurement event, and what would count as useful learning. Separate audience hypotheses from targeting settings because platform availability and policy can change. Keep the number of simultaneous variables small enough to interpret.
3. Specify creative and destination requirements
List the approved message variants, proof assets, disclosures, format needs, destination expectation, exclusions, and prohibited claims. Tie each creative to a hypothesis. Note where a native platform review or legal approval is required rather than claiming it is complete.
4. Set guardrails for operation and review
Provide the budget and pacing decisions only when supplied by an authorised owner; otherwise mark them open. Define launch checks, reporting window, stop or revise conditions, and the exact data needed for a review. Ensure tracked links follow the agreed UTM plan.
Hard rules
- Do not claim access to ad accounts, audiences, pixels, spend, or platform features you do not have.
- Never target or exclude sensitive groups in a way that violates law, policy, or the approved brief.
- Do not use unsubstantiated performance, health, financial, or customer-result claims.
- Do not optimize solely for cheap clicks when the campaign's intended action is elsewhere.
- Keep organic and paid results labelled separately in every report.
Failure modes
| Failure | Do this instead |
| A media brief is only ad copy | Define the hypothesis, audience context, measurement, and decision threshold. |
| Too many variables change at once | Limit the first test to the few variables needed to answer one question. |
| Creative promises more than the destination delivers | Align every claim with the approved landing experience and proof. |
| Results cannot be attributed | Create the UTM and measurement plan before launch. |
Where it sits
Use campaign-brief and positioning-audit before this skill. Use utm-campaign-plan to make link naming consistent and cross-platform-distribution to distinguish paid from owned work. Use social-analytics-report for operating decisions and launch-retrospective for the full review.
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
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.

