Hire an AI two-week social post and results reviewer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A calendar and ready posts for each platform
• A sharing score for each post, with the weakest reason and one change
• Engagement rates, a post ranking and what to post next
• A reason the worst post failed and the one change to make

How it does the job well

• Write for one named audience and one action. Each asset has a single job.
• Use the customer's own words from reviews, calls or surveys before inventing language.
• Every claim needs proof the business can show. Leave unproven claims out or mark them.
• Judge results against the business goal, such as profit or qualified leads, not clicks alone.

Mistakes it avoids

• Generic copy that could fit any brand.
• Comparing periods or campaigns that are not comparable, such as different dates, budgets or tracking.
• Calling a test winner before there is enough data.

What a good result looks like

An example, not your task: You post often but have no proof of what works.

• Step 1: Calendar and posts. Topics, a mix of post types, a two-week calendar and the written posts for each platform.
• Step 2: Sharing check. Six ratings per post with quotes, a score out of 30, the weakest reason and one change.
• Pause. You post for two weeks, then export your numbers from each platform.
• Step 3: Results. Engagement rate for each post, a platform comparison, a ranking and what to post next.
• Step 4: Flop diagnosis. Whether the worst post was unseen, skipped or ignored, and the one change to make.
• Hand-back summary. Each step's file and every MISSING line in one list.

How the work is checked

• Every rating in the sharing check quotes the part of the post that earns it.
• Engagement is worked out the same way for every post, so the posts can be compared.
• The flop is placed in one cause (unseen, skipped or ignored) with the number that shows it.
• The next-post advice follows from your numbers, not from a general rule.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Jonah Berger and Gary Vaynerchuk would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Plan and write the posts. Sets topics and a mix of post types, lays out a calendar and writes the posts for each platform.
• Check each post for sharing. Rates every post on six reasons people pass things on, quotes the part that earns each, and names the weakest with one change.
• Post and export (you). You post for two weeks, then export reach, likes, comments, shares and clicks for each post.
• Read the numbers. Works out the engagement rate per post, compares each platform with your own past posts, ranks the posts and says what to post next. It uses a benchmark only if you give a source and date for it.
• Diagnose the flop. Takes the worst post and tells apart three causes. Few people saw it, they skipped it, or they saw it and did not care. Then it gives the one change.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id post-for-two-weeks-and-learn-what-worked-and-flopped only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/post-for-two-weeks-and-learn-what-worked-and-flopped/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• The platforms you use and your goal
• Your brand file (optional)
• Who you want to reach (optional)
• Your post numbers after two weeks (reach, likes, comments, shares, clicks and impressions)
• Numbers for your past posts, to compare against (optional)

Tools and access

• Any good chat AI: Rating a draft against fixed reasons is text work any strong chat AI does well with this skill.

Functions and deliverables

• Two-week social post and results reviewer: Share platforms, goals and brand facts. Get post drafts, sharing checks and a results review after two weeks of real posts.
  • A calendar and ready posts for each platform
  • A sharing score for each post, with the weakest reason and one change
  • Engagement rates, a post ranking and what to post next
  • A reason the worst post failed and the one change to make
• Social post calendar and draft writer: Name your platforms and goal. Get a content calendar and draft posts for those platforms.
  • A content calendar
  • Drafted posts for each platform
  • A topic mix
  • A reply and comment triage routine
  Source: Corey Haines.
• Shareable content checker: Check if your post or video is worth sharing. Get a score out of 30 on six reasons people pass things on, plus one change to test.
  • Six ratings from 0 to 5, each with a reason from your draft
  • A total out of 30 and how it was worked out
  • The weakest reason, named
  • One angle to test, and the one change that adds it
• Social media results analyst: Compare post results and engagement rates. See ROI only when you supply sales revenue, spend and how sales were tracked.
  • Engagement rate for each post
  • Campaign totals and activity costs; financial ROI only when its required revenue and attribution inputs are supplied
  • Comparison with platform benchmarks
  • Top and bottom posts and what to do next
  Source: Alireza Rezvani.
• Low-performing post reviewer: Find out why your X or LinkedIn post flopped. Paste the post and its numbers to learn if it was unseen, skipped or ignored, and get one fix.
  • Verdict: not seen, skipped or ignored
  • Evidence from your numbers
  • Specific changes to try
  • Honest note when numbers are missing
  Source: sickn33.
• Brand profile builder: Share your website. Get a reusable profile covering your products, customers, voice and approved claims, with sources.
  • A folder of eight plain files, from a start file for your AI to a claims list and a change log
  • A tag on every fact, and every claim marked approved, pending or banned
  • A two-sentence diagnosis of your biggest gap, and a list of what's missing and who can answer it
  • A short slice for your next step, if you name one
• Jonah Berger: Make a message easier to share or a change easier to try through Jonah Berger’s recorded research. Find the useful hook and remove barriers.
  • Your problem worked on the way Jonah Berger would: their questions, their method, their push-back
  • The answer or the work, in Jonah Berger's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Gary Vaynerchuk: Plan useful content or an audience launch using Gary Vaynerchuk’s public approach. Fit the format, give value before asking and learn from real responses.
  • Your problem worked on the way Gary Vaynerchuk would: their questions, their method, their push-back
  • The answer or the work, in Gary Vaynerchuk's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• You post often but have no proof of what works.
• You are about to start posting and want a first set you can trust.
• A post flopped and you don't know whether to rewrite it or drop the topic.

Limits to check before starting

• You have one post that flopped and want only its reason: use the Social post performance reviewer.
• You want a week of posts with no numbers read afterwards: use the Weekly social post writer.
• You want posts for one account on X and LinkedIn: use the X and LinkedIn post pair writer.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the handoff pack. It's a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Name your platforms and goal. Fix the weakest posts, then post them on the days in the calendar.
• After two weeks, export your numbers from each platform and give them back.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/post-for-two-weeks-and-learn-what-worked-and-flopped for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.