analyze-performance
Skill1 starsChanged 41 days agoMITView on GitHub
Pull analytics from Upload-Post (account-level and post-level), summarise what is working, and suggest content moves. Use when the user asks about analytics, performance, engagement, impressions, reach, top posts, or what to post next.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- athina-ai/goose-skillstheir own version, first seen Nov 9, 2026
- gooseworks-ai/goose-skillstheir own version, first seen Nov 1, 2026
- microsoft/power-platform-skillstheir own version, first seen Nov 1, 2026
- r3bl-org/r3bl-open-coretheir own version, first seen Oct 17, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- athina-ai/goose-skills★ 1.3ksame name
- gooseworks-ai/goose-skills★ 1.3ksame name
- microsoft/power-platform-skills★ 1.1ksame name
- r3bl-org/r3bl-open-core★ 486same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository7 other files it gives its agents.
- autodm-setupSkill
- manage-commentsSkill
- posting-queueSkill
- repurpose-videoSkill
- schedule-campaignSkill
- setupSkill
- whitelabel-connectSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
3
Distinctive
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
Before calling tools, narrow down:
- Distinctive: line 19
If the user is vague, default to: all connected accounts, last 28 days, engagement rate.
- Distinctive: line 23
Call the analytics tools in parallel:
“Common” is measured: kept by at least 6 in 10 of the 4 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.
Files
Analyse account performance
Pulling raw numbers is easy. The value is in the interpretation. Do both.
1. Scope the question
Before calling tools, narrow down:
- One platform or all of them?
- One account or the whole portfolio?
- Time window (default to last 28 days)?
- Headline metric (reach, engagement rate, follower growth, DM conversion)?
If the user is vague, default to: all connected accounts, last 28 days, engagement rate.
2. Fetch
Call the analytics tools in parallel:
get_analyticswithprofileUsername— overall snapshot for the profile.get_total_impressionswithprofileUsername— headline number across platforms.get_platform_metrics— per-platform breakdown for the workspace.get_post_analyticswithrequestId— deep dive on a specific upload.get_history— paginated log of what was actually published, and when. Use it to build the denominator (posting cadence) that the engagement numbers hang off.manage_autodmswithaction: "status"anduser— AutoDM counters, if any are running.
For qualitative signal, get_post_comments on the top and bottom post is worth more than another metric: what people actually said explains the numbers.
3. Summarise
Lead with the headline number and the delta vs the previous period. Then three bullets:
- What worked: the top post, why it stood out (format, length, hook).
- What underperformed: the bottom post, with a guess at why.
- One concrete next move: not "post more reels" — something specific like "your 25–35s reels with a face-cam hook are 3x your other content; cut two more from your last livestream."
4. Hand off to action
If the user agrees with the next move, route them to the right skill: repurpose-video if it is about shorts, schedule-campaign if they have content ready, posting-queue if the problem is cadence rather than content, manage-comments if the win is in replying, autodm-setup if the action is about converting engagement into leads.
Cross-platform comparisons
Be careful comparing raw impressions across platforms — TikTok and YouTube Shorts inflate views vs Instagram. Compare engagement rate (engagements / reach) instead.
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.