Linkedin Post Autopsy
Diagnose why a LinkedIn post over- or under-performed against the seven content moves and prescribe the single highest-impact fix. Use after a post has run long enough to have real stats.
Install
$ agentstack add skill-styfinity-linkedin-engine-linkedin-post-autopsy ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
LinkedIn Post Autopsy
Every post is data. This skill reads the post against the moves that drive distribution, reads the engagement ratios, and tells you the one thing to change next time.
Inputs
- The post text and its stats (impressions, comments, reactions, saves, profile views): $ARGUMENTS
- The brief (persona, pillars, offer, pains) loads automatically.
Do this
- Score the post against the seven moves, one line each, present or missing:
- Value-lever hook (first line earns the second)
- Status reframe (shifts how the reader sees themselves or the problem)
- System, not tips (a repeatable mechanism, not a listicle)
- Quantified before/after (real numbers, attributed to a post / a client / an operator)
- Contrarian line (one claim the feed disagrees with)
- Comment-keyword CTA (asks for a specific word, not "thoughts?")
- Saveable asset (something worth keeping: a checklist, a teardown, a swipe)
- Read the ratios. Comments are the heaviest-weighted signal. An inverted ratio (more comments than reactions) is the viral fingerprint. Note reactions-to-comments, and saves and profile views as intent signals.
- Tie the ratio read back to the moves. Which present move drove the signal, which missing move capped it.
- Name the single weakest move: the one that, fixed, would have moved this post most.
Output
Return labelled: a move-by-move scorecard (seven rows, present/missing + one-line read), the ratio read (what the comments-to-reactions ratio says about distribution), and THE ONE CHANGE that would have moved it most. Hand the rewrite to /linkedin-humanizer if you redraft the hook.
Rules
- End on one fix, not a list of five. If you can't reduce to one, you haven't finished reading the stats.
- Ground every claim in the numbers given. No verdict the stats don't support.
- Attribute any quoted number to a post / a client / an operator, never a named person or company.
- No em-dashes.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: styfinity
- Source: styfinity/linkedin-engine
- License: MIT
- Homepage: https://styfinity.com
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.