AB linkedin-post-writer
Use to write a LinkedIn post — professional, thought-leadership, or founder/personal-brand content optimized for LinkedIn's specific mechanics (dwell time, early comments, the "see more" hook). Run when the user says "write a LinkedIn post," "LinkedIn," "post this on LinkedIn," "thought leadership post," "founder post," or wants professional/B2B social content. Reads brand-profile and voice first, uses hook-writer for the opening line that must win the "see more" expand, formats for dwell, drives genuine comments, and routes links to the first comment to protect reach. Avoids LinkedIn cringe (broetry, engagement bait). This is the single-post craft: to "grow on LinkedIn" or set the account strategy use linkedin-growth; for company-page strategy use linkedin-company-pages; for general captions use caption-writer; for X threads use thread-writer; for the carousel slides use carousel-writer.
As a process B 67/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 67/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 31 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1526 tokens
- low 12 top-level sections: this looks like several domains in one skill
- low No test case covers injection arriving through data
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 901: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +4Structure: 13 headings
- +3Step-by-step instructions: 31 items
- +4Reference files are cited in the instructions (4 of 4)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.