AB LinkedIn Post Optimizer
Takes an existing LinkedIn draft and returns a fully optimized version with a change log explaining every decision. Use when a user pastes a LinkedIn post and asks to optimize, improve, rewrite, fix, or strengthen it — trigger phrases include "optimize this LinkedIn post," "make this LinkedIn post stronger," "rewrite my LinkedIn post," "fix this LinkedIn post," "improve my LinkedIn post," "my LinkedIn post isn't performing," "can you punch up this draft," or "make this post better." This is an optimizer, not a writer — it requires an existing draft as input.
As a process B 67/100 · Nearly there — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- 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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - note
frontmatter-keyunknown frontmatter key "slug"
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
- 40Consistency. Frontmatter name (LinkedIn Post Optimizer) differs from the folder (linkedin-post-optimizer)
- 70Failures and branches. 17 branches
- 100Tools and files. No external tools needed
- 100Steps. 42 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 2602 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 564: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 42 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.