AC profile-optimization
Use to optimize a social media profile so it converts visitors into followers and followers into leads — bio, handle, name/headline field, profile picture, banner/header, link-in-bio, CTA, pinned posts, and highlights. Run when the user says "optimize my profile/bio," "write my bio," "my Instagram/LinkedIn/TikTok bio," "profile," "link in bio," "my profile isn't converting," asks about creator mode or a professional/business account, or wants their account to convert better. Reads brand-profile, voice, audience, and social-strategy first. Treats the profile as a conversion landing page — 3-second clarity, searchable-field keywords, a who/what/why bio with one CTA, a goal-matched link, and specs for the visuals, pinned posts, and highlights. Advisory: produces a ready-to-apply per-platform spec (WoopSocial publishes posts/media; it does not edit profile fields). Judges results via native profile insights, not WoopSocial analytics.
Use to optimize a social media profile so it converts visitors into followers and followers into leads — bio, handle, name/headline field, profile picture…
As a process C 62/100 · Has gaps — 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 62/100
- 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. 4 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 26 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1428 tokens
- low 11 top-level sections: this looks like several domains in one skill
- medium 9 test cases, all positive: not one "should refuse" or "should ask first"
- 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 943: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +4Structure: 12 headings
- +3Step-by-step instructions: 26 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.