AC creator-account-teardown
Take apart a creator account and walk away with your own version of it. Bring what you can see — profile screenshots, the bio, a pasted list of recent posts with their counts, a few captions — or hand it the handle: it reads profiles and recent posts on Douyin, TikTok, Xiaohongshu, Instagram, YouTube and X, and comments on the first three. This account teardown and account diagnosis workflow reads the positioning, the audience it speaks to, the content matrix behind the grid, the hook and structure pattern its best posts repeat, and the posting cadence, then turns it into a build template for your own account: a positioning line, a bio, content pillars with formats and cadence, a viral formula, and an opening plan — finishing with your first post produced, its cover rendered and its script voiced. Use it for competitor account analysis, account benchmarking and comment analysis, for a new account or a stalled one.
Take apart a creator account and walk away with your own version of it.
As a process C 64/100 · Has gaps — weak spots: result and completion, running it twice, progress reporting
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: 17. 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 64/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 8 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4012 tokens
- 100Steps. 21 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- low 10 top-level sections: this looks like several domains in one skill
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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 927: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -32 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 11 headings
- +3Step-by-step instructions: 21 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (11 of 11)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.