AF content-compliance-review
Review planned social-media content before publication for legal, platform-policy, account-safety, privacy, copyright, advertising, and audience-safety risks across scripts, captions, titles, comments, images, cover art, video frames, and audio. Use when a user asks for content compliance review, pre-publication risk checking, platform rule comparison, moderation-risk diagnosis, or safer revisions for one or more publishing platforms.
Review planned social-media content before publication for legal, platform-policy, account-safety, privacy, copyright, advertising, and audience-safety risks…
As a process F 28/100 · Will not run — References files that are not bundled: references/platforms/<platform>-*.md, references/platforms/<platform>.md
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.
Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.
How to improve
- The text references files that are not there: add them or drop the references.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Obfuscation
obf-hex-escape-chainreferences/laws/china-advertising.md:7Escaped/char-code string obfuscation- [中华人民共和国广告法（国家法律法规数据库）](https://flk.npc.gov.cn/detail?id=…&title=…), effective
Files scanned: 18. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/platforms/<platform>-*.md - warning
missing-refreference to a missing file: references/platforms/<platform>.md
Process rating: all ten parameters 28/100
- 0Tools and files. 2 referenced file(s) missing: references/platforms/<platform>-*.md, references/platforms/<platform>.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (content-compliance-review) differs from the folder (content-compliance-review-skill)
- 100Steps. 33 steps
- 100Execution cost. Instruction body is 1584 tokens
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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 438: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 33 items
- +4Has examples (0 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.