AF xiaohongshu-ops
End-to-end Xiaohongshu (小红书 / RedNote) operations skill for setting content style, saving an operating profile, generating posts in that house style, choosing or generating suitable images, and publishing through the dedicated independent browser flow. Use when the user says things like “帮我运营小红书”, wants a Xiaohongshu operating style configured, wants ongoing post generation in a fixed house style, or wants to test or run a full Xiaohongshu publishing workflow.
As a process F 44/100 · Will not run — References files that are not bundled: references/repo-notes.md
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 · 0
✓ No critical or high findings
Files scanned: 29. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/repo-notes.md
Process rating: all ten parameters 44/100
- 0Tools and files. 1 referenced file(s) missing: references/repo-notes.md
- 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. 18 mutating operations with no state check
- 40Consistency. Frontmatter name (xiaohongshu-ops) differs from the folder (rednote-ops)
- 70When it triggers. States when to use, but not when not to
- 100Steps. 47 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Execution cost. Instruction body is 1125 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 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)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 464: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 47 items
- +4Reference files are cited in the instructions (12 of 13)
- +3All 10 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.