AC editorial-review
This skill should be used when the user asks for a "sensitivity reader", "authenticity reader", "cultural review", "is this portrayal okay", "real people in my novel", "defamation", "can I use song lyrics", "epigraph permission", "permissions", "quote permission", "fair use", "AI disclosure", "do I need to disclose AI", "send to my editor", "editorial round", "Word file for my editor", "editor review copy", "co-author", "collaborate on a book", "shared world", "back up my book", "does this echo my source", "similarity check", "check overlap with my earlier books", or wants to run human editorial, ethics, permissions, or collaboration workflows around a story project. NOT for contracts or selling rights (use publishing) or reader feedback rounds (use feedback-triage).
This skill should be used when the user asks for a "sensitivity reader", "authenticity reader", "cultural review", "is this portrayal okay", "real people in…
As a process C 57/100 · Has gaps — References files that are not bundled: templates/github/
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
-
low Concealment
en-hide-from-userSKILL.md:115Instruction to hide actions from the user (detector / deny-list definition; "do not tell the user <a claim>" — honesty guidance, not concealment)sources nobody gave it, so never tell the user a manuscript is
detectorhonesty claim
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: templates/github/
Process rating: all ten parameters 57/100
- 0Tools and files. 1 referenced file(s) missing: templates/github/
- 0Result and completion. Does not say what the result is
- 30Running it twice. 13 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 45 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2949 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- high The skill tells the model to perform an irreversible action with no human approval
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
- +1No license
- +2Single-language instructions
- +5Description quotes 24 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 777: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 45 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.