BF novel-studio
End-to-end Chinese web novel production workflow for turning a novel idea into a structured deliverable project. Covers hot-search and trend scan, discovery discussion, requirement intake, market/topic analysis, title confirmation, story planning, outline design, character bible creation, chapter drafting, polishing, proofreading, final review, and optional Feishu Wiki sync. Use when the user wants to create, develop, optimize, or deliver a serialized novel, web fiction project, long-form Chinese fiction pipeline, or a full novel production workflow from concept to manuscript.
As a process F 66/100 · Will not run — References files that are not bundled: scripts/validate_stage_execution_result.py
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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
-
high Concealment
en-hide-from-userreferences/human-style.md:61Instruction to hide actions from the user- they do not tell the user what to do next
Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5473 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: scripts/validate_stage_execution_result.py
Process rating: all ten parameters 66/100
- 0Tools and files. 1 referenced file(s) missing: scripts/validate_stage_execution_result.py
- 30Running it twice. 12 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5473 tokens
- 100Steps. 246 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 12 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 25 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
- -323 of 30 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 583: enough signal without eating the budget
- +4Structure: 26 headings
- +3Step-by-step instructions: 246 items
- +4Reference files are cited in the instructions (40 of 45)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.