AB novel-writing
Use this skill whenever the user wants to write, create, continue, or plan short stories (短篇), medium-length novellas (中篇), or full-length novels (长篇小说). Triggers: "写小说", "创作小说", "短篇小说", "中篇小说", "长篇小说", "小说大纲", "写故事", "续写", "小说情节" etc. Always ensure: - 记叙文三要素 (Time, Place, Characters) are clearly incorporated. - Rich application of rhetorical devices (修辞手法): metaphor, personification, simile, symbolism, foreshadowing, parallelism, sensory description, irony, etc. - Detailed descriptions: actions (动作描写), psychology (心理描写), dialogue/language (语言描写). - Multiple characters (多人) with interactions, distinct voices, and relationships. - Story is coherent, logical progression, natural transitions. - High readability: engaging language, vivid descriptions, emotional resonance, suitable pacing, Chinese literary style (can use idioms, classical allusions when fitting).
As a process B 79/100 · Nearly there — weak spots: 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: 2. 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 79/100
- 0Progress reporting. Says nothing while it works
- 55Failures and branches. 1 branches
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 45 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 787 tokens
- 100Running it twice. No mutating operations
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 870: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 10 headings
- +3Step-by-step instructions: 45 items
- +3Output format is stated explicitly
- +4Has examples (0 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.