AC novel-writing
Assists with writing novels, serialized fiction, and long-form fiction — building a story bible, designing outlines with foreshadowing, generating chapters with pacing/consistency checklists, catching character or plot drift, recovering from writer's block, polishing prose to remove "AI-flavored" writing, and scoring/reviewing chapter quality. Trigger this skill whenever the user wants to write a novel/story/chapter, asks to "continue my novel", "write the next chapter", design a story outline, character sheet, or foreshadowing tracker, says they're stuck/blocked on what happens next, wants to polish/rewrite a draft, wants a quality review or score for a chapter, or mentions 写小说、写故事、网文、续写、下一章、故事大纲、故事圣经、人物设定、伏笔、卡文、润色、精修、去AI味、改写、评审、打分 or similar phrases — even if they don't use the word "skill" explicitly.
Assists with writing novels, serialized fiction, and long-form fiction — building a story bible, designing outlines with foreshadowing, generating chapters…
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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: 0. 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 58/100
- 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
- 40Consistency. Frontmatter name (novel-writing) differs from the folder (flowdream-novel-writing)
- 100Tools and files. No external tools needed
- 100Steps. 34 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 1099 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
- +3Description length 815: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 14 headings
- +3Step-by-step instructions: 34 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 94.