SKILLEMALL.ai

BF novel-writer

长篇网文 Agent 创作技能 v3.0 — 卷/事件/章四层编排、产物驱动流水线、Pre-Init 创意门禁、作者签名跨题材复用

ClawHub Hermes author: Luck_Liang v0.1.0 MIT-0 2 files body ≈ 5 083 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process F 28/100 · Will not run — References files that are not bundled: scripts/openclaw_entry.py, references/author_profile.template.json, templates/chapter_write_v142.md

GeneratorAI and agentsSoftware developmenttype and topics are labelled automatically from the skill text
JSON
Technical rating
B
76/100
safety, quality, tests
Safety 60%
100
Quality 40%
39
Run on models
none yet
Process rating
F
28/100
Will not run
References files that are not bundled: scripts/openclaw_entry.py, references/author_profile.template.json, templates/chapter_write_v142.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
  3. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  4. The text references files that are not there: add them or drop the references.
For the model run — optional
  • 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

  • warning description-long-hermes description is 65 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • warning description-no-when neither description nor a "## When to Use" section says when to use the skill
  • warning body-long SKILL.md body ≈ 5083 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: scripts/openclaw_entry.py
  • warning missing-ref reference to a missing file: references/author_profile.template.json
  • warning missing-ref reference to a missing file: templates/chapter_write_v142.md
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 28/100

Will not run. References files that are not bundled: scripts/openclaw_entry.py, references/author_profile.template.json, templates/chapter_write_v142.md
  • 0Tools and files. 3 referenced file(s) missing: scripts/openclaw_entry.py, references/author_profile.template.json, templates/chapter_write_v142.md
  • 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
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 3 mutating operations with no state check
  • 60Consistency. The Hermes dialect needs category and tags
  • 70Execution cost. Instruction body is 5083 tokens
  • 100Steps. 165 steps
  • low 20 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)
  • +3Description length 65: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -228 emoji in the instructions: noise for the model
  • +2Single-language instructions
  • +4Structure: 55 headings
  • +3Step-by-step instructions: 165 items
  • +4Has examples (10 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 39.

External checks

ClawHub: clean
This skill is a disclosed novel-writing workflow that reads and writes local story-planning files, with no evidence of hidden code, credential access, network exfiltration, or destructive behavior.
LLM: benign (high) · VirusTotal: · 9 Jul 2026