SKILLEMALL.ai
GitHub ↗ RU Sign in

BD huo15-img-prompt

火一五文生图提示词 v3.2 — AI 创作生态中枢，14 件套 + ⭐v3.2 审美锚点系统：88 预设新增 aesthetic_anchor 字段（每个预设映射到具体导演 / 摄影师 / 艺术家 / 电影场景，赛博朋克→Roger Deakins 银翼杀手 2049 / 汉服写真→张叔平一代宗师 / ghibli→千与千寻汤屋窗景）+ 15 个 Master 档设计师级预设（Pentagram / Saul Bass / Massimo Vignelli / Wim Crouwel / Paul Rand / Tibor Kalman / Stefan Sagmeister / Paula Scher / Otl Aicher / Bruno Munari / 杉本博司 / 原研哉 / 安藤忠雄 / 王家卫 / Wes Anderson）。适配 Midjourney/SD/SDXL/Flux/DALL-E 3。触发词：文生图、火一五文生图提示词、文生视频、提示词增强、故事板、storyboard、剧本拆分、关键帧、视频脚本包、品牌套件、brand kit、品牌规范、风格学习、style learn、自学习预设、learned preset、参考图学习、Claude Vision、闭环迭代、五维评审、A/B 测试、角色卡、MCP server、Web UI、Obsidian 集成、Replicate、Fal、即梦、可灵、Hailuo、Sora、Claude Code、Cursor、aesthetic anchor、审美锚点、Master 档预设、设计师级预设、Pentagram、Saul Bass、Massimo Vignelli、Roger Deakins、王家卫、张叔平、杉本博司。

ClawHub Agent Skills author: Job Zhao v3.2.0 MIT-0 30 files · 1 script body ≈ 6 298 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureObsidianAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
80/100
safety, quality, tests
Safety 60%
90
Quality 40%
64
Run on models
none yet
Process rating
D
49/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

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. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 2

✓ No critical or high findings

Medium and low: 2
  • medium Exfiltration net-redirectable-api-key scripts/claude_polish.py:42
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Exfiltration net-redirectable-api-key scripts/image_review.py:41
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment

Files scanned: 29. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 6298 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "displayName"
  • note frontmatter-key unknown frontmatter key "aliases"

Process rating: all ten parameters 49/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (python) that frontmatter does not declare
  • 70Execution cost. Instruction body is 6298 tokens
  • 100Steps. 66 steps
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. No mutating operations
  • low 18 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (6 tags): a typed call is more reliable

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
  • -2localhost URLs: will not work for another user
  • -239 emoji in the instructions: noise for the model
  • +2Single-language instructions
  • +3Description length 756: enough signal without eating the budget
  • +4Structure: 58 headings
  • +3Step-by-step instructions: 66 items
  • +4Has examples (31 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)
  • +3All 15 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 64.

External checks

ClawHub: suspicious
This is a real image-prompt toolkit, but it includes prompt-safety bypass helpers and several under-scoped data, credential, and persistence behaviors that warrant review before installation.
LLM: suspicious (high) · 29 May 2026