SKILLEMALL.ai

BC COS后期提示词

为 COS 照片(cosplay 角色照 / 写真)生成专业级 JSON 后期指令,可直接配合 Nano Banana (Gemini 图像模型)使用。用户在给自己的角色照做后期时使用——加特效(魔法阵、火焰、雷电、 冰霜、翅膀、光环、圣光、粒子、辉光、霓虹、雨、雪、花瓣、赛博街景)、做综合修图(身体塑形 液化、服装焕新、裙摆/披风风动效果)都在范围内。本技能会输出一份结构化的 JSON 指令: 保底规则(构图/脸/姿势不变)+ 检测分析 + 按需启用的处理模块 + 约束与光影噪点一致性。 请务必在用户提到「给照片加特效」「COS 后期」「P 图」「修图」「加魔法阵/火焰/光环/翅膀」 「液化/瘦身/塑形」「裙子飘起来/加风效」「衣服太皱了」等任何 COS 照片后期需求时使用本技能, 即使他们没有说出「提示词」或「指令」——用户提到 Nano Banana / 香蕉模型 / Gemini 图像 时也务必使用。 用户**给出照片**并问「这个效果怎么做」「分析这张图的后期」「这张图用了什么修图/特效」 「照着这张图做」「反推一下提示词」时,进入**反推模式**:观察照片、识别已有后期处理、 反推出可复现的 JSON 指令。 输出格式为**可直接导入图像处理插件的预设 JSON**(信封结构:id/title/content/category/ subCategory/refImages/_isFactory),content 内是转义后的指令 JSON 字符串。 用户提到「MJ 风格 / Midjourney / 二次元 / 动漫 / 日系 / 原画 / 官方立绘 / 厚涂 / 手绘 / 赛博朋克 / 霓虹 / 电影感 / 大片质感 / 梦幻 / 仙气 / 写实 / 极简 / 高级感」等任何**画面风格** 需求,或提到「插件预设 / 导入插件 / 预设格式 / 提示词模板」时,也务必使用本技能——内置 MJ 风格知识库,能把风格需求转译成可执行的指令措辞。 用户问「这是什么风格 / 识别这张图的风格 / 分析画风 / 这个风格叫什么 / 这个风格怎么做」时, 进入**风格识别**:对照风格库识别照片或描述的风格,输出可用的风格预设;用户提供**新风格** 时,可**学习**入库(styles-learned.md),之后生成可直接调用。

ClawHub Agent Skills author: Aleaaaan v1.0.0 MIT-0 13 files body ≈ 2 670 tokens Open the sourceclawhub.ai analyzed 2 d ago

为 COS 照片(cosplay 角色照 / 写真)生成专业级 JSON 后期指令,可直接配合 Nano Banana (Gemini 图像模型)使用。用户在给自己的角色照做后期时使用——加特效(魔法阵、火焰、雷电、 冰霜、翅膀、光环、圣光、粒子、辉光、霓虹、雨、雪、花瓣、赛博街景)、做综合修图(身体塑形…

As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
B
86/100
safety, quality, tests
Safety 60%
100
Quality 40%
65
Run on models
none yet
Process rating
C
51/100
Has gaps
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

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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: 12. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 51/100

  • 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
  • 30Running it twice. 1 mutating operations with no state check
  • 40Consistency. Frontmatter name (COS后期提示词) differs from the folder (cos-effect-prompt-main)
  • 50Failures and branches. 0 branches, has a failure section
  • 100Tools and files. No external tools needed
  • 100Steps. 72 steps
  • 100Execution cost. Instruction body is 2670 tokens

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 985: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • +2Single-language instructions
  • +4Structure: 26 headings
  • +3Step-by-step instructions: 72 items
  • +4Has examples (7 code blocks)
  • +4Reference files are cited in the instructions (6 of 6)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.

External checks

ClawHub: clean
This is a disclosed COS photo prompt generator, with some local file-writing and learning behavior users should understand before installing.
LLM: benign (medium) · VirusTotal: · 21 Aug 2026