grid-image-generator

图片提示词生成指南 — 角色、场景、宫格图三类提示词规范

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/grid_prompt_generator/SKILL.md

Quality

Content

80%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a concise, highly actionable set of prompt templates and rules with clean organization. Its main weaknesses are missing verification for the fragile batch panel-count requirement and references to a 'reference/' directory that is not actually provided.

Suggestions

Add an explicit verification step for grid generation, e.g. 'After composing the prompt, count the listed panels and confirm the total equals rows×cols before returning; fix any missing or merged panels.'

Either create the referenced reference/ files (character-prompt.md, scene-prompt.md, shot-prompt.md) or remove the dead '参考：reference/...' links since the templates are already inlined.

Consolidate the repeated boilerplate ('no merged panels, no missing panels, no text, no watermark') into the shared 通用规则 section to reduce duplication across the three grid-mode templates.

Dimension	Reasoning	Score
Conciseness	The body is lean: it provides template structures and tight generation rules without explaining concepts Claude already knows (no preamble on what image prompts are), and every section earns its place.	3 / 3
Actionability	It gives concrete, copy-paste-ready templates with specific constraints — exact panel counts ('exactly [rows*cols] visible panels'), dimensions ('每格 960x540'), and required phrases ('consistent art style') — leaving little ambiguity for an instruction-only skill.	3 / 3
Workflow Clarity	Generation rules and a numbered general-rules checklist give a clear procedure, but grid generation is a batch operation with heavy emphasis on exact panel counts and no verification checkpoint (e.g. 'count panels, confirm = rows×cols before returning'), which caps this at 2.	2 / 3
Progressive Disclosure	The body is well-organized with clear per-type sections and inline content, but it repeatedly references 'reference/character-prompt.md', 'reference/scene-prompt.md', and 'reference/shot-prompt.md' — files that do not exist in the bundle — so the signaled references are broken.	2 / 3
	Total	10 / 12 Passed

Description

50%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description clearly scopes the skill to image-prompt generation across three named types, but it is essentially a title plus category list rather than an action- and trigger-rich statement. It lacks concrete action verbs, a 'Use when...' trigger clause, and broader keyword coverage, leaving it adequate but not strong.

Suggestions

Add concrete action verbs and an explicit trigger clause, e.g. 'Generates character, scene, and grid-image prompts. Use when the user asks for image prompts, AI drawing prompts, or grid/panel image layouts.'

Broaden trigger-term coverage to include natural variations users might say ('AI绘图提示词', 'image generation prompt', 'panel layout', '宫格拼图').

Reframe as a third-person action statement ('Generates...') rather than a noun-phrase guide title to lift specificity.

Dimension	Reasoning	Score
Specificity	The description names the domain ('图片提示词生成指南') and enumerates three concrete categories ('角色、场景、宫格图三类提示词'), but it states scope rather than concrete actions — there are no verbs describing what the skill does.	2 / 3
Completeness	It answers 'what' (image prompt generation across three types) but provides no 'when to use' guidance; per the rubric, a missing 'Use when...' clause caps completeness at 2.	2 / 3
Trigger Term Quality	It includes some natural terms a user might say ('图片提示词', '角色', '场景', '宫格图'), but coverage is thin and missing common variations or English equivalents users may invoke.	2 / 3
Distinctiveness Conflict Risk	The grid-image (宫格图) niche is fairly specific, but without explicit triggers it could still overlap with other generic image-prompt skills.	2 / 3
	Total	8 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: chatfire-AI/huobao-drama
Path: skills/grid_prompt_generator/SKILL.md
Commit: ad1cd7c

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.