CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

intelligent-prompt-generator

智能提示词生成器 v2.0 - 支持人像/跨domain/设计三种模式,语义理解、常识推理、一致性检查

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.codex/skills/intelligent-prompt-generator/SKILL.md

The canonical home for this skill is intelligent-prompt-generator in huangserva/skill-prompt-generator

SKILL.md
Quality
Evals
Security

Quality

Content

56%Weight 40%Scale 1-5

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

The body contains genuinely concrete code and a sequenced workflow with a consistency-check feedback loop, but it is severely over-long, repeats examples, re-teaches common knowledge, and inlines everything that should live in reference files. Conflicting API entry points and a hardcoded user path slightly undermine executability.

Suggestions

Move the framework field definitions, the ElementSelector scoring algorithm, and the example bank into reference files (e.g. FRAMEWORK.md, SELECTION.md, EXAMPLES.md) and keep SKILL.md as a concise overview with one-level-deep links.

Collapse the repeated Dragon Ball walkthrough into a single example and remove explanations of common knowledge (ethnicity/eye-color, what 'anime' means) that Claude already has.

Pick one canonical generation entry point and document it; remove the hardcoded '/Users/serva/...' path and use a relative path resolved from the skill directory.

DimensionReasoningScore

Conciseness

The ~1340-line body re-explains the same Dragon Ball example three times in near-full detail and lectures on common knowledge (ethnicity→eye color, what 'anime' means), with heavy emoji/marketing padding — noticeably verbose with several padded sections.

2 / 5

Actionability

Provides concrete, copy-pasteable Python calls (CrossDomainGenerator, FrameworkDrivenGenerator, ElementSelector.select_best_element, save_generated_prompt), but gaps remain: a hardcoded personal path '/Users/serva/...' and three overlapping/conflicting entry points leave it slightly short of fully executable.

4 / 5

Workflow Clarity

A clear 步骤1–步骤6 sequence exists with an explicit consistency-check checkpoint (detect conflict → explain → auto-correct), but step numbering is broken (a duplicate '步骤4:返回提示词') and there is no validation that Python calls succeed, leaving minor validation gaps.

4 / 5

Progressive Disclosure

No bundle files exist and the entire framework spec, selection algorithm, and example bank are inlined in one 1340-line SKILL.md; section headers give some structure, but content that clearly belongs in separate reference files is not split out.

3 / 5

Total

13

/

20

Passed

Description

50%Weight 40%Scale 1-5

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 identifies the skill's domain and enumerates its modes and capabilities, but it reads as a product feature list rather than a trigger-oriented skill description. It lacks any explicit 'when to use' guidance, which caps its completeness and weakens trigger quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to generate image prompts, describes a portrait/scene/design poster, or mentions 人像/赛博朋克/古装/海报 prompts.'

Replace abstract capability labels ("语义理解、常识推理") with concrete actions ("解析用户描述,从元素库匹配光影/构图/风格,检测并修正人种与特征冲突").

Drop marketing artifacts ("v2.0", "🆕") and state the medium (image generation) explicitly so it does not collide with general prompt skills.

DimensionReasoningScore

Specificity

Names the domain ("提示词生成器") and lists three modes plus three capabilities, but the actions are abstract feature labels ("语义理解、常识推理、一致性检查") rather than concrete operations, matching the 'names domain and 1-2 concrete actions' anchor.

3 / 5

Completeness

It conveys a 'what' (a prompt generator with three modes) but has no 'Use when…' trigger clause or equivalent explicit trigger guidance, so per the rubric guideline completeness is capped at 3.

3 / 5

Trigger Term Quality

Contains some natural terms a user might say ("提示词", "人像", "设计") but is padded with product jargon ("v2.0", "跨domain") and misses common synonyms/variations, fitting the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

"提示词生成器" is fairly generic and could overlap with other prompt-related skills; the portrait/design modes narrow it toward image prompts but the word "image" never appears, so it 'could still overlap with similar skills'.

3 / 5

Total

12

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (1346 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

huangserva/skill-prompt-generator

Path

.codex/skills/intelligent-prompt-generator/SKILL.md

Reviewed

Table of Contents

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.