klingai-content-policy

Implement content policy compliance for Kling AI. Use when ensuring generated content meets guidelines or filtering inappropriate prompts. Trigger with phrases like 'klingai content policy', 'kling ai moderation', 'safe video generation', 'klingai content filter'.

Install with Tessl CLI

npx tessl i github:jeremylongshore/claude-code-plugins-plus-skills --skill klingai-content-policy

What are skills?

Review — 56%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Validation — 9 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

100%

58%

Prompt Safety Screening Module

Content filter with categories and sanitization

Criteria

Without context

With context

ContentCategory enum

14%

100%

FilterResult dataclass

42%

100%

ContentFilter class

100%

Blocked pattern: violence

83%

100%

Blocked pattern: adult content

33%

100%

Blocked pattern: dangerous/illegal

33%

100%

Warning pattern: political

100%

Warning pattern: medical/financial

100%

IGNORECASE matching

83%

100%

Sanitize map words

100%

Sanitized prompt returned

62%

100%

Strict mode blocks warnings

77%

100%

Normal mode passes warnings

77%

100%

Policy summary method

55%

100%

Without context: $0.1867 · 54s · 12 turns · 13 in / 3,375 out tokens

With context: $0.6127 · 1m 51s · 34 turns · 1,188 in / 6,288 out tokens

99%

20%

Content Violation Audit Tracker

Policy violation audit logging

Criteria

Without context

With context

PolicyViolationLogger class

50%

100%

Default log filename

100%

Prompt hash stored

100%

Prompt preview stored

100%

Violation record fields

37%

100%

UTC timestamp

100%

85%

Repeat-offender threshold

100%

Per-user violation count

100%

get_violation_stats total

50%

100%

get_violation_stats by_flag

100%

get_violation_stats unique users

100%

Persistent JSON storage

100%

Without context: $0.2479 · 56s · 16 turns · 58 in / 3,047 out tokens

With context: $0.4245 · 1m 20s · 26 turns · 1,183 in / 4,415 out tokens

59%

Video Generation Service with Content Moderation

Two-stage moderation pipeline with sanitized prompt

Criteria

Without context

With context

ContentModerationService class

57%

42%

Local filter first

100%

Optional external API stage

87%

100%

Sanitized prompt submitted

100%

Correct API endpoint

Default model kling-v1.5

100%

auto_reject parameter

Blocked prompt rejected before API

100%

generate_with_moderation method

62%

75%

Approved result structure

50%

25%

API key from environment

Without context: $0.3962 · 1m 37s · 21 turns · 21 in / 5,784 out tokens

With context: $0.6404 · 2m 27s · 29 turns · 3,441 in / 8,534 out tokens

Evaluated: about 18 hours ago
Agent: Claude Code

Table of Contents

Prompt Safety Screening Module Content Violation Audit Tracker Video Generation Service with Content Moderation

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.