klingai-content-policy

Implement content policy compliance for Kling AI prompts and outputs. Use when filtering user prompts or handling moderation. Trigger with phrases like 'klingai content policy', 'kling ai moderation', 'safe video generation', 'klingai content filter'.

Quality

75%

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 ./plugins/saas-packs/klingai-pack/skills/klingai-content-policy/SKILL.md

Quality

Content

68%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 content is highly actionable with executable code and mostly concise, but it inlines full implementations that duplicate unreferenced bundle files and lacks an explicit validate/retry feedback loop for policy rejections.

Suggestions

Replace the inlined PromptFilter/SafeKlingClient/handle_policy_rejection implementations with concise summaries and link to the corresponding references/*.md files (e.g. 'See [content-filter-implementation.md](references/content-filter-implementation.md)'), so the bundle structure is actually navigable.

Add an explicit rejection-handling workflow with a validation checkpoint: on content_policy_violation, surface the blocked reason, prompt the user to revise, and re-run the filter before resubmitting.

Either populate references/examples.md with concrete worked examples or remove it, since it currently only says 'See code examples above'.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient: direct overview, a compact category table, and runnable code with minimal preamble, though a few inline docstrings and comments ('to save credits') could be trimmed.	4 / 5
Actionability	Provides complete, copy-paste-ready Python (PromptFilter, safe_request, SafeKlingClient, handle_policy_rejection) covering the common cases of pre-submission filtering, request building, and rejection handling.	5 / 5
Workflow Clarity	The filter-then-submit-then-handle flow is implicit in the code and a numbered best-practices list exists, but there is no explicit validation checkpoint or revise-and-retry feedback loop for rejected prompts, which the rubric caps at 3 for filter/batch-style operations.	3 / 5
Progressive Disclosure	Five reference files exist (content-filter-implementation, content-moderation-service, errors, examples, policy-violation-logger) but the body never links to or signals them, while full implementations that belong in those files are inlined; references/examples.md is effectively empty.	2 / 5
	Total	14 / 20 Passed

Description

82%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 is well-structured with explicit what/when guidance and product-specific triggers that make it highly distinguishable. Its main weakness is specificity, where the stated actions ('filtering', 'handling moderation') are generic rather than naming the concrete operations the skill performs.

Suggestions

Replace the generic 'filtering user prompts or handling moderation' with concrete operations, e.g. 'pre-screen prompts against blocked patterns, inject safety negative prompts, and parse server-side policy rejections'.

Mention the key artifacts the skill works with (e.g. negative-prompt defaults, rejection handlers) to make capabilities more tangible.

Dimension	Reasoning	Score
Specificity	Names the domain ('Kling AI prompts and outputs') and two concrete actions ('filtering user prompts', 'handling moderation'), but the actions stay high-level rather than enumerating specific operations like pattern matching, negative-prompt injection, or rejection handling.	3 / 5
Completeness	Explicitly answers both what ('Implement content policy compliance for Kling AI prompts and outputs') and when ('Use when filtering user prompts or handling moderation. Trigger with phrases like...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Provides four natural trigger phrases ('klingai content policy', 'kling ai moderation', 'safe video generation', 'klingai content filter') that a user might plausibly say, with synonym variation, though a few common phrasings are absent.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (Kling AI content policy) with product-specific trigger terms, making overlap with generic moderation skills minimal.	5 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/saas-packs/klingai-pack/skills/klingai-content-policy/SKILL.md
Commit: 8585d6d

Reviewed: 13 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.