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'.
64
77%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/klingai-pack/skills/klingai-content-policy/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description with strong completeness and distinctiveness due to its explicit 'Use when' clause and Kling AI-specific trigger terms. The main weakness is that the capability description could be more specific about what concrete actions the skill performs beyond 'implement content policy compliance' and 'filtering/handling moderation'.
Suggestions
Add more specific concrete actions, e.g., 'Checks prompts against prohibited content categories, flags policy violations, sanitizes unsafe outputs, and returns moderation verdicts for Kling AI video generation.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Kling AI content policy) and some actions ('filtering user prompts', 'handling moderation'), but doesn't list specific concrete actions like blocking categories, flagging violations, or returning moderation verdicts. | 2 / 3 |
Completeness | Clearly answers both 'what' (implement content policy compliance for Kling AI prompts and outputs) and 'when' (use when filtering user prompts or handling moderation), with explicit trigger phrases provided. | 3 / 3 |
Trigger Term Quality | Includes multiple natural trigger terms: 'klingai content policy', 'kling ai moderation', 'safe video generation', 'klingai content filter', plus general terms like 'filtering user prompts' and 'moderation'. Good coverage of what users might say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific to Kling AI content policy and moderation, with brand-specific trigger terms like 'klingai content policy' and 'klingai content filter'. Unlikely to conflict with generic moderation or other AI platform skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with executable Python code covering pre-submission filtering, safe defaults, client integration, and server-side rejection handling. Its main weaknesses are the lack of an explicit end-to-end workflow with validation/feedback loops, and some generic advice in the user-facing guidelines section that doesn't add value for Claude. The code quality is high but the overall structure could benefit from better sequencing and progressive disclosure.
Suggestions
Add an explicit end-to-end workflow section showing the complete sequence: filter prompt → build safe request → submit → check status → handle rejection → retry with revised prompt
Remove or significantly trim the 'User-Facing Guidelines' section — these are generic software engineering practices Claude already knows
Add a feedback loop showing what to do when a prompt passes the client-side filter but is still rejected server-side (e.g., update blocked patterns, log the gap)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with good use of tables and code blocks, but includes some unnecessary elements like the 'User-Facing Guidelines' section which contains generic advice Claude already knows (rate limiting, logging, human review). The overview is concise though. | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready Python code for prompt filtering, sanitization, safe request building, client integration, and server-side rejection handling. The code is complete with proper class structure, type hints, and clear method signatures. | 3 / 3 |
Workflow Clarity | The implicit workflow is clear (filter → submit → handle rejection), but there's no explicit sequenced workflow with validation checkpoints. The pieces are presented as separate code blocks without a clear end-to-end flow showing how they connect, and there's no feedback loop for when server-side rejection occurs despite passing the client-side filter. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a table, but it's somewhat monolithic — the full PromptFilter class, SafeKlingClient, and rejection handling could be split into referenced files. For a standalone skill with no bundle files, the inline content is reasonable but lengthy at ~130 lines. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Commit
d41e58e
- 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.