klingai-video-extension
Extend video duration using Kling AI continuation. Use when creating longer videos from shorter clips or building sequences. Trigger with phrases like 'klingai extend video', 'kling ai video continuation', 'klingai longer video', 'extend klingai clip'.
59
70%
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-video-extension/SKILL.mdQuality
Discovery
75%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 functional and clearly scoped to a specific tool (Kling AI) with explicit trigger guidance, which is a strength. However, the trigger terms feel artificially constructed rather than reflecting natural user language, and the capability description could be more detailed about what specific actions the skill performs beyond just 'extend video duration'.
Suggestions
Add more natural trigger terms users would actually say, such as 'make video longer', 'continue this clip', 'video extension', or 'loop video'.
List additional specific capabilities beyond extending duration, such as configuring continuation parameters, handling different video formats, or chaining multiple extensions into sequences.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Kling AI video continuation) and one core action (extend video duration), but doesn't list multiple specific concrete actions like specifying parameters, chaining sequences, or handling different input formats. | 2 / 3 |
Completeness | Clearly answers both 'what' (extend video duration using Kling AI continuation) and 'when' (creating longer videos from shorter clips, building sequences) with explicit trigger phrases provided. | 3 / 3 |
Trigger Term Quality | Includes branded trigger terms like 'klingai extend video' and 'kling ai video continuation', but these feel more like engineered keyword phrases than natural user language. Missing more natural terms like 'make video longer', 'continue video', or 'video extension'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting Kling AI video continuation specifically. The branded terms ('klingai', 'kling ai') make it highly unlikely to conflict with other video or AI skills. | 3 / 3 |
Total | 10 / 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 code examples and good structural organization. Its main weaknesses are some redundancy between the basic and usage sections, and incomplete validation/error handling in the polling workflow (no timeouts, no retry logic, hand-waved polling in the basic example). The error handling table is a nice touch but doesn't compensate for missing programmatic safeguards in the code itself.
Suggestions
Add explicit polling code with a timeout in the 'Basic Extension' section instead of the hand-waved comment, and add timeout/max-retry logic to chain_extensions to prevent infinite loops
Consolidate the 'Basic Extension' and 'Usage: Build a 20-Second Video' sections to reduce redundancy—the basic section could show just the extension call, since the chain example already demonstrates the full flow
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with good use of tables and code, but includes some redundancy—the 'Basic Extension' section and the 'Usage: Build a 20-Second Video' section overlap significantly in showing initial video generation + extension. The parameter table and error handling table are well-structured but the overall content could be tightened. | 2 / 3 |
Actionability | Provides fully executable Python code with complete authentication setup, API calls, polling logic, and chaining. The code is copy-paste ready with real endpoints, proper JWT token generation, and concrete examples including prompts and response parsing. | 3 / 3 |
Workflow Clarity | The multi-step process (generate → poll → extend → poll) is present and sequenced, but the polling step in the basic example is hand-waved with a comment ('Wait for completion... poll until task_status == succeed') rather than showing explicit validation. The chain_extensions function has proper polling but lacks timeout handling or retry logic for a process that involves multiple sequential API calls that could fail. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections progressing from basic to advanced usage, and includes external resource links. However, with no bundle files, all content is inline in a single file that runs fairly long (~150 lines of substantive content). The chain_extensions helper and the usage example could potentially be split out, but for a skill of this complexity the inline approach is borderline acceptable. | 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.