CtrlK
BlogDocsLog inGet started
Tessl Logo

klingai-usage-analytics

Build usage analytics and reporting for Kling AI video generation. Use when tracking patterns, analyzing costs, or building dashboards. Trigger with phrases like 'klingai analytics', 'kling ai usage report', 'klingai metrics', 'video generation stats'.

64

Quality

77%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/saas-packs/klingai-pack/skills/klingai-usage-analytics/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

64%

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

The skill provides solid, executable Python code for Kling AI usage analytics with good structure and concrete implementations. Its main weaknesses are the lack of an integration workflow showing how the components connect (e.g., log during generation → aggregate → report) and the monolithic inline presentation of full class implementations that could benefit from progressive disclosure. Adding a quick-start usage example and validation steps would significantly improve it.

Suggestions

Add a 'Quick Start' section at the top showing a 5-line end-to-end usage example that wires the logger, analytics, and report together

Add validation/error handling for reading JSONL files (e.g., handle missing files, malformed lines) and document these as explicit checkpoints

Move full class implementations to separate referenced files (e.g., logger.py, analytics.py) and keep only concise usage examples in SKILL.md

DimensionReasoningScore

Conciseness

The code is mostly efficient and avoids explaining basic concepts, but the full class implementations are quite lengthy. Some methods like print_report and cost_analysis could be more concise since Claude can infer formatting patterns. The overall content is ~150 lines of code that could potentially be tightened.

2 / 3

Actionability

All code is fully executable Python with complete class definitions, concrete method signatures, and real field names. The event logger, analytics aggregator, cost analysis, and CSV export are all copy-paste ready with no pseudocode.

3 / 3

Workflow Clarity

The skill presents components (logger, aggregator, cost analysis, export) but doesn't provide a clear sequenced workflow showing how to wire them together end-to-end. There are no validation checkpoints—e.g., no verification that log files exist before aggregation, no error handling for malformed JSONL lines, and no guidance on when/how to invoke each component in relation to the others.

2 / 3

Progressive Disclosure

The content is reasonably structured with clear section headers, but all implementation details are inline in a single file. The full class implementations could be split into referenced files with just usage examples in the SKILL.md overview. The Resources section at the end is a good touch but minimal.

2 / 3

Total

9

/

12

Passed

Description

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 that clearly identifies a specific niche (Kling AI video generation analytics), provides explicit 'when' guidance with trigger phrases, and is highly distinctive. The main weakness is that the capability actions could be more concrete—specifying exactly what kinds of analytics, reports, or dashboard components are built would strengthen the specificity.

Suggestions

Add more specific concrete actions, e.g., 'calculate cost-per-video, track generation success/failure rates, summarize API usage by model/resolution, build time-series dashboards' to improve specificity.

DimensionReasoningScore

Specificity

Names the domain (Kling AI video generation analytics) and some actions (tracking patterns, analyzing costs, building dashboards), but the actions are somewhat generic and not deeply specific—e.g., it doesn't specify what kinds of reports, what metrics are tracked, or what dashboard components are built.

2 / 3

Completeness

Clearly answers both 'what' (build usage analytics and reporting for Kling AI video generation) and 'when' (use when tracking patterns, analyzing costs, or building dashboards) with explicit trigger phrases provided.

3 / 3

Trigger Term Quality

Includes multiple natural trigger terms: 'klingai analytics', 'kling ai usage report', 'klingai metrics', 'video generation stats', plus contextual phrases like 'tracking patterns', 'analyzing costs', 'building dashboards'. Good coverage of terms a user might naturally say.

3 / 3

Distinctiveness Conflict Risk

Highly specific niche—Kling AI video generation analytics is a very distinct domain. The trigger terms are product-specific ('klingai', 'kling ai') making conflicts with other skills very unlikely.

3 / 3

Total

11

/

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.

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

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

Repository
jeremylongshore/claude-code-plugins-plus-skills
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.