CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

fal-kling-o3

Generate images and videos with Kling O3 — Kling's most powerful model family — via fal.ai.

48

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/fal-kling-o3/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

43%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 body is a tidy, token-efficient catalogue stub, but it provides no executable guidance for the advertised capability — everything is deferred to an external repository with no concrete install or usage steps. It functions as a discovery pointer rather than an actionable skill.

Suggestions

Include at least one executable example of invoking the capability (e.g. a minimal fal.ai client call for Kling O3 with key parameters) so the skill is actionable without leaving the file.

Replace "inspect the upstream README for exact paths" with the concrete installation steps or a direct clone/copy command for the upstream bundle.

Inline the core usage workflow (inputs, model modes, how results are returned) and keep the external repo link as a secondary reference rather than the sole source of instructions.

DimensionReasoningScore

Conciseness

The body is lean and sectioned with no explanations of concepts Claude already knows; the only bloat is that "What it does" and "Source" repeat the frontmatter description and upstream URL verbatim. Not a 5 because that duplication could be trimmed.

4 / 5

Actionability

The only concrete command is `open https://github.com/fal-ai-community/skills`, and the actual task (image/video generation) has zero executable guidance — no API call, parameters, or examples. This matches "minimal concrete guidance; high-level hints but missing the specific steps to execute."

2 / 5

Workflow Clarity

The sequence "install the upstream bundle, then invoke the skill by name" is present but the critical install step has no actual command — the reader is told to "inspect the upstream README for exact paths," leaving many gaps and no validation checkpoints. This matches the anchor 2 example of a rough sequence with poorly defined steps.

2 / 5

Progressive Disclosure

Sections are well organized for a sub-50-line skill, but all substantive content is deferred behind an external GitHub URL (with the README presumably pointing further to the real files), mirroring the nested "see advanced.md" anti-pattern, and no local bundle files (references/, scripts/, assets/) exist to navigate.

3 / 5

Total

11

/

20

Passed

Description

61%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 states a clear, distinct capability (Kling O3 image/video generation via fal.ai) in third person with good natural keywords, but it is a single generic action with no "when to use" guidance, leaving it moderately complete rather than comprehensive.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to generate AI images or videos with Kling, mentions Kling O3, or wants fal.ai-based generation."

List the concrete capabilities more granularly (e.g. text-to-image, text-to-video, image-to-video) to raise specificity beyond one generic action.

Include common user phrasings/synonyms such as "AI video", "text-to-video", or "render" to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

"Generate images and videos with Kling O3" names the domain and 1-2 concrete actions but nothing more granular — no inputs, outputs, or formats — matching the 'names domain and 1-2 concrete actions' anchor. It falls short of anchor 4, which requires several specific listed actions.

3 / 5

Completeness

The "what" is clear (generate images and videos with Kling O3 via fal.ai) but there is no "Use when..." clause or equivalent explicit trigger guidance, which the guidelines state caps completeness at 3.

3 / 5

Trigger Term Quality

Natural terms present — "images", "videos", "Kling O3", "fal.ai" — giving good keyword coverage, though common variations like "text-to-video", "AI image", or "render" are missing, so it sits between anchors 3 and 4 but noticeably above the midpoint.

4 / 5

Distinctiveness Conflict Risk

"Kling O3 ... via fal.ai" is a clear, specific niche, but "Kling's most powerful model family" carries minor overlap risk with other Kling-version and fal.ai generation skills, so it is mostly distinct rather than minimal-conflict.

4 / 5

Total

14

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

nexu-io/open-design

Path

skills/fal-kling-o3/SKILL.md

Revision

78d5637

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill