CtrlK
BlogDocsLog inGet started
Tessl Logo

media-gen

Generate or edit images, videos, or audio (text-to-speech) in the current task. Use whenever the user asks to create/generate/produce or edit/modify a picture / image / illustration / cover / poster / icon / artwork, a video / clip / animation, or speech / voiceover / narration / TTS — e.g. generate image, draw, design a cover, edit this image, change the background, text-to-video, generate speech; 画一张, 配图, 编辑图片, 改图, 换背景, 做个视频, 配音, 文字转语音. Also use when a document (slides, poster, README hero) needs an inline image.

68

Quality

84%

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

SKILL.md
Quality
Evals
Security

Quality

Content

77%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.

A highly actionable, well-sequenced skill body with excellent executable examples and validation checkpoints across image, video, and audio generation. Its main weaknesses are restated rules that hurt conciseness and a monolithic inline structure that underuses progressive disclosure.

Suggestions

De-duplicate the repeated concurrency and cost-gate rules: state each hard rule once in a prominent "Rules" block and reference it instead of restating in bold across sections.

Move the Seedance multimodal field reference and examples (~170 lines) into a separate references/ file (e.g. SEEDANCE.md) and link to it from the video section to improve progressive disclosure.

Tighten the prompt-writing tips section, which leans on generally-known guidance, to only the modality-specific advice that Claude would not infer.

DimensionReasoningScore

Conciseness

The dense API reference across three modalities mostly earns its place, but key rules are restated multiple times (the "one at a time" concurrency warning and Seedance cost-gate each appear 2-3x in bold, and the "Hard rules" block repeats earlier points) and could be tightened.

3 / 5

Actionability

Fully executable copy-paste curl commands, complete request/response JSON, field tables, a poll loop, and helper-script invocations cover the common image/video/audio and chaining cases.

5 / 5

Workflow Clarity

Clear Step 1/2/3 sequence, a 6-step video-chaining workflow, and explicit Seedance async-poll validation checkpoints with feedback loops (400 -> drop aspect_ratio and retry); cost-gate validation is present so the destructive/batch cap does not apply.

5 / 5

Progressive Disclosure

The single bundle script (scripts/video_seq.sh) is appropriately referenced, but ~560 lines of per-modality API reference are inlined monolithically and the Seedance multimodal deep-dive (~170 lines) is a candidate for a separate reference file.

3 / 5

Total

16

/

20

Passed

Description

91%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.

A strong, trigger-rich description that explicitly covers what the skill does and when to use it across image, video, and audio generation/editing, with extensive natural synonyms in English and Chinese. Action breadth is slightly limited to generate/edit verbs.

DimensionReasoningScore

Specificity

"Generate or edit images, videos, or audio (text-to-speech)" names the domain plus concrete generate/edit actions across three modalities; not a 5 because the distinct verbs are limited to generate/edit rather than a comprehensive action list.

4 / 5

Completeness

Explicitly answers both what ("Generate or edit images, videos, or audio") and when ("Use whenever the user asks to create/generate/produce or edit/modify...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural synonyms ("picture / image / illustration / cover / poster / icon / artwork", "video / clip / animation", "speech / voiceover / narration / TTS") plus concrete user phrases and Chinese variants; matches the anchor-5 example.

5 / 5

Distinctiveness Conflict Risk

Clear media-generation niche with distinct triggers and minimal conflict risk; not a 5 due to minor overlap with design/charting skills for terms like "cover" and "icon".

4 / 5

Total

18

/

20

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.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (568 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 2 suspicious

Warning

Total

13

/

16

Passed

Repository
clacky-ai/openclacky
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.