CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cowart-film-gen

Create or edit storyboarded HTML/JavaScript motion films in a Cowart AI 影片 frame, with continuous action, a coherent visual system, seekable playback, and synchronized sound.

Quality

80%

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/cowart-film-gen/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

92%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 SKILL.md body is an exemplary instruction-only skill: highly actionable with concrete tool contracts and defaults, a clearly sequenced workflow with validation checkpoints and error-recovery paths, and clean one-level-deep progressive disclosure across its bundle. Only minor sentence-level tightening in the densest sections would improve token efficiency.

DimensionReasoningScore

Conciseness

The body is dense, directive, and assumes Claude's competence throughout — no padding or explanations of known concepts. Minor tightening is possible: steps 4 and 6 and the permission section pack many clauses into single long sentences that could be split or trimmed without losing meaning.

4 / 5

Actionability

Guidance is fully executable: exact tool calls with parameters (insert_cowart_html_draft with dryRun, matchAnchor, replaceDraftHolder, draftShapeId), a copy-paste JSON payload with sample-vs-real values called out, explicit defaults (15 s duration, 1–120 s range, 30 FPS quantization), and concrete API requirements (window.CowartFilm, renderAudio, data-cowart-text-id).

5 / 5

Workflow Clarity

The sequence is explicit — read target → check session permissions → dry-run preflight → style routing → direct/make (7 numbered steps) → visual review → final insertion — with explicit validation checkpoints (preflight dry run, rendered-frame inspection of anticipation/peak/settle and transitions, confirming the returned shape ID and saved path), error-recovery loops (rejection handling, permission-bypass prohibition, unverified-work disclosure).

5 / 5

Progressive Disclosure

The body is a well-organized overview that splits detail into 9 real reference files (directing, runtime-contract, 5 style guides, sources, visual-review), each linked with a stated purpose and explicit read-conditions (e.g., sources.md only when the user asks about inspiration). References are one level deep and verified to exist.

5 / 5

Total

19

/

20

Passed

Description

58%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 clearly communicates a niche capability with concrete actions and specific technical features, and it is appropriately concise in third person. Its main weaknesses are the absence of any "Use when…" trigger clause and missing natural synonyms (animation, video) that would improve discoverability.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to create or edit a film, motion piece, or animated 影片 in a Cowart frame."

Include natural synonyms users would say — "animation", "video", "movie", "motion graphics" — alongside "motion films" to broaden trigger coverage.

Optionally mention the MP4 export capability ("exportable to MP4 with music") so the description covers the full workflow value.

DimensionReasoningScore

Specificity

"Create or edit storyboarded HTML/JavaScript motion films… seekable playback, and synchronized sound" names several concrete actions and artifacts (create, edit, the HTML/JS medium, playback and sound features). It falls short of a 5 because coverage is a single sentence and omits other workflow capabilities such as style routing, MP4 export, and text editing.

4 / 5

Completeness

The "what" is clear (create/edit HTML/JavaScript motion films with continuous action, coherent visual system, seekable playback, synchronized sound), but there is no "Use when…" clause or equivalent explicit trigger guidance, which caps completeness at 3.

3 / 5

Trigger Term Quality

"motion films", "create or edit", and "HTML/JavaScript" are relevant keywords, but common natural variations users would say are missing — "animation", "video", "movie", or a plain-language "film/影片" phrasing beyond the platform-specific "Cowart AI 影片 frame".

3 / 5

Distinctiveness Conflict Risk

"storyboarded HTML/JavaScript motion films in a Cowart AI 影片 frame" is a distinct niche with platform-anchored triggers. Minor overlap risk remains with generic animation, video, or web-page generation skills, so it does not reach the minimal-conflict level of 5.

4 / 5

Total

14

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

zhongerxin/Cowart

Path

skills/cowart-film-gen/SKILL.md

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.