CtrlK
BlogDocsLog inGet started
Tessl Logo

character-animation-qa

Review local character animation with schema checks, Playwright browser previews, frame sampling, and FFmpeg/ffprobe final output checks.

60

Quality

70%

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 ./.agents/skills/character-animation-qa/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 concise and well-structured for a simple single-purpose QA skill, but the review layers stay at a descriptive level and lack the executable commands and per-step validation loops needed to fully act on them.

Suggestions

Add concrete executable commands for the non-Playwright layers, e.g. an ffprobe invocation for the final MP4 check and a schema-validation command for layer 1.

Specify how frames are sampled and compared for the motion check (e.g. ffmpeg frame extraction at fixed timestamps plus a diff threshold) so the step is reproducible.

Insert an explicit validation feedback loop (run check → if it fails, fix and re-run) between the technical layers and the final pass/revise/fail decision to raise workflow clarity.

DimensionReasoningScore

Conciseness

The ~38-line body is lean and efficient — numbered review layers, a short Playwright snippet, pass/revise/fail definitions, and source links — with no padding or explanation of concepts Claude already knows.

5 / 5

Actionability

Provides one concrete executable Playwright code block, but the review layers are high-level descriptions (e.g. 'ffprobe metadata, duration, resolution', 'compare sampled frames') without the actual ffprobe commands, frame-sampling method, or schema-validation tooling needed to execute them.

3 / 5

Workflow Clarity

The six numbered review layers form a clear sequence with a terminal pass/revise/fail decision, but there are no explicit per-step validation feedback loops; since frame sampling and final renders are batch/render operations, the rubric caps workflow clarity at 3.

3 / 5

Progressive Disclosure

A self-contained skill under 50 lines with a single purpose and well-organized sections (Review Layers, Playwright Pattern, Pass/Revise/Fail, Sources) and no need for external bundle references, qualifying for the simple-skill exception.

5 / 5

Total

16

/

20

Passed

Description

67%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 is specific and occupies a distinctive niche, but lacks an explicit 'Use when...' trigger clause and is missing common natural trigger phrases a user would actually say.

Suggestions

Add an explicit trigger clause, e.g. 'Use when reviewing or QA-ing a character animation preview or final render before presenting it to the user.'

Include more natural user-side phrases and file extensions (e.g. 'animation review', 'render check', '.mp4', 'preview QA') to improve trigger term coverage.

Consider naming the runtime/output artifacts explicitly (e.g. '.mp4 final render', 'preview HTML') to sharpen distinctiveness.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — 'schema checks', 'Playwright browser previews', 'frame sampling', 'FFmpeg/ffprobe final output checks' — giving comprehensive coverage of the QA pipeline rather than minor gaps.

5 / 5

Completeness

Has a clear 'what' (the four review actions) but no 'Use when...' trigger clause; per the rubric a missing explicit trigger guidance caps completeness at 3.

3 / 5

Trigger Term Quality

Contains relevant keywords like 'character animation', 'browser previews', and 'frame sampling', but is missing common natural user-side variations (e.g. 'animation review', 'render check') and any file extensions.

3 / 5

Distinctiveness Conflict Risk

Targets a clear niche ('character animation' QA with Playwright and FFmpeg/ffprobe) with distinct, specific triggers and minimal overlap risk with other skills.

5 / 5

Total

16

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
calesthio/OpenMontage
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.