CtrlK
BlogDocsLog inGet started
Tessl Logo

ascii-video

ASCII video: convert video/audio to colored ASCII MP4/GIF.

60

Quality

71%

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/creative/ascii-video/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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 well-engineered skill body: lean table-driven overview, a clear 6-stage pipeline, a sequenced workflow with genuine validation checkpoints, and exemplary progressive disclosure into 8 real, one-level-deep reference files. The only weaknesses are mild redundancy in the creative-philosophy prose and the fact that most executable code lives in references rather than the body itself.

DimensionReasoningScore

Conciseness

The body is dense and table-driven with no explanations of concepts Claude already knows, but it repeats the "catalog is vocabulary — write the painting/poem" idea three times (Creative Standard, Project-Specific Invention, Creative Divergence) and the Creative Divergence section could be trimmed or moved. Not 5 because these redundancies are real tokens a reader must re-scan; not 3 because the rest is lean, actionable, and pointer-based.

4 / 5

Actionability

Concrete, executable guidance throughout: a complete copy-paste tonemap() implementation, explicit thresholds (canvas.mean() > 8), per-scene gamma values, and specific fixes (font.getmetrics() for cell height, stderr redirect for ffmpeg deadlock). Not 5 because the body contains only one code block — the pipeline's executable detail (scene protocol, shader chain, input loaders) lives in the references rather than as inline examples covering common cases.

4 / 5

Workflow Clarity

A clearly sequenced 4-step workflow (Creative Vision → Technical Design → Build → Quality Verification) with explicit validation checkpoints: render test frames first, brightness check with a concrete fix, visual coherence and creative-vision checks with a go-back feedback loop. This matches the anchor for clear sequence with explicit validation, error-recovery loops, and a checklist.

5 / 5

Progressive Disclosure

SKILL.md is a true overview: a References table maps all 8 existing reference files to their contents, in-body pointers are precise ("references/composition.md § Adaptive Tonemap"), and references are exactly one level deep with only sibling cross-links — verified against the actual bundle. Easy navigation with appropriately split content.

5 / 5

Total

18

/

20

Passed

Description

57%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 concise and distinctive, with a clear statement of what the skill does, but it functions as a label rather than a trigger. It lacks a "Use when..." clause, misses natural synonyms users would say, and undersells the skill's actual capability breadth. Adding explicit trigger phrases and naming the additional modes would raise completeness and trigger quality substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to convert video to ASCII art, make a text/terminal-style animation, create an ASCII music visualizer, or produce retro text-video output."

Include natural synonyms users actually say — "ASCII art", "text art", "character art", "terminal-style video" — alongside "ASCII video" to improve trigger matching.

Reflect the full capability breadth in the description by mentioning the audio-reactive visualizer, generative animation, and lyrics/TTS narration modes, not just the single convert action.

DimensionReasoningScore

Specificity

Names the domain ("ASCII video") and one concrete action ("convert video/audio to colored ASCII MP4/GIF") with input and output formats, but does not list several actions — it omits the audio-reactive visualizer, generative animation, and TTS narration capabilities the body actually covers.

3 / 5

Completeness

The "what" is clear (convert video/audio to colored ASCII MP4/GIF), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not 4 because the trigger context is entirely absent, not merely underspecified.

3 / 5

Trigger Term Quality

Relevant keywords are present ("ASCII", "video", "MP4/GIF"), but common user phrasings like "ASCII art", "text art", "terminal", or "convert X to ASCII" are missing. Not 4 because a user asking for "ASCII art video" or "make this clip look like text" would not reliably match this wording.

3 / 5

Distinctiveness Conflict Risk

"ASCII video" is a clear niche with distinct triggers and minimal overlap risk with other skills; the format-specific outputs (colored ASCII MP4/GIF) further narrow the match. Not 4 because nothing about the phrasing invites triggering for adjacent skills.

5 / 5

Total

14

/

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.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

Total

13

/

16

Passed

Repository
NousResearch/hermes-agent
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.