CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

videodb

Video and audio perception, indexing, and editing. Ingest files/URLs/live streams, build visual/spoken indexes, search with timestamps, edit timelines, add overlays/subtitles, generate media, and create real-time alerts.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/videodb/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 highly actionable, with executable code, explicit validation rules, and strong error-recovery guidance, and it is largely free of padding. However, its progressive-disclosure architecture is broken as shipped: ten referenced reference/*.md files are absent from the bundle, leaving workflows that depend on them (notably desktop capture) incomplete.

Suggestions

Ship the ten reference/*.md files listed under 'Additional docs', or remove the dead links and inline the critical content — especially the desktop-capture workflow, which currently depends on the missing reference/capture.md and is unusable without it.

Trim the opening capability sections (1-5) and 'Common inputs/outputs', which largely restate the frontmatter description, to reduce token cost.

Add a build-time existence check for every referenced bundle path so referenced files are guaranteed to ship with the skill.

DimensionReasoningScore

Conciseness

The body is dominated by VideoDB-specific knowledge Claude cannot already know (SDK quirks like 'index_scenes() has no force parameter', exact error strings, a pitfalls table) with almost no concept re-teaching; the opening capability sections 1-5 plus 'Common inputs'/'Common outputs' partially restate the frontmatter description and could be trimmed, which keeps it just below fully lean.

4 / 5

Actionability

Copy-paste-ready executable examples cover the common cases: 'coll.upload(url=...)', 'video.index_spoken_words(force=True)', search wrapped in 'try/except InvalidRequestError', Timeline construction with 'VideoAsset(asset_id=video.id, start=10, end=30)', 'conn.transcode(...VideoConfig(resolution=720...))', reframe presets, and exact install commands, plus a pitfalls table mapping real error messages to concrete fixes.

5 / 5

Workflow Clarity

Sequences are explicit (numbered capture Quick Start, install-then-configure-key setup) with validation checkpoints ('start must be >= 0', 'start must be < end', 'end must be <= video.length'), feedback loops for error recovery (extract 'scene_index_id' from the error and re-raise otherwise; treat 'No results found' as 'shots = []'), and a checklist-style pitfalls table.

5 / 5

Progressive Disclosure

The 'Additional docs' section is well-formatted with one-line descriptions, but scored against the actual bundle none of the ten referenced 'reference/*.md' files exist — only 'scripts/ws_listener.py' ships — so nearly every navigation path dead-ends and the capture workflow's stated dependency (reference/capture.md) is unavailable. Not 3: the failure is not unclear signaling but non-functional navigation; not 4: the referenced files are simply missing.

2 / 5

Total

16

/

20

Passed

Description

66%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, action-dense description for a distinct video/media niche, weakened by the complete absence of any 'Use when...' trigger guidance and by missing high-frequency natural terms like 'transcribe' and 'clip'. It is well above the vague-baseline but falls short of the exemplary examples that pair a concrete 'what' with an explicit 'when'.

Suggestions

Add an explicit trigger clause, e.g. 'Use when working with video or audio files, live streams, or when the user mentions subtitles, transcription, clips, or timestamped search.'

Include the missing natural trigger terms: 'transcribe/transcription', 'clip(s)', 'screen recording/desktop capture', and common extensions like .mp4/.mov.

Mention desktop/screen capture, a primary capability in the skill body (section 1), which is currently absent from the description.

DimensionReasoningScore

Specificity

Lists seven concrete actions — 'Ingest files/URLs/live streams', 'build visual/spoken indexes', 'search with timestamps', 'edit timelines', 'add overlays/subtitles', 'generate media', 'create real-time alerts' — but omits desktop/screen capture and transcoding, which the body presents as headline capabilities, leaving minor coverage gaps rather than the comprehensiveness of a 5.

4 / 5

Completeness

The 'what' is clear and concrete, but there is no 'Use when...' clause or any equivalent explicit trigger guidance ('when should Claude use it' is entirely absent), which caps this dimension at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Good natural keyword coverage — 'video', 'audio', 'subtitles', 'editing', 'live streams', 'search with timestamps' — but common user phrasings like 'transcribe'/'transcription', 'clip(s)', 'screen recording', and file extensions (.mp4, .mov) are missing.

4 / 5

Distinctiveness Conflict Risk

Anchored to a clear video/media niche with distinct triggers (visual/spoken indexes, subtitles, live streams), but generic terms like 'editing' and 'generate media' leave minor overlap risk with general media-editing or image-generation skills.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 11 missing

Warning

Total

14

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

skills/videodb/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.