videodb

See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio, video), and create real time alerts for events from live streams or desktop capture.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/videodb/SKILL.md

Quality

Content

77%

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 examples, explicit validation, and real error-recovery loops. Its main weaknesses are repeated/restated content that could be trimmed and a reference/ index whose linked files are absent from the bundle.

Suggestions

Include the referenced reference/*.md files in the bundle (or remove/correct the links) so the progressive-disclosure navigation resolves to real content.

Collapse the 'When to use' section so it does not duplicate the frontmatter description, and consolidate the repeated inline-vs-heredoc and API-key guidance into one place.

Verify the capture quick-start step references (e.g. 'see reference/capture.md') resolve once the reference files are restored.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly earns its place with executable code, but the 'When to use' section largely restates the frontmatter description and several guidance points are repeated (e.g. the inline-vs-heredoc and api-key notes), so it is efficient yet could be tightened.	2 / 3
Actionability	Provides fully executable, copy-paste-ready code for upload, indexing, search, scene search, timeline editing, transcoding, reframe, and generation, plus a concrete pitfalls table with exact error strings and fixes — matching the fully-executable anchor.	3 / 3
Workflow Clarity	Multi-step flows are explicitly sequenced with validation checkpoints (timestamp validation before building a Timeline) and error-recovery feedback loops (re.search to recover an existing scene_index_id, try/except around InvalidRequestError for empty results).	3 / 3
Progressive Disclosure	The overview is clean and signals one-level-deep references to a reference/ directory, but those 11 referenced reference/*.md files are not present in the bundle (only scripts/ws_listener.py exists), so navigation points to missing material rather than well-split content.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 highly specific and clearly niche-scoped, but it is a single dense run-on sentence with no explicit 'Use when...' trigger guidance, which caps completeness. Tightening it and adding a natural trigger clause would lift the weaker dimensions.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g. 'Use when the user works with video/audio files, live RTSP streams, or wants desktop capture with real-time alerts').

Break the long single sentence into a concise capability list plus a one-line trigger sentence to reduce verbosity.

Include common natural trigger terms users say — 'transcribe', 'clip', 'record screen', 'stream link' — alongside the existing jargon.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions across the domain — 'ingest from local files, URLs, RTSP/live feeds', 'build visual/semantic/temporal indexes', 'transcode and normalize (codec, fps, resolution, aspect ratio)', 'perform timeline edits (subtitles, text/image overlays... dubbing, translation)' — matching the multiple-specific-actions anchor.	3 / 3
Completeness	The 'what' is thoroughly covered, but there is no explicit 'when should Claude use it' / 'Use when...' guidance — only an implied scope — so per the guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	Contains relevant natural terms like 'video', 'audio', 'live streams', 'RTSP', 'subtitles', 'dubbing', but misses common user variations (e.g. 'transcribe', 'clip', 'record screen', 'stream link') and lacks an explicit 'Use when...' trigger clause, so it sits between anchor 2 and 3.	2 / 3
Distinctiveness Conflict Risk	The niche is clearly video/audio perception plus timeline editing and live-stream alerting, with distinct triggers (RTSP, desktop capture, playable stream links) that are unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

81%

Warnings & errors only

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

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 10 missing	Warning

	Total	13 / 16 Passed

Repository: affaan-m/ECC
Commit: 754b8dd

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.