CtrlK
BlogDocsLog inGet started
Tessl Logo

seek-and-analyze-video

Seek and analyze video content using Memories.ai Large Visual Memory Model for persistent video intelligence

50

Quality

55%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/seek-and-analyze-video/SKILL.md

The canonical home for this skill is seek-and-analyze-video in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

56%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 clearly structured with a sensible workflow and useful command vocabulary, but it is an instruction skill whose referenced reference files and routing table do not exist in the bundle, and the guidance stays at a pseudocode level rather than giving executable command details.

Suggestions

Provide the missing reference files (video_qa.md, social_research.md, etc.) or inline the routing table that maps each of the 6 intent categories to a workflow so the disclosure structure is real.

Add concrete command signatures or example request/response for the named API commands (caption_video, chat_video, search_public) instead of arrow-pseudocode workflows.

Collapse the duplicate "When to Use" / "When to Use This Skill" sections and remove the restated Description section to tighten token usage.

DimensionReasoningScore

Conciseness

The body is mostly efficient but redundant: "When to Use" and "When to Use This Skill" overlap, the "Description" section restates the frontmatter, and "Unlike one-shot video analysis tools..." is promotional padding.

3 / 5

Actionability

Named commands (caption_video, chat_video, search_audio, memory_add, search_public, wait) give some concrete guidance, but workflows are expressed as pseudocode arrows ("uploads video -> waits -> uses chat_video") with no signatures, parameters, or example requests/responses.

3 / 5

Workflow Clarity

"How It Works" sequences Intent Detection -> Reference Loading -> Workflow Execution, and the upload -> wait -> analyze -> present flow has an explicit validation checkpoint ("Always use the wait command after upload before any analysis"), with Common Pitfalls as feedback guidance.

4 / 5

Progressive Disclosure

Sections are well organized and reference files are named (video_qa.md, social_research.md), but no references/ bundle exists so those paths are dangling, and the promised "routing table in SKILL.md" is not actually present in the body.

3 / 5

Total

13

/

20

Passed

Description

53%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 about the tool and domain but lacks trigger guidance and natural keyword variations. It is third-person and free of major over-claims, yet reads as more technical than user-facing.

Suggestions

Add a "Use when..." clause listing concrete triggers (e.g., summarizing recordings, researching TikTok/YouTube/Instagram trends, building a video knowledge base).

Swap "seek" for the more natural "search" and add platform and task keywords (YouTube, TikTok, transcript, summarize) that users actually say.

Replace "persistent video intelligence" with a concrete capability phrase (e.g., "index videos once and query them repeatedly across sessions").

DimensionReasoningScore

Specificity

"Seek and analyze video content" names the domain and two actions (seek, analyze) tied to a specific tool (Memories.ai LVMM), but the actions are generic and "persistent video intelligence" is fluffy rather than a concrete capability.

3 / 5

Completeness

It clearly states what the skill does (seek/analyze video via LVMM) but has no "Use when..." clause or equivalent trigger guidance, so completeness is capped at 3 per the rubric.

3 / 5

Trigger Term Quality

"video content" and "analyze" are relevant natural terms, but common user phrasings (YouTube, TikTok, Instagram, summarize, transcript, search) and synonyms are missing; "seek" is less natural than "search".

3 / 5

Distinctiveness Conflict Risk

Naming Memories.ai's LVMM and "persistent video intelligence" carves a fairly distinct niche with only minor overlap risk against generic one-shot video-analysis skills; not a 5 because "seek and analyze video" is still broad.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.