CtrlK
BlogDocsLog inGet started
Tessl Logo

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

61

Quality

72%

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/media-ingest/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 a well-structured, actionable orchestration guide with a clear phased workflow, validation checkpoints, and clearly signaled one-level-deep references. It is slightly held back by a few high-level format actions and minor verbosity.

DimensionReasoningScore

Conciseness

The body is lean, assumes Claude's competence (no definitions of PDF/OCR/STT), and uses tables and tight lists; a few emphatic restatements like 'A media item is NOT fully ingested until entity propagation is complete.' could be trimmed.

4 / 5

Actionability

Concrete executable commands ('gbrain files upload-raw <file> --page <slug>', 'gbrain sync'), a copy-ready page template, and enumerated Phase 4 steps are present, though several format actions remain high-level ('Transcribe with available STT service').

4 / 5

Workflow Clarity

A clear five-phase sequence with real checkpoints (duplicate detection before Phase 3, entity-propagation completion gate, retry policy, Known Pitfalls checklist); it stops short of a tight validate→fix→retry loop on the produced page, which keeps it below 5.

4 / 5

Progressive Disclosure

External references ('skills/_brain-filing-rules.md', 'skills/conventions/quality.md') are one level deep and clearly signaled via blockquote callouts, and the body is organized into well-named sections for easy navigation.

5 / 5

Total

17

/

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.

The description clearly conveys what the skill does across multiple media formats and names concrete capabilities, but it lacks an explicit 'Use when...' trigger clause, which limits completeness. Trigger-term coverage is good but misses a few natural synonyms.

Suggestions

Add an explicit 'Use when ...' sentence listing natural trigger phrases (e.g., 'Use when the user wants to save a video, podcast, PDF, book, screenshot, or GitHub repo into the brain').

Include natural synonyms users actually say — 'podcast', 'YouTube', 'mp3' — alongside the format list to improve trigger-term quality.

Clarify the relationship to the video-ingest/youtube-ingest/book-ingest subtypes to reduce overlap confusion, e.g., note this is the parent that delegates to them.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('entity extraction', 'backlink propagation', 'multi-format handling') across six media formats, but the verbs stay moderately high-level compared to the anchor-5 example of granular operations.

4 / 5

Completeness

The 'what' is clearly stated, but there is no 'Use when...' clause or equivalent explicit trigger guidance in the description, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Natural format keywords are present ('video, audio, PDF, book, screenshot, GitHub repo'), but common variations users would say such as 'podcast', 'YouTube', or 'mp3' are absent from the description text.

4 / 5

Distinctiveness Conflict Risk

It carves a clear media-ingest niche with distinct triggers, but 'Covers video-ingest, youtube-ingest, and book-ingest subtypes' introduces minor overlap risk with those closely related subskills.

4 / 5

Total

15

/

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
garrytan/gbrain
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.