CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

media-ops-skill

Process local image / video / audio files, or download videos from the web. Images: resize, crop, rotate, convert format (→webp/png/jpeg), apply filters, inspect dimensions. Video: convert format, extract audio, inspect metadata. Download: public videos from YouTube / Bilibili etc. Also the go-to skill for post-processing AI-generated images (format conversion, resizing). **Not for**: AI generating images/video/voice from scratch (→cloud-media-skill), or rendering charts inline (→visualization-ops-skill).

65

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

83%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 tight, highly actionable skill body: concrete parameter tables, an intent-to-tool decision tree, and executable workflow examples, with no filler. The gaps are the absence of validation/verification steps in the batch and overwrite-risk workflows (capping workflow clarity at 3) and slight redundancy in the act-immediately/loading notes.

Suggestions

Add a validation checkpoint to the batch conversion workflow, e.g. run get-info on the first output to confirm format/size before processing the rest, and verify each output exists before reporting success.

Dedupe the '⚡ Act immediately' block with the 'Loading' note into a single activation instruction.

For overwrite-in-place operations, add an explicit verify step (confirm the output file is valid before notifying the user the original is gone).

DimensionReasoningScore

Conciseness

The body is lean — terse tables, a compact decision tree, and short per-tool sections that teach only tool-specific facts (actions, parameters, pitfalls) rather than concepts Claude already knows. Not 5 because of minor redundancy: the '⚡ Act immediately' block repeats the ToolSearch activation already stated in the 'Loading' note, and a few rationale clauses ('the user may need the original for comparison or rollback', 'WebP maintains visual quality at roughly 70% of JPEG file size') could be trimmed; not 3 because the padding is isolated and never obscures the instructions.

4 / 5

Actionability

Guidance is concrete and near copy-paste ready: full action/parameter tables ('resize | width/height/fit'), a decision tree mapping user intents to specific tool+action pairs, and executable workflow call sequences such as 'ImageProcess(action: "convert", filePath: "…", format: "webp", outputPath: "…")' covering the common cases. Not 4 because the specific examples plus parameter inventories leave no significant gaps in executable detail.

5 / 5

Workflow Clarity

Multi-step workflows are clearly sequenced (get-info first, download → extract-audio, batch convert) and there is a useful 'Run get-info first' pre-check, but there are no output validation or verification steps — notably the batch conversion workflow ('Call ImageProcess(action: "convert", format: "webp") for each image') proceeds with no checkpoint. Per the judging guideline, missing validation in a batch operation caps workflow clarity at 3; not 4 because the batch/overwrite-risk workflows lack verification rather than having only minor gaps.

3 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/), and the single SKILL.md is well organized — Tool Inventory, Decision Tree, per-tool sections, Common Workflows, Common Pitfalls — with everything appropriately inlined for a skill of this size. Not 5 because at ~110 lines it exceeds the lean single-file ideal and denser reference material (e.g. format guidelines, filter parameters) could be split into one-level-deep reference files; not 3 because structure is clear and nothing is buried.

4 / 5

Total

16

/

20

Passed

Description

75%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 highly specific, well-disambiguated description with strong natural trigger terms across image, video, and audio domains. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which leaves the activation conditions only weakly implied for the general case.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user asks to resize, crop, convert, or filter an image/video, extract audio, or download a public video link.'

Include a few more natural user phrases such as 'compress', 'mp4', or 'trim' to round out trigger coverage.

DimensionReasoningScore

Specificity

The description enumerates many concrete actions per domain — 'resize, crop, rotate, convert format (→webp/png/jpeg), apply filters, inspect dimensions' for images, 'convert format, extract audio, inspect metadata' for video, and 'download videos from the web' — matching the anchor for multiple specific concrete actions with comprehensive coverage. Not 4 because coverage spans all three domains with named operations and output formats rather than having minor gaps.

5 / 5

Completeness

The 'what' is clearly and comprehensively stated, but there is no explicit 'Use when...' clause or general trigger guidance — the closest is the sub-case phrase 'the go-to skill for post-processing AI-generated images' and the '**Not for**' boundary, which only weakly implies when to use it. Per the judging guideline, a missing 'Use when...' clause or equivalent explicit trigger guidance caps completeness at 3; not 4 because the 'when' for the general case is absent rather than merely under-specified.

3 / 5

Trigger Term Quality

Good natural-term coverage: 'image / video / audio', 'resize, crop, rotate', 'convert format', 'extract audio', 'download videos', 'YouTube / Bilibili', and format names 'webp/png/jpeg'. Not 5 because a few natural user phrases are missing — e.g. 'compress', 'mp4', 'mp3', 'trim' — which users commonly say; not 3 because synonym and platform coverage clearly exceeds 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche (local media processing + downloading) and explicitly disambiguates neighbors via '**Not for**: AI generating images/video/voice from scratch (→cloud-media-skill), or rendering charts inline (→visualization-ops-skill)'. This matches the anchor for a clear niche with distinct triggers and minimal conflict risk.

5 / 5

Total

17

/

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.

Validation — 15 / 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

itsablabla/openloaf-web

Path

apps/server/src/ai/builtin-skills/media-ops/en/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.