CtrlK
BlogDocsLog inGet started
Tessl Logo

image-analyzer

Analyze images with AI - extract text, describe content, detect objects

48

Quality

61%

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/research-tools/capabilities/image-analyzer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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 content delivers concrete, domain-specific commands and avoids explaining concepts Claude already knows, but its reliability is undermined by broken JSON in three of the curl examples, a mislabeled 'workflow' that is really a list of alternatives, and a fully duplicated example section. Structure exists but everything is inlined with no progressive disclosure.

Suggestions

Fix the malformed JSON payloads in Step 2, Step 3, and Example Usage so every curl command is copy-paste executable (the -d argument must enclose the entire JSON body in single quotes).

Remove the 'Example Usage' section that duplicates Steps 2 and 4, or replace it with genuinely distinct end-to-end examples; also retitle 'Workflow' to reflect that the steps are alternative use cases, not a sequence.

Add validation guidance — check HTTP status codes, handle auth/fetch failures, and verify the image was retrieved before extraction — and move per-API endpoint details (e.g. riveter's output schema) into a references/ file.

DimensionReasoningScore

Conciseness

The body is mostly lean commands, but the intro sentence restates the frontmatter description, the 'Example Usage' section duplicates Step 2 and Step 4 commands nearly verbatim, and full curl auth boilerplate repeats across all seven blocks — it could be meaningfully tightened.

3 / 5

Actionability

Concrete curl commands are provided throughout, but several are not executable as written: Step 2, Step 3, and Example Usage have malformed JSON payloads (the -d argument terminates early and leaves 'website_url'/'input' fields outside quotes), and the 'Discover More' blocks append stray text and a truncated, misquoted path.

3 / 5

Workflow Clarity

Steps 1–4 are labeled as a workflow but are actually four independent use cases rather than a sequence, and there are no validation checkpoints (no status-code checks, error handling, or guidance for failed fetches or auth errors).

3 / 5

Progressive Disclosure

Sections are clearly headed (Setup, Workflow, Example Usage, Tips, Discover More), but there are no bundle files or references at all — all per-API details are inlined in a ~120-line file where a reference layer could offload the endpoint details.

3 / 5

Total

12

/

20

Passed

Description

55%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 concise and names three concrete capabilities, giving it decent specificity. However, it entirely lacks a 'when to use' clause, has thin trigger-term coverage without synonyms or file extensions, and carries moderate conflict risk with other image-handling skills.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants OCR on images, image descriptions, object detection, or analysis of photos/screenshots (.jpg, .png).'

Include natural synonyms and file extensions users would actually say — 'OCR', 'photos', 'screenshots', 'image recognition', '.jpg/.png' — to improve trigger-term coverage.

Mention the structured-data extraction and website-screenshot capabilities the skill actually supports to close the coverage gap and sharpen distinctiveness.

DimensionReasoningScore

Specificity

Names three concrete actions ('extract text, describe content, detect objects') but omits capabilities the skill actually has (screenshots, structured data extraction), so it lists several specific actions with minor gaps rather than comprehensive coverage.

4 / 5

Completeness

It clearly answers 'what' with three named operations, but contains no 'Use when...' clause or any equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Includes relevant keywords like 'images', 'extract text', and 'detect objects', but misses common natural variations users would say such as 'OCR', 'photos', 'screenshots', 'image recognition', and file extensions like .jpg or .png.

3 / 5

Distinctiveness Conflict Risk

'Analyze images with AI' carves out a recognizable niche but is broad enough to overlap with other image, vision, or screenshot skills, and no distinct trigger phrases differentiate it.

3 / 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.

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
gooseworks-ai/goose-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.