image-analyzer

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

Quality

55%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/research-tools/capabilities/image-analyzer/SKILL.md

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill body is structured around a clear four-step workflow and stays lean, but its curl examples are malformed and non-executable and it lacks any error-handling guidance. Fixing the JSON payloads and adding a failure path would substantially improve it.

Suggestions

Repair the curl JSON payloads so each `-d` value is a single valid quoted object (e.g. wrap website_url/user_prompt inside the same JSON string); the current examples close the quote before the body fields.

Remove the duplicate examples in 'Example Usage' or replace them with genuinely different use cases to cut redundant tokens.

Add a brief error-handling note (check the HTTP status / response error field, retry or surface the message) so the workflow has a validation checkpoint, and clean up the malformed 'Discover More' commands.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean code with brief intros and avoids explaining concepts Claude already knows, but the 'Example Usage' section repeats the Step 2 and Step 4 curl examples, adding tokens that could be trimmed.	2 / 3
Actionability	Concrete curl commands are provided, but the JSON payloads are malformed — the `-d` value closes early and leaves `website_url`/`user_prompt`/`input` lines outside the quoted string, and the 'Discover More' commands append stray `api show` tokens with a syntax error in the olostep example — so the code is not copy-paste executable, matching the 'concrete guidance but incomplete' anchor.	2 / 3
Workflow Clarity	Steps 1–4 are clearly sequenced and labeled, but there are no validation checkpoints or error-handling feedback loops despite the API calls being able to fail, which fits 'steps listed but validation gaps'.	2 / 3
Progressive Disclosure	It is a single file organized into clearly named sections (Setup, Workflow, Example Usage, Tips, Discover More) with no external references, but the content is entirely inline and the 'Discover More' block is disorganized, so it lands at 'some structure but could be better organized' rather than well-signaled one-level references.	2 / 3
	Total	8 / 12 Passed

Description

60%

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 actions but omits any explicit trigger guidance, leaving the crucial 'when to use it' question unanswered. It is a competent but incomplete description that would benefit from a 'Use when...' clause.

Suggestions

Add a 'Use when...' clause naming natural user triggers, e.g. 'Use when the user wants OCR, image descriptions, or object detection from image files or URLs.'

Broaden trigger terms to include common variations users actually say, such as 'OCR', 'screenshots', 'image descriptions', and 'read text from images'.

Sharpen the niche wording so it is less likely to conflict with generic image or document skills.

Dimension	Reasoning	Score
Specificity	The description lists three concrete actions ('extract text, describe content, detect objects') rather than vague language, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It states what the skill does but never says when Claude should use it; there is no 'Use when...' clause, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Terms like 'images', 'extract text', 'detect objects' are natural but coverage is thin — common variations a user might say (e.g. 'OCR', 'image description', 'screenshots') are missing, so it sits at 'some relevant keywords but missing common variations' rather than a 3.	2 / 3
Distinctiveness Conflict Risk	'Analyze images with AI' names a niche but the trigger phrasing is generic enough that it could overlap with other image-handling skills, matching the 'somewhat specific but could still overlap' anchor rather than a clear distinct niche.	2 / 3
	Total	9 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: gooseworks-ai/goose-skills
Path: skills/research-tools/capabilities/image-analyzer/SKILL.md
Commit: 8866b2a

Reviewed: 1 day 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.