CtrlK
BlogDocsLog inGet started
Tessl Logo

image-analyzer

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

51

Quality

56%

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

53%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 skill provides concrete, mostly-real curl examples organized into clear sections, but multiple JSON payloads are malformed and will not execute, the steps are disconnected options rather than a sequenced workflow, and there are no validation checkpoints. Fixing the broken payloads and clarifying the workflow sequence would materially raise the score.

Suggestions

Fix the malformed -d JSON payloads in Steps 2, 3, Example Usage, and Discover More — the object currently closes with '}' before the website_url/input fields, making the commands non-executable.

Reconcile the workflow so the steps form a coherent sequence (e.g., have Step 1 fetch an image that the later steps actually consume) or relabel them as independent capabilities rather than 'Step 1..4'.

Remove the redundant Example Usage duplication of Step 2 and the restated description line, and add a brief validation/verification check (e.g., confirm the API returned a 2xx and non-empty result before reporting success).

DimensionReasoningScore

Conciseness

The body is mostly lean curl examples with no concept-explanation padding, but the Example Usage section largely duplicates Step 2 (smartscraper) and the line 'Analyze images to extract text, describe content, and detect objects using AI.' restates the frontmatter, so it could be tightened — matching the 'mostly efficient but some redundancy' anchor.

3 / 5

Actionability

Concrete curl commands with real endpoints are provided, but the -d JSON payloads in Steps 2, 3, Example Usage, and Discover More are syntactically broken (the object closes early with '}' then continues with stray keys), so several examples are not copy-paste executable — 'some concrete guidance but incomplete; missing key details'.

3 / 5

Workflow Clarity

Steps 1–4 are labeled and listed, but they are really parallel independent options rather than a connected sequence (Step 1 fetches an image that Steps 2–4 never consume), and there are no validation or verification checkpoints, matching the 'steps listed but validation gaps; checkpoints missing' anchor.

3 / 5

Progressive Disclosure

The body is a single self-contained file with clear section headers (Setup, Workflow, Example Usage, Tips, Discover More) and no bundle files to navigate; structure is good with only minor gaps such as the muddled Discover More section, matching the 'good structure; most content appropriately placed' anchor rather than a 5 (no overview-pointing-to-details reference structure).

4 / 5

Total

13

/

20

Passed

Description

58%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 states what the skill does with three concrete actions, but omits any explicit 'when to use it' trigger guidance and lacks common natural synonyms like 'OCR' or 'image recognition'. It is fairly distinct as a niche but would benefit from a Use-when clause.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill, e.g. 'Use when the user wants to extract text (OCR) from images, describe image content, or detect objects.'

Include natural trigger synonyms users actually say — 'OCR', 'image recognition', 'screenshots', and file extensions like .jpg/.png — to improve trigger matching.

Drop the 'with AI' filler or replace it with a more specific capability to tighten the description.

DimensionReasoningScore

Specificity

Lists several concrete actions ('extract text, describe content, detect objects') beyond merely naming the image-analysis domain, matching the 'several specific actions; minor gaps' anchor; not 5 because 'describe content' is somewhat generic and 'with AI' is light padding rather than comprehensive coverage.

4 / 5

Completeness

The 'what' is clear (analyze images / extract text / describe content / detect objects) but there is no 'when' or 'Use when...' trigger clause, which per the rubric caps completeness at 3 ('clear what but when missing or weakly implied').

3 / 5

Trigger Term Quality

Relevant keywords are present ('images', 'extract text', 'detect objects') but common natural variations users say are missing — notably 'OCR', 'image recognition', 'screenshots', and file extensions (.jpg/.png) — matching the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

The image-analysis niche with concrete OCR/object-detection triggers is mostly distinct, with only minor overlap risk against PDF/OCR or general vision skills, matching the 'mostly distinct; minor overlap' anchor rather than the broader score-3.

4 / 5

Total

14

/

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
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.