Name: depth-estimation
Rating: 65.60000000000001 (1 reviews)
Author: SharpAI

Blog Docs Log in Get started

depth-estimation

Real-time depth map privacy transforms using Depth Anything v2 (CoreML + PyTorch)

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./SKILL.md

The canonical home for this skill is depth-estimation in SharpAI/DeepCamera

Quality

Content

100%

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

The content is concise, actionable, and well-structured for a single-purpose transform skill, with executable interface and protocol examples plus a real, one-level-deep bundle. No significant weaknesses relative to the rubric.

Dimension	Reasoning	Score
Conciseness	The body is lean — a backends table, short bullet list, two compact code blocks, JSONL protocol samples, and a two-line setup — and assumes Claude's competence without explaining what depth estimation or CoreML is, matching the score-3 'lean and efficient' anchor.	3 / 3
Actionability	It provides an executable interface contract (subclass TransformSkillBase, implement load_model/transform_frame), concrete bidirectional JSONL protocol examples, and copy-paste setup commands, fitting the score-3 'fully executable code/commands' anchor.	3 / 3
Workflow Clarity	This is a single-task transform skill with a clearly sequenced protocol (ready, transform, perf_stats, plus config-update handling) and no destructive batch step requiring validation checkpoints, so per the simple-skill scoring note a clear workflow earns 3.	3 / 3
Progressive Disclosure	The ~60-line overview is well-organized into clear sections and points one level deep to real bundle files (scripts/transform.py, transform_base.py) that are referenced in the interface example and frontmatter capability, with no nested-reference chain.	3 / 3
	Total	12 / 12 Passed

Description

57%

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 names a specific model and backends and occupies a distinct niche, but it is missing explicit 'when to use it' trigger guidance and leans on technical jargon over natural user phrasing. Adding a 'Use when...' clause with common terms would raise the weakest dimensions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to anonymize camera feeds, estimate scene depth, or generate depth maps/overlays from video.'

Broaden natural keywords to include terms users actually say, such as 'depth estimation' and 'anonymize/blind camera feeds', alongside 'depth map' and 'privacy'.

Consider listing concrete actions (e.g. 'generates colorized depth maps, overlays depth on live feeds, anonymizes scenes via depth-only mode') to move specificity from naming the domain to enumerating actions.

Dimension	Reasoning	Score
Specificity	Quotes 'Real-time depth map privacy transforms' and 'Depth Anything v2 (CoreML + PyTorch)' name the domain, model, and backends but do not enumerate multiple concrete actions, matching the score-2 anchor rather than the multi-action score-3 example.	2 / 3
Completeness	It states what the skill does but lacks any 'Use when...' clause or explicit trigger guidance, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Terms like 'depth map', 'privacy', 'CoreML', and 'PyTorch' are relevant but technical and miss common natural variations such as 'depth estimation' or 'anonymize camera', fitting the score-2 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The phrase carves out a clear, specialized depth-estimation/privacy niche that is unlikely to trigger for unrelated skills, matching the score-3 'clear niche with distinct triggers' anchor.	3 / 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: SharpAI/DeepCamera
Path: SKILL.md
Commit: 2264fcb

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.