Name: depth-estimation
Rating: 63.2 (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

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

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

92%Weight 40%Scale 1-3

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

The body is concise, actionable, and presents a clear event-driven workflow with executable code and protocol examples. Progressive disclosure is the weak point: detailed reference material (protocol/interface specs) is inlined in SKILL.md rather than split into clearly signaled reference files.

Suggestions

Move the full Aegis↔Skill protocol and TransformSkillBase interface details into a reference file (e.g. PROTOCOL.md) and link to it with a clearly signaled one-level-deep reference.

List the available bundle scripts (setup.sh, start_service.sh, transform.py) with one-line descriptions so navigation to them is explicit.

Keep SKILL.md as an overview pointing to the deeper material rather than embedding the complete wire-format specification.

Dimension	Reasoning	Score
Conciseness	Lean, well-organized content with a backends table, capabilities, interface code, protocol examples, and setup; it assumes Claude's competence without padding concepts Claude already knows.	3 / 3
Actionability	Provides executable code (TransformSkillBase subclass with imports), concrete JSONL protocol examples, and copy-paste setup commands rather than vague direction.	3 / 3
Workflow Clarity	The event-driven transform action is unambiguous and the setup is a concrete sequenced command pair; no destructive or batch operations require validation checkpoints, so the single-action workflow is clear.	3 / 3
Progressive Disclosure	Sections are well-organized and a real bundle script (scripts/transform.py) is referenced, but the full protocol spec and interface details are inlined rather than split into one-level-deep reference files, and bundle scripts are not clearly signaled for navigation.	2 / 3
	Total	11 / 12 Passed

Description

57%Weight 40%Scale 1-3

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 and distinctive, naming the model and backends clearly, but it lacks an explicit 'Use when...' trigger clause and omits common natural variations users would say. Adding trigger guidance would raise completeness and trigger-term quality.

Suggestions

Append a 'Use when...' clause naming concrete triggers, e.g. 'Use when anonymizing camera feeds, estimating monocular depth, or visualizing scene depth for privacy monitoring.'

Include natural user phrasings like 'depth estimation', 'monocular depth', and 'anonymize camera feed' alongside the technical terms.

Broaden the action verbs beyond 'transforms' to enumerate the concrete actions (estimates depth, anonymizes identities, overlays depth maps).

Dimension	Reasoning	Score
Specificity	Names the domain and concrete backends ('depth map privacy transforms', 'Depth Anything v2 (CoreML + PyTorch)') but the verb 'transforms' is generic and not comprehensive of the actions (no explicit 'estimates depth', 'anonymizes', 'overlays').	2 / 3
Completeness	It states what the skill does but has no 'Use when...' trigger clause, so 'when to use' is only implied, capping completeness at 2.	2 / 3
Trigger Term Quality	Relevant keywords ('depth map', 'privacy transforms', 'Depth Anything v2', 'CoreML', 'PyTorch') are present but common natural variations ('depth estimation', 'monocular depth', 'anonymize camera feed') are missing.	2 / 3
Distinctiveness Conflict Risk	A specific niche (Depth Anything v2 depth maps for privacy with named backends) with third-person voice makes it unlikely to trigger for the wrong skill.	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: 22 days 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.