hand-tracking-toolkit

Facebook Research Hand Tracking Challenge Toolkit - evaluation and visualization tools for 3D hand tracking. Supports loading HOT3D data, computing metrics (PA-MPJPE, AUC, etc.), visualizing 3D pose projections, and generating tracking evaluation reports. Essential for benchmarking hand tracking algorithms.

Quality

73%

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/vision/hand-tracking-toolkit/SKILL.md

Quality

Content

65%

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

A well-organized, action-oriented skill body with concrete commands and code examples. It loses points for redundant/padded phrasing, missing validation checkpoints in the evaluation workflow, and a monolithic structure that doesn't leverage separate reference files.

Suggestions

Add explicit validation/verification steps after evaluation runs (e.g. confirm output files exist and inspect a sample metric) to satisfy the batch-operation feedback-loop requirement.

Move the detailed Metrics Reference table and prediction-format spec into separate reference files referenced from the body, leaving the overview lean.

Tighten redundant prose — remove the repeated 'Essential for benchmarking...' sentiment and the filler intros ('Rich visualization options', 'Easy data loading').

Dimension	Reasoning	Score
Conciseness	Mostly efficient using lists and tables, but has redundancy (the 'Essential for benchmarking...' line repeats the frontmatter) and low-value intro phrases like 'Rich visualization options' and 'Easy data loading' that could be trimmed.	2 / 3
Actionability	Provides concrete, copy-paste-shaped bash commands (clone, install, evaluate.py, visualize.py) and Python examples with specific class/method calls and metric keys, giving clear executable guidance.	3 / 3
Workflow Clarity	The Quick Start gives a clear clone→install→evaluate→visualize sequence, but there are no validation or verification checkpoints for the batch evaluation operations, which caps workflow clarity at 2.	2 / 3
Progressive Disclosure	Content is well-sectioned but monolithic — metrics reference, prediction format, and all examples are inlined in one ~190-line file with no bundle files to offload detail to, so it is only partially split.	2 / 3
	Total	9 / 12 Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, well-scoped description with concrete capabilities and natural trigger terms. Its main weakness is the lack of an explicit 'Use when...' trigger clause, leaving the 'when to use' guidance only implied.

Suggestions

Add an explicit 'Use when...' sentence naming the scenarios (e.g. 'Use when evaluating or benchmarking 3D hand tracking systems, visualizing predictions against HOT3D ground truth, or generating evaluation reports').

Broaden trigger terms to include common variations users say, such as 'hand pose estimation', 'pose predictions', and 'keypoint error'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'loading HOT3D data, computing metrics (PA-MPJPE, AUC, etc.), visualizing 3D pose projections, and generating tracking evaluation reports.'	3 / 3
Completeness	Strong 'what' (loads data, computes metrics, visualizes, generates reports) but 'when' is only implied via 'Essential for benchmarking hand tracking algorithms' with no explicit 'Use when...' trigger clause, which caps completeness at 2.	2 / 3
Trigger Term Quality	Covers natural user-facing terms ('hand tracking', 'evaluation', 'benchmarking', 'HOT3D', '3D pose') that a researcher would plausibly say. Missing a few common variations ('hand pose', 'pose estimation') but overall good coverage.	3 / 3
Distinctiveness Conflict Risk	Clear niche — 3D hand tracking on the HOT3D dataset with specific named metrics — making it unlikely to trigger for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/vision/hand-tracking-toolkit/SKILL.md
Commit: df37802

Reviewed: about 1 hour 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.