annotation-data

Dataset annotation management — COCO labels, sequences, export, and Kaggle upload

Quality

64%

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 ./skills/annotation/dataset-management/SKILL.md

Quality

Content

72%

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 and well-structured as a protocol contract, but its message examples leave payload schemas unspecified and it omits validation checkpoints for destructive operations like delete_dataset. Filling in payload shapes and adding verification steps would raise the mid-level dimensions.

Suggestions

Replace the '[...]' placeholders for labels and annotations with concrete field schemas or a short example payload so the message templates are fully actionable.

Add a verification/checkpoint note for destructive and batch commands (e.g., confirm dataset existence before delete_dataset, verify export path after export_coco) to satisfy workflow-clarity level 3.

Briefly note error/invalid-command handling in the Skill → Aegis direction so the protocol contract is complete.

Dimension	Reasoning	Score
Conciseness	The body is lean — a one-line summary plus concrete JSONL protocol examples with no conceptual padding or explanation of things Claude already knows, matching the 'lean and efficient; every token earns its place' anchor.	3 / 3
Actionability	It provides concrete, copy-paste-ready message templates for both protocol directions, but the data payloads use '[...]' placeholders (labels, annotations) with no schema detail and no executable code in the body, fitting the 'some concrete guidance but incomplete' anchor rather than fully executable level 3.	2 / 3
Workflow Clarity	The request/response protocol with request_id correlation is clear, but destructive and batch operations like delete_dataset and export_coco have no validation or verification checkpoints, which per the guidelines caps workflow clarity at 2.	2 / 3
Progressive Disclosure	At under 50 lines with well-organized sections (Protocol, Aegis → Skill, Skill → Aegis) and a single referenced entry script, this self-contained body meets the 'simple skill, well-organized sections' criterion for level 3.	3 / 3
	Total	10 / 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 is specific and distinctive about its annotation-dataset niche but lacks an explicit 'Use when…' trigger clause, which caps its completeness and trigger-term coverage at the mid level. Adding natural trigger phrasing would lift the weaker dimensions.

Suggestions

Append a 'Use when…' clause listing natural triggers (e.g., 'Use when managing annotation datasets, exporting COCO labels, or uploading datasets to Kaggle') to reach completeness level 3.

Reframe capabilities as concrete verbs ('Create, edit, and delete annotation datasets; manage COCO labels; export to COCO format; upload to Kaggle') to strengthen specificity.

Add common keyword variations users might say ('bounding boxes', 'image labels', 'dataset export') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Dataset annotation management') plus several concrete capabilities ('COCO labels, sequences, export, and Kaggle upload'), but the items are noun-based rather than a verb-driven action list, so it stops short of the multi-action level-3 anchor.	2 / 3
Completeness	It clearly states what the skill does but provides no 'Use when…' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	It includes relevant domain terms a user might say ('COCO labels', 'Kaggle upload', 'annotation'), but coverage is partial and misses common variations, matching the 'some relevant keywords but missing common variations' anchor rather than the full level-3 set.	2 / 3
Distinctiveness Conflict Risk	The annotation-dataset niche with COCO-format export and Kaggle upload is specific and unlikely to overlap with unrelated skills, matching the '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: skills/annotation/dataset-management/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.