CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

labelu-data-annotation

Read saved annotations and help users work in the data annotation training workbench.

Quality

71%

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 ./plugins/data-annotation/skills/labelu-data-annotation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 body is exceptionally lean with sensible guardrails (read-only boundary, read-back-before-claiming, no external transmission without authorization) and needs no bundle structure at its size. Its main weakness is actionability: the `input` object is never concretized, leaving the actual tool calls underspecified.

Suggestions

Add one concrete example invocation for each action, e.g. `ipollo_annotation({action: "list-projects", input: {...}})` with the actual input fields, so calls are copy-paste ready.

Specify the required and optional fields of the `input` object for `list-projects` and `get-project` (e.g. project ID, pagination) to close the key execution gap.

DimensionReasoningScore

Conciseness

The body is ~6 lean lines covering tool name, actions, workspace context, and safety constraints with zero padding or explanation of concepts Claude already knows; every sentence (including the workbench context that grounds the read-only boundary) earns its place.

5 / 5

Actionability

Concrete guidance exists (tool name `ipollo_annotation`, actions `list-projects`/`get-project`) but it is incomplete: "an `input` object" is specified with no fields or example invocation, so a call cannot be constructed without guessing — matching the missing-key-details anchor rather than the minor-gaps level of 4.

3 / 5

Workflow Clarity

The single-action workflow is clear and includes an explicit checkpoint ("do not... claim a saved result until it has been read back") plus a read-only guardrail, but the unspecified `input` structure keeps the action from being fully unambiguous, so the simple-skill score of 5 is not reached.

4 / 5

Progressive Disclosure

This is an under-50-line skill with no bundle files (no references/, scripts/, or assets/ exist) and no content that needs external files; the short single-paragraph form is appropriately self-contained per the simple-skill exception.

5 / 5

Total

17

/

20

Passed

Description

50%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 names a specific niche domain and one concrete capability (reading saved annotations) but omits any usage triggers and most natural synonym terms. It is serviceable but would benefit most from an explicit when-to-use clause and broader trigger vocabulary.

Suggestions

Add an explicit 'Use when...' clause, e.g. "Use when the user asks about annotation projects, labeling progress, or saved annotation results in the data annotation training workbench."

Broaden trigger vocabulary with natural synonyms users would actually say: labeling, labels, 标注, LabelU, annotation tasks, annotation projects.

Replace the generic "help users work in the data annotation training workbench" with the concrete capabilities offered, such as listing annotation projects and fetching project details.

DimensionReasoningScore

Specificity

"Read saved annotations" is one concrete action and the domain ("data annotation training workbench") is named, matching the anchor for domain plus 1-2 concrete actions; the remainder ("help users work in the... workbench") is generic, so it does not reach the several-specific-actions level of 4.

3 / 5

Completeness

The "what" is reasonably clear (reading saved annotation records) but the "when" is entirely absent — there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3; it is not a 2 because the what is concrete, not vague.

3 / 5

Trigger Term Quality

"annotations" and "data annotation" are relevant natural keywords, but common variations users would say — labeling, labels, 标注, LabelU, annotation tasks/projects — are missing, matching the some-keywords-missing-synonyms anchor rather than the good-coverage level of 4.

3 / 5

Distinctiveness Conflict Risk

"data annotation training workbench" names a fairly niche domain, but the only trigger-ish terms ("annotations", "data annotation") could overlap with other labeling/annotation skills, fitting the somewhat-specific-but-could-overlap anchor rather than the mostly-distinct level of 4.

3 / 5

Total

12

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

Devin-AXIS/iPolloWork

Path

plugins/data-annotation/skills/labelu-data-annotation/SKILL.md

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.