terra-data

Terra API health data retrieval and management. Use when fetching activity, sleep, body, daily, nutrition, menstruation, or athlete data from wearables.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/terra-data/SKILL.md

Quality

Content

65%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 highly actionable with concrete code and sample responses, but it is verbose and monolithic, and its batch/database/write workflows omit validation checkpoints. Splitting reference material into bundle files and adding verification steps would raise the weaker dimensions.

Suggestions

Add validation/verification checkpoints to the batch and write workflows: confirm webhook delivery for >28-day backfill, verify post responses succeed, and validate upserted rows in handle_data_update before declaring success.

Move per-data-type sample JSON responses, the database schema, and the provider historical-limits table into separate reference files under references/, linking to them from the body so the SKILL.md body stays a lean overview.

Collapse the seven near-identical get_* function definitions into a single parameterized pattern plus a table of per-type return fields to remove the repeated boilerplate.

Dimension	Reasoning	Score
Conciseness	Content is mostly efficient code and tables, but near-identical get-function boilerplate repeats across seven operations and full verbose sample JSON responses are inlined for each data type, so it could be tightened.	3 / 5
Actionability	Provides concrete, copy-paste-ready calls (e.g. client.activity.get(user_id, start_date, end_date)) plus full sample JSON responses covering the common cases for each data type.	5 / 5
Workflow Clarity	Sequences are present (quick start, backfill branching at >28 days) but batch backfill, database upsert/insert in handle_data_update, and Writing Data posts all lack validation or verification checkpoints, capping this dimension at 3 per the rubric.	3 / 5
Progressive Disclosure	The ~550-line body is well-sectioned but monolithic: per-data-type sample responses, the database schema, and provider-limits table are all inlined with no reference files, and only external Related-Skills links are offered.	3 / 5
	Total	14 / 20 Passed

Description

87%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 is strong: it states the capability concretely, gives an explicit 'Use when' trigger with the supported data types, and occupies a distinct niche. The only gaps are unmentioned write/webhook capabilities and a few missing trigger synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete actions ('retrieval and management') across seven enumerated data types (activity, sleep, body, daily, nutrition, menstruation, athlete), but omits write/webhook capabilities the body actually supports, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both 'what' ('Terra API health data retrieval and management') and 'when' (concrete 'Use when fetching...' trigger listing the data types) in third person.	5 / 5
Trigger Term Quality	'Use when fetching activity, sleep, body, daily, nutrition, menstruation, or athlete data from wearables' supplies good natural keyword coverage, though a few common synonyms or device-brand terms are absent.	4 / 5
Distinctiveness Conflict Risk	Clear niche scoped to the Terra API and wearable health data with distinct data-type triggers, giving minimal overlap with other skills.	5 / 5
	Total	18 / 20 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
skill_md_line_count	SKILL.md is long (553 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/terra-data/SKILL.md
Commit: 93ed392

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.