terra-data

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

Quality

70%

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 ./.claude/skills/terra-data/SKILL.md

Quality

Content

57%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.

A thorough, highly actionable reference for Terra data retrieval, but it is a long monolithic file that inlines reference-grade material and lacks validation checkpoints for its batch and database operations.

Suggestions

Move the per-data-type full JSON response samples, the provider historical-limits table, and the SQL schema into separate reference files (e.g. references/responses.md, references/providers.md, references/schema.sql) and link to them from SKILL.md to improve progressive disclosure and conciseness.

Add validation/verification steps to the backfill and handle_data_update workflows (e.g. confirm upsert row counts, retry/verify webhook delivery for >28-day async requests) so batch and database operations have explicit feedback loops.

Tighten the per-operation sections by showing one representative request/response pair inline and pointing the rest to the reference file, removing the duplicated 'always OVERWRITE previous data' note.

Dimension	Reasoning	Score
Conciseness	API-specific content with no concept padding, but ~550 lines with a full JSON sample inlined per data type and a repeated OVERWRITE note could be tightened by moving bulk samples to reference files, fitting the 'mostly efficient but could be tightened' anchor.	3 / 5
Actionability	Concrete copy-paste-ready code covering every data type, bulk retrieval, backfill, writes, and DB schema, with only minor gaps ('os' unimported in Quick Start; async get_all_user_data calls sync .get()), so it is 'mostly executable' rather than fully gap-free.	4 / 5
Workflow Clarity	The backfill branch and update-strategy code give a rough sequence, but batch backfill and DB upsert operations lack validation/verification and feedback loops, so the rubric's batch/destructive cap holds workflow_clarity at 3.	3 / 5
Progressive Disclosure	Sections are clearly organized, but it is a monolithic ~550-line file with no bundle files; per-data-type JSON samples, the provider-limits table, and the DB schema are inline material that belongs in separate reference files.	3 / 5
	Total	13 / 20 Passed

Description

83%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.

A well-constructed description that clearly states both capability and trigger conditions with a concrete data-type list. Minor improvements would add provider-name triggers and a second concrete verb beyond 'fetching'.

Dimension	Reasoning	Score
Specificity	Names the Terra domain and lists concrete data types to fetch ('activity, sleep, body, daily, nutrition, menstruation, or athlete data'), but action verbs are limited (retrieval/fetching) and 'management' is vague, so it stops short of the multi-verb anchor 5.	4 / 5
Completeness	Explicitly answers both what ('Terra API health data retrieval and management') and when ('Use when fetching ... data from wearables') with concrete trigger phrases, matching the anchor 5 example.	5 / 5
Trigger Term Quality	'Use when fetching ... data from wearables' covers all data types plus 'wearables', but omits provider names (Garmin, Fitbit, Oura) and synonyms like 'fitness tracker' that users naturally say, keeping it below the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche with distinct wearable-data triggers, but a sibling terra-sdk skill (listed in the body) creates minor overlap risk, so it is not the minimal-conflict anchor 5.	4 / 5
	Total	17 / 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: .claude/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.