CtrlK
BlogDocsLog inGet started
Tessl Logo

terra-auth

Terra API authentication, credentials management, and environment configuration. Use when setting up Terra integration, managing API keys, generating widget sessions, or configuring testing/staging/production environments.

63

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/terra-auth/SKILL.md
SKILL.md
Quality
Evals
Security

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.

Highly actionable content with complete, executable Python and cURL examples and useful reference tables, but it is held back by triple-duplicated credentials, an inline reimplementation of a helper whose import path does not exist in the bundle, and the absence of any validation checkpoint around the destructive deauthenticate operation.

Suggestions

State the credential values once (e.g., in the environment table or a reference file) and reference them from the Quick Start, setup-environment, and cURL examples instead of repeating all three dev_id/api_key pairs verbatim.

Add a validation step to deauthenticate-user before revoking access (e.g., confirm the user_id exists and the caller intends removal, then check the response), and verify connections with an explicit success check rather than a bare print.

Either ship the referenced scripts/terra_client.py helper in the bundle or remove the 'from scripts.terra_client import get_terra_client' import and keep only the inline implementation, so the skill's references match its actual files.

DimensionReasoningScore

Conciseness

The same credential dev_id/api_key pairs are pasted three times (Quick Start env vars, the setup-environment config dict, and the cURL example), and get_terra_client is shown both as a helper import and again as a full inline reimplementation. This redundant duplication is unnecessary token spend, though there is no padding that explains concepts Claude already knows — squarely the 3 anchor 'mostly efficient but could be tightened', not the 2 anchor's pervasive verbosity.

3 / 5

Actionability

Every operation ships copy-paste-ready executable code with usage examples, expected response shapes, and concrete values; the REST section adds a working cURL example and header table. This matches the 5 anchor 'fully executable; copy-paste ready code or commands; specific examples cover the common cases'.

5 / 5

Workflow Clarity

Each operation is unambiguous individually, but the skill documents the destructive deauthenticate-user ('Remove user and revoke data access') with no validation or verification step, which caps this dimension at 3 per the destructive-operation rule. There is also no validation on the connection-verify step beyond a print, fitting the 3 anchor 'sequence present but checkpoints missing or implicit' rather than the 4 anchor's 'most checkpoints present'.

3 / 5

Progressive Disclosure

Sections are well-organized, but the body references 'from scripts.terra_client import get_terra_client' and no scripts/ directory exists in the bundle — a broken reference that would fail on use — and the credential config duplicated inline belongs in that script or a reference file. This fits the 3 anchor ('content that should be separate is inline', references not fully sound) better than the 4 anchor's 'most content appropriately placed' with only minor gaps.

3 / 5

Total

14

/

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 strong description: concrete capability statement paired with an explicit 'Use when...' clause enumerating natural trigger phrases in third person. Main weaknesses are minor coverage gaps (deauthentication, mobile tokens) and slight overlap with sibling Terra skills on the broad 'setting up Terra integration' trigger.

DimensionReasoningScore

Specificity

The description lists several concrete actions — 'Terra API authentication, credentials management, and environment configuration' plus 'managing API keys, generating widget sessions' — but omits operations the body covers (deauthenticating users, mobile SDK tokens), leaving minor gaps. It exceeds the 3 anchor ('1-2 concrete actions') in breadth but falls short of the comprehensive coverage of a 5.

4 / 5

Completeness

It explicitly answers both what ('Terra API authentication, credentials management, and environment configuration') and when ('Use when setting up Terra integration, managing API keys, generating widget sessions, or configuring testing/staging/production environments') with concrete trigger phrases in third person, matching the 5 anchor exactly. The 4 anchor's weaker 'when' does not apply since triggers are specific and enumerated.

5 / 5

Trigger Term Quality

Natural phrases users would say are present: 'setting up Terra integration', 'managing API keys', 'generating widget sessions', 'configuring testing/staging/production environments'. A few natural variants are missing (e.g., 'auth', 'login', 'connect wearables'), matching the 4 anchor's 'good keyword coverage; a few natural terms missing' rather than the synonym-complete 5.

4 / 5

Distinctiveness Conflict Risk

The 'Terra API' scope carves a clear niche, but the trigger 'setting up Terra integration' overlaps with closely related sibling skills (terra-sdk, terra-connections), matching the 4 anchor 'mostly distinct; minor overlap risk'. It is not a 5 because integration setup requests could plausibly route to those skills instead.

4 / 5

Total

17

/

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
fernandezbaptiste/Skrillz
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.