CtrlK
BlogDocsLog inGet started
Tessl Logo

terra-troubleshooting

Terra API troubleshooting and debugging. Use when experiencing connection issues, data sync problems, webhook failures, SDK errors, or provider-specific issues.

60

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/terra-troubleshooting/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.

A strong, dense troubleshooting catalog that is highly actionable per-issue but reads as a monolith: no references, no overall triage workflow, and some duplicated or non-executable snippets. The description is solid; the body's main gains lie in restructuring and adding verification steps.

Suggestions

Add an explicit top-level diagnostic workflow at the top (run the health check → match the failing category → apply the fix → verify the symptom is resolved), and end key solutions with a verification step (e.g. re-run check_user_data or re-test the webhook after each fix).

Split the body into one-level-deep reference files (e.g. references/provider-issues.md, references/sdk-issues.md, references/webhook-verification.md), keeping SKILL.md as a concise overview with well-signaled links.

Remove the duplicated Health Check Script section (it repeats Quick Diagnostics), add the missing `import os`, and either delete or flesh out comment-only code blocks like the Garmin 'solution'.

DimensionReasoningScore

Conciseness

The body uses a tight Cause/Solution format with code-first content and no explanation of concepts Claude already knows, but it carries redundancy: the closing "Health Check Script" largely duplicates the "Quick Diagnostics" section, and a few blocks (e.g. the Garmin solution) are comment-only filler. Anchor 4 (efficient, minor instances that could be trimmed); not 5 because of the duplicated health-check content.

4 / 5

Actionability

Mostly copy-paste-ready code with concrete specifics (webhook IP allowlist, per-provider historical-data table, signature debug function). Minor gaps keep it below anchor 5: `os` is never imported in the ENVIRONMENTS and health-check blocks, the Swift function signature is truncated, the MyFitnessPal retry uses positional args unlike the keyword style elsewhere, and the Garmin "solution" is comments only.

4 / 5

Workflow Clarity

The content is a symptom catalog with an entry-point health check and one ordered checklist ("Webhooks not received"), but there is no top-level triage sequence (health check → classify symptom → apply fix → verify) and most solutions end without a verify-the-fix checkpoint. Fits anchor 3 (sequence present per-issue, checkpoints missing or implicit); not 4 because the overall diagnostic flow and validation steps are not explicitly stitched together.

3 / 5

Progressive Disclosure

Roughly 500 lines are inlined in a single file with no bundle files at all; section headers keep it navigable, but provider-specific and per-platform SDK detail (iOS/Android/React Native, provider quirks) would fit naturally in one-level-deep reference files. Anchor 3 (some structure, content that should be separate is inline); not 2 because the headers and consistent Cause/Solution organization make it easy to scan.

3 / 5

Total

14

/

20

Passed

Description

78%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-formed description with an explicit and well-triggered when-clause; the main weakness is that the stated actions are generic verbs, leaving the real capability picture implicit. There is also modest trigger overlap with the sibling terra-* skills.

Suggestions

Replace the generic verbs with the concrete capabilities the skill actually delivers, e.g. "Diagnose Terra API connection, webhook, data-sync, and SDK errors with cause-solution recipes and health-check scripts."

Add one or two high-frequency natural terms users say, such as specific provider names (Garmin, Fitbit, WHOOP) or "webhook signature verification failed".

Add a disambiguating phrase (e.g. "for debugging and error resolution, not initial integration — see terra-* setup skills") to reduce wrong-skill triggering against the sibling skills.

DimensionReasoningScore

Specificity

The description names the domain ("Terra API") and two actions ("troubleshooting and debugging"), but those verbs are generic — the concrete specificity comes from the when-clause's issue list rather than the stated capabilities. Matches anchor 3 (domain plus 1-2 actions, not comprehensive); not 4 because the 'what' verbs themselves are not distinct specific actions.

3 / 5

Completeness

Explicitly answers both questions: the what ("Terra API troubleshooting and debugging") and a concrete when-clause ("Use when experiencing connection issues, data sync problems, webhook failures, SDK errors, or provider-specific issues") with multiple concrete trigger phrases, matching the anchor-5 example pattern.

5 / 5

Trigger Term Quality

"connection issues, data sync problems, webhook failures, SDK errors, provider-specific issues" are natural phrases a user would say, giving good keyword coverage. Not 5 because common variations and specific provider names (Garmin, Fitbit, WHOOP, duplicate data, signature verification) that the body covers are absent from the description.

4 / 5

Distinctiveness Conflict Risk

"Terra API" carves out a clear niche with distinct triggers, but the trigger terms (webhook failures, SDK errors, connection issues) overlap the sibling terra-webhooks, terra-sdk, and terra-connections skills referenced in the body, creating minor wrong-skill risk. Fits anchor 4 (mostly distinct, minor overlap with closely related skills), not 5.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (508 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

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.