provider-health

Starter: one-screen provider health summary — availability, auth method, version drift, and cost posture for every seatable provider

Quality

74%

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 ./skills/octopus-starter-pack/provider-health/SKILL.md

Quality

Content

90%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 tight, highly actionable body: concrete commands, explicit output contract, and a strong anti-drift guardrail with zero padding. The only gaps are a missing failure-handling checkpoint in the workflow and script references that don't resolve within the bundle.

Dimension	Reasoning	Score
Conciseness	Every line carries instruction: exact commands, thresholds, a defined output shape, and a guardrail, with no explanation of concepts Claude already knows. This matches the lean-and-efficient anchor; the brief purpose statements ("before spending money") earn their place by constraining behavior.	5 / 5
Actionability	Fully executable guidance: exact script paths ("${CLAUDE_PLUGIN_ROOT}/scripts/helpers/check-providers.sh"), concrete fix commands ("grok login", "opencode auth login", key export), precise version thresholds, and an explicit table schema. Matches the copy-paste-ready anchor covering the common cases.	5 / 5
Workflow Clarity	Four well-sequenced steps with a ranked problem taxonomy and a report-only-what-detection-returns guardrail, matching the clear-sequence/most-checkpoints anchor. Not 5 because there is no explicit validate-and-retry checkpoint (e.g., what to do if a detection script fails or a provider is missing from the report); not 3 because the guardrail does function as an implicit correctness check for a read-only operation.	4 / 5
Progressive Disclosure	Well-organized sections (When to use, Steps, Output shape, Guardrails) with appropriately brief content. Not 5 because the two referenced helper scripts do not exist in the skill bundle (no scripts/ directory), so the references cannot be verified against the actual bundle structure; not 3 because the body itself is correctly scoped and easy to navigate.	4 / 5
	Total	18 / 20 Passed

Description

58%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 states a clear, specific "what" with a well-scoped niche, but omits any "when to use" guidance and under-covers natural trigger phrasing. Adding a Use-when clause with user-facing phrases would lift the two lowest dimensions.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks what providers they have, a workflow banner shows (unavailable - skipping), or a session starts on a new machine."

Include natural synonyms users would say, such as "provider status", "which models are available", or "check my providers", to improve trigger term coverage.

Lead with an action verb in third person (e.g. "Reports provider health: ...") to strengthen the concrete-actions framing of the capability list.

Dimension	Reasoning	Score
Specificity	Enumerates four concrete content dimensions ("availability, auth method, version drift, and cost posture for every seatable provider"), matching the several-specific-items anchor. Not 5 because these are topics rather than concrete actions, and not 3 because it goes well beyond naming 1-2 items.	4 / 5
Completeness	The "what" is clear (one-screen health summary with explicit dimensions), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not 2 because the "what" is explicit rather than vague.	3 / 5
Trigger Term Quality	"provider health", "availability", and "auth" are relevant keywords, but common natural variations users would actually say ("what providers do I have", "provider status", "which models are available") are missing. This matches the some-relevant-keywords-but-missing-synonyms anchor rather than the good-coverage anchor above it.	3 / 5
Distinctiveness Conflict Risk	Niche vocabulary ("seatable provider", "cost posture", "version drift") makes it mostly distinct with minimal overlap risk. Not 5 because, lacking explicit triggers, closely related provider-configuration or model-selection skills could still vie for the same request.	4 / 5
	Total	14 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: nyldn/claude-octopus
Path: skills/octopus-starter-pack/provider-health/SKILL.md
Commit: 0093dab

Reviewed: 5 days 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.