provider-health

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

Quality

64%

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

72%

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 and well-structured for a simple skill, with concrete script paths, fix commands, and a precise output shape. Its main weaknesses are time-sensitive version numbers embedded in the main flow and the absence of an explicit validation checkpoint.

Suggestions

Move the version thresholds ('v2.1.219', 'v0.144.0') into a clearly labeled 'Version drift thresholds (verify currency)' section so the main steps stay evergreen and conciseness is not penalized for stale values.

Add an explicit validation checkpoint after detection, e.g. 'If a detection script errors, re-run it once and only then mark the provider DOWN — do not report from prior session state.'

Note that the referenced scripts live at ${CLAUDE_PLUGIN_ROOT}/scripts/helpers (plugin-level, outside this skill bundle) so the one-level reference is unambiguous to maintainers.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's intelligence with no concept padding, but time-sensitive version thresholds ('v2.1.219', 'v0.144.0', 'GPT-5.6', 'Opus 5') sit in the main steps rather than a deprecated section, which the rubric penalizes, holding it at anchor 2.	2 / 3
Actionability	Gives exact executable script paths ('check-providers.sh', 'check-versions.sh'), concrete fix commands ('grok login', 'opencode auth login', key export), named provider rosters, and exact table columns — fully copy-paste ready, matching anchor 3.	3 / 3
Workflow Clarity	A clear 4-step ranked sequence is present, but there is no explicit validation checkpoint or error-recovery feedback loop; the detection-as-source-of-truth checkpoint is only implicit via the guardrails, matching anchor 2.	2 / 3
Progressive Disclosure	A single under-50-line file with well-organized sections (When to use, Steps, Output shape, Guardrails) and only one-level-deep plugin-script references with exact paths — no nesting — matching anchor 3 for a simple skill.	3 / 3
	Total	10 / 12 Passed

Description

57%

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 conveys a clear, distinctive niche and concrete deliverable components but omits any explicit trigger guidance, leaving the 'when to use' half unanswered. It is specific in domain yet thin on natural trigger terms users would say.

Suggestions

Append a 'Use when...' clause with natural triggers, e.g. 'Use when the user asks what providers they have, a workflow shows (unavailable - skipping), or a session starts on a new machine.'

Rephrase jargon like 'seatable provider' and 'cost posture' toward language users actually say, and add common variations (e.g. 'provider status', 'which models are available').

Lead with the concrete action(s) the skill performs (e.g. 'Detects, summarizes, and ranks provider health') so the description reads as actions rather than only a deliverable's attributes.

Dimension	Reasoning	Score
Specificity	Names a domain and concrete summary components ('availability, auth method, version drift, and cost posture') but describes a deliverable's attributes rather than enumerating multiple distinct actions, matching anchor 2.	2 / 3
Completeness	The 'what' is clear (one-screen provider health summary with named components) but 'when' is entirely missing — no explicit trigger guidance, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Some relevant keywords ('provider', 'health', 'availability', 'auth') appear, but jargon ('seatable provider', 'cost posture', 'version drift') dominates and there is no 'Use when...' phrasing or common variations, so it does not reach anchor 3.	2 / 3
Distinctiveness Conflict Risk	The multi-provider health niche with version drift and cost posture is narrow and unlikely to overlap with generic skills, matching anchor 3 rather than the 'somewhat specific' anchor 2.	3 / 3
	Total	9 / 12 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: 9f39f0c

Reviewed: 2 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.