omni-resilience

Monitor provider health, circuit-breaker states, p50/p95/p99 latency metrics, and budget guard alerts. Inspect connection cooldowns and model lockouts in real time.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/omni-resilience/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 a strong, executable API reference with concrete curl commands, response shapes, and error codes, well-organized into navigable sections. Its main weakness is duplicated/conflicting health-endpoint content from the generated and curated blocks that hurts conciseness and clarity.

Suggestions

De-duplicate the health-endpoint content: remove the stub '## Endpoints'/'## System health' generated block or merge it into the curated '## System health' section to avoid two env-var conventions ($OMNIROUTE_TOKEN vs $OMNIROUTE_KEY).

Resolve the inconsistent auth env vars across sections so the skill presents one canonical setup (OMNIROUTE_URL/OMNIROUTE_KEY or the token-based variant).

Expand the '## Errors' list into a short recovery sequence (e.g. retry 503 after 5s, then escalate) to add validation/feedback-loop clarity.

Dimension	Reasoning	Score
Conciseness	Mostly efficient curl+JSON reference content with little concept over-explanation, but duplicated health sections (the generated '## Endpoints/## System health' block plus the curated '## System health') and a redundant '## Endpoints' stub add tokens that could be tightened.	2 / 3
Actionability	Provides fully executable curl commands with auth headers, a real POST payload for the budget guard, concrete JSON response shapes, an MCP tool list, and error codes — copy-paste ready.	3 / 3
Workflow Clarity	It is a reference/look-up skill with unambiguous single actions, but duplicated and partly conflicting health sections (two env-var conventions) and a thin error list without recovery sequencing leave the structure with validation/sequence gaps.	2 / 3
Progressive Disclosure	Content is organized into clearly-labeled topic sections (health, circuit breakers, metrics, MCP, quota, budget, audit, errors) with external references (entry-point SKILL URL, OpenAPI spec) signaled one level deep; no bundle files exist to navigate.	3 / 3
	Total	10 / 12 Passed

Description

60%

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 is specific and concrete about monitoring actions and metrics but lacks an explicit trigger ('Use when...') clause that would tell Claude when to invoke it. It is concise and third-person, with a reasonably distinct niche.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when diagnosing provider outages, circuit-breaker lockouts, latency regressions, or budget-limit issues in OmniRoute.'

Broaden trigger terms to cover natural user phrasings ('provider down', 'spend limit', 'quota reset', 'rate-limited') to improve trigger-term quality.

Tie the metrics to a single clear product niche (OmniRoute monitoring) to further reduce overlap with generic ops/cost skills.

Dimension	Reasoning	Score
Specificity	Names several concrete monitoring actions and objects ('provider health, circuit-breaker states, p50/p95/p99 latency metrics, and budget guard alerts', 'connection cooldowns and model lockouts'), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly states what the skill does but provides no explicit 'Use when...' trigger clause; per rubric guidelines a missing trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	Includes some natural, relevant terms (provider health, latency, budget) but stays fairly technical and omits common user phrasings like 'is my provider down' or 'check my spend'; missing common variations.	2 / 3
Distinctiveness Conflict Risk	The monitoring/latency/budget niche is fairly specific and concrete, reducing broad conflict risk, yet it could still overlap with general ops or cost-monitoring skills; not maximally distinct.	2 / 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: diegosouzapw/OmniRoute
Path: skills/omni-resilience/SKILL.md
Commit: 3070925

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.