skill-native-escalation-routing

Use when choosing native or multi-LLM handling for init, review, or security requests

Quality

68%

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 ./.claude/skills/skill-native-escalation-routing/SKILL.md

Quality

Content

67%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 clear, well-structured routing policy skill with concrete slash commands, decision criteria, and example triggers. Its main weakness is redundancy across the Core Policy, criteria, and Suggested User Framing sections, which costs conciseness.

Suggestions

Remove the 'Suggested User Framing' section or fold its one useful sentence into Core Policy, since it restates the native-first/escalation policy already covered above.

Merge the Core Policy slash-command list into the two criteria sections to avoid listing the same commands twice.

Add an explicit decision ordering (e.g. '1. Check escalation triggers; 2. Otherwise route native; 3. If ambiguous, default native and surface Octopus') so the workflow reads as a single sequenced procedure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and free of concept over-explanation, but the 'Suggested User Framing' section restates the Core Policy and the criteria sections overlap the slash-command list, so it could be tightened rather than earning the lean 4 or 5.	3 / 5
Actionability	It gives concrete, executable routing guidance — specific slash commands (/init, /review, /octo:review), explicit decision criteria, and example user phrases — with only minor gaps, fitting 'mostly executable guidance' for an instruction-only skill.	4 / 5
Workflow Clarity	The decision logic is clearly sequenced: native-first conditions, escalation conditions, and an explicit ambiguous-case fallback ('prefer Claude-native first and mention Octopus'), which is a clear sequence with most checkpoints present rather than the full validation-loop 5.	4 / 5
Progressive Disclosure	Content is well-organized into clearly labeled sections with no nested references and no need for external files, but at ~60 lines with some structural redundancy it sits just below the ideal one-level-deep 5 for a simple skill.	4 / 5
	Total	15 / 20 Passed

Description

70%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 concise, third-person description with an explicit 'Use when' trigger and a clear routing niche. It is held back from the top band by a somewhat abstract 'what' and a single broad action verb rather than several concrete capabilities.

Suggestions

Replace the abstract 'choosing ... handling' with concrete routing actions, e.g. 'Routes init, review, and security requests to Claude-native or Octopus multi-LLM escalation'.

Add a natural synonym users say, such as 'multiple model opinions' or 'multi-LLM review', to broaden trigger coverage beyond 'multi-LLM handling'.

Dimension	Reasoning	Score
Specificity	The description names the domain (init, review, security) and a single concrete action ('choosing native or multi-LLM handling'), but does not enumerate several distinct capabilities, matching the 'names domain and 1-2 concrete actions' anchor rather than the several-actions anchor at 4.	3 / 5
Completeness	Both halves are present — 'Use when ... init, review, or security requests' gives the when and 'choosing native or multi-LLM handling' gives the what — but the what is somewhat abstract, so it sits at 4 rather than the fully explicit 5.	4 / 5
Trigger Term Quality	It surfaces natural user terms ('init', 'review', 'security requests') that users actually say, with only the jargon 'multi-LLM handling' being less user-natural, fitting 'good keyword coverage; a few natural terms missing' rather than the comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	The native-vs-multi-LLM routing niche is clearly distinguishable from ordinary review/init skills, with only minor overlap risk on the shared init/review/security triggers, matching 'mostly distinct; minor overlap risk'.	4 / 5
	Total	15 / 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: .claude/skills/skill-native-escalation-routing/SKILL.md
Commit: 1bee725

Reviewed: 4 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.