skill-native-escalation-routing

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

Quality

66%

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

Quality

Content

75%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 well-structured, mostly lean routing skill with concrete decision criteria and examples; it would benefit from a compact decision tree and trimming the redundant framing section.

Suggestions

Add a compact decision tree or routing checklist (e.g. 'multiple opinions requested? -> Octopus; else native') to make the workflow unambiguous at a glance.

Trim the 'Suggested User Framing' section or fold it into 'Execution Guidance', since it restates the core policy already covered above.

Resolve the reference to skills/blocks/codex-host-adapter.md — either confirm it resolves from the skill bundle or move that host-adapter note to a bundled reference file.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, using tight bullet lists and examples; minor redundancy comes from the 'Suggested User Framing' section restating the core policy and the slash-command list appearing twice.	4 / 5
Actionability	Concrete decision criteria (native-first conditions, escalation conditions), explicit example phrases, and clear execution rules give mostly executable routing guidance with only minor gaps.	4 / 5
Workflow Clarity	The decision flow is clear — evaluate native-first conditions, else escalate, with explicit execution guidance — but it lacks an explicit decision tree or checklist that would make routing unambiguous in ambiguous cases.	4 / 5
Progressive Disclosure	Well-organized into clearly labeled sections with a single one-level-deep reference to codex-host-adapter.md; no bundle files exist, and the slight over-50-line length and the out-of-bundle reference keep it just short of a 5.	4 / 5
	Total	16 / 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 is a clear 'Use when' trigger with both what and when, but it stays at a routing/decision level of specificity, uses a narrow set of trigger terms, and overlaps with the very native skills it arbitrates between.

Suggestions

Add concrete trigger synonyms users actually say, e.g. 'initialize this repo', 'code review', 'security audit', 'get multiple model opinions'.

Sharpen the 'what' beyond 'choosing' to name the outcome, e.g. 'Routes init/review/security requests to Claude-native handling or Octopus multi-LLM escalation based on whether multiple model opinions or adversarial review are needed.'

Differentiate from native review skills by making the escalation signal explicit in the description, e.g. 'Use when the user wants multiple model opinions or adversarial review, not ordinary single-model review.'

Dimension	Reasoning	Score
Specificity	Names the request domain ('init, review, or security requests') and one concrete meta-action ('choosing native or multi-LLM handling'), but coverage is not comprehensive and the action is a routing decision rather than a set of concrete capabilities.	3 / 5
Completeness	Both 'what' ('choosing native or multi-LLM handling') and 'when' ('Use when ... for init, review, or security requests') are present with concrete trigger phrases, though the 'what' is a thin meta-action.	4 / 5
Trigger Term Quality	Includes natural terms a user would say ('init', 'review', 'security requests') but misses common variations and synonyms such as 'initialize', 'code review', 'audit', or 'multiple model opinions'.	3 / 5
Distinctiveness Conflict Risk	The escalation/multi-LLM niche is distinct, but the trigger terms overlap heavily with the native /init, /review, and /security-review skills it routes between, creating real overlap risk.	3 / 5
	Total	13 / 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/skill-native-escalation-routing/SKILL.md
Commit: 242e51d

Reviewed: 3 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.