dmk-business-logic

Explain the design rationale and domain concepts behind the Ledger Device Management Kit (DMK) API, including Clear Signing, Secure Channel, Ledger OS (BOLOS), Device Actions vs Commands, sessions, transports, derivation paths, and Genuine Check. Use when a developer asks 'what is X?' about a DMK concept, 'why does X work this way?' about an API design decision, or 'what's the difference between X and Y?' for DMK components.

1.12x

Quality

—

Does it follow best practices?

Impact

100%

1.12x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

80%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An information-rich, actionable concept reference with executable examples, but it is a monolithic single-file document with no progressive disclosure to separate reference files and no workflow validation checkpoints.

Suggestions

Split large topic sections (e.g. Clear Signing, Secure Channel, Derivation Paths) into one-level-deep reference files under references/ and link to them from a concise overview in SKILL.md, so the main file stays a navigable hub.

For the operational sequences that do exist (Secure Channel setup, Clear Signing enablement), add explicit validation/feedback steps — e.g. 'after connect, verify session state is Connected before proceeding' — to lift workflow clarity.

Tighten the few general-knowledge asides (e.g. 'Given the same seed phrase, the same path always produces the same key') to only the DMK-specific implication, removing context Claude already has.

Dimension	Reasoning	Score
Conciseness	The body is dense with DMK-specific knowledge Claude lacks (Clear Signing, Secure Channel handshake, derivation-path parsing quirks) rather than general concepts, and its code snippets are minimal and purposeful; a few contextual asides (e.g. seed-phrase determinism) are brief and domain-anchored, so most tokens earn their place.	3 / 3
Actionability	Provides concrete, executable TypeScript snippets (SignerEthBuilder with/without originToken, the sessionRefresher connect call, the BOLOS dashboard check) plus exact derivation-path strings and decision tables — copy-paste ready guidance, not pseudocode.	3 / 3
Workflow Clarity	Some multi-step sequences exist (e.g. the 4-step Secure Channel handshake, the Clear Signing setup) and each topic follows a consistent What/Why/How structure, but there are no validation checkpoints or error-recovery feedback loops because the skill is explanatory rather than operational.	2 / 3
Progressive Disclosure	No bundle files exist and the entire ~230-line concept catalog lives inline in SKILL.md; internal sectioning is clear and there are no nested references, but at this length content that could be split into per-topic reference files is kept monolithic with no signaled navigation to deeper material.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 strong, third-person description that clearly states what the skill covers and when to use it, with natural quoted trigger phrases and a distinct DMK-scoped niche.

Dimension	Reasoning	Score
Specificity	Names the concrete domain it covers ('design rationale and domain concepts') and enumerates many specific topics — 'Clear Signing, Secure Channel, Ledger OS (BOLOS), Device Actions vs Commands, sessions, transports, derivation paths, and Genuine Check' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both 'what' (explain rationale and domain concepts, with a named topic list) and 'when' (an explicit 'Use when...' clause with three concrete trigger patterns), matching the top anchor.	3 / 3
Trigger Term Quality	The 'Use when' clause quotes natural developer phrasing verbatim — "'what is X?'", "'why does X work this way?'", "'what's the difference between X and Y?'" — exactly the phrases a user would say, giving good coverage of natural trigger terms.	3 / 3
Distinctiveness Conflict Risk	Scoped tightly to 'Ledger Device Management Kit (DMK) API' concepts with triggers phrased as DMK-specific questions, giving it a clear niche unlikely to fire for unrelated skills; uses third-person voice ('Explain').	3 / 3
	Total	12 / 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: LedgerHQ/agent-skills
Commit: c9739bb

Reviewed: 6 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.