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

82%

Does it follow best practices?

Impact

100%

1.12x

Average score across 3 eval scenarios

Securityby

Medium

Suggest reviewing before use

Quality

Content

65%Weight 40%Scale 1-3

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

A well-organized, concept-rich reference with concrete executable examples and useful tables, but it is a long monolithic inline document that could benefit from splitting into one-level-deep reference files and tighter prose. Actionability is its strongest dimension; conciseness and progressive disclosure are the main weaknesses.

Suggestions

Split each major topic (Clear Signing, Secure Channel, Derivation Paths, etc.) into one-level-deep reference files in ./references/ and keep SKILL.md as a concise overview that links to them, improving progressive disclosure and token efficiency.

Tighten the conceptual prose — for example, merge the Clear Signing 'What it means' and 'Why it matters' blocks into a few dense sentences so the body assumes more of Claude's competence.

For the multi-step processes that do exist (e.g. Secure Channel handshake, session recovery after Disconnected), add explicit validation/error-recovery checkpoints to lift workflow clarity toward the anchor-3 pattern.

Dimension	Reasoning	Score
Conciseness	The ~230-line body delivers dense domain knowledge Claude does not already have (justified for a concepts skill), but prose sections like the Clear Signing 'What it means'/'Why it matters' explanations could be tightened. It is mostly efficient rather than lean, matching the 'mostly efficient but could be tightened' anchor rather than the fully lean anchor at 3.	2 / 3
Actionability	Provides copy-paste-ready TypeScript (SignerEthBuilder with/without originToken, dmk.connect with sessionRefresherOptions, BOLOS dashboard detection), concrete derivation paths, exact URLs, and lookup tables for transports and secure-channel operations. This meets the 'fully executable code/commands; specific examples; copy-paste ready' anchor.	3 / 3
Workflow Clarity	Sequenced processes exist (the 4-step Secure Channel handshake, session lifespan rules), but this is primarily a reference/concepts document rather than a guided workflow, and no validation checkpoints appear. It sits above the 'steps unclear or missing' anchor at 1 but below the explicit validate/fix/retry checklist anchor at 3.	2 / 3
Progressive Disclosure	The body is well-sectioned into nine labeled topics, but it is a single ~230-line inline reference with no references/scripts/assets bundle files, matching the anchor-2 example of '200 lines of API reference that could be in a separate file'. Splitting per-topic detail into reference files would lift it to the anchor-3 structure.	2 / 3
	Total	9 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 states concrete capabilities, enumerates the specific domain concepts covered, and provides explicit natural-language triggers for when to use the skill. It cleanly satisfies all four dimensions with no vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists concrete actions ('Explain the design rationale and domain concepts') and enumerates many specific concrete concepts (Clear Signing, Secure Channel, BOLOS, Device Actions vs Commands, derivation paths, Genuine Check). It clearly exceeds the 'names domain and some actions' anchor at 2.	3 / 3
Completeness	Explicitly answers both what ('Explain the design rationale and domain concepts behind the DMK API, including...') and when ('Use when a developer asks...'), with an explicit 'Use when' clause matching the anchor-3 example. It is not capped at 2 because the trigger guidance is explicit, not merely implied.	3 / 3
Trigger Term Quality	Includes natural phrasings a developer would actually say — 'what is X?', 'why does X work this way?', 'what's the difference between X and Y?' — plus domain terms like 'DMK concept' and 'API design decision', giving good coverage of real trigger language.	3 / 3
Distinctiveness Conflict Risk	Scoped tightly to the Ledger Device Management Kit (DMK) API with concept-specific triggers, making it a clear niche unlikely to fire for unrelated skills. It does not use the generic 'helps with code and documents' language of the anchor-1 example.	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
Path: skills/dmk/dmk-business-logic/SKILL.md
Commit: 2edb393

Reviewed: 12 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.