dmk-intent-vocabulary

Map developer intent and natural language to the correct Ledger Device Management Kit (DMK) components, operations, and API methods. Use when a developer's request is phrased informally, incompletely, or in terms of outcomes rather than API methods, when the intent is ambiguous and needs mapping to a specific DMK component or operation, or when a developer asks 'how do I...', 'what's the difference between...', or describes a symptom rather than an API.

1.15x

Quality

—

Does it follow best practices?

Impact

98%

1.15x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

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 lean, well-organized intent-to-API mapping with concrete method names and strong security gating. Its main weakness is actionability for non-ETH chains, where 'signer equivalent' placeholders omit the actual method names.

Suggestions

Replace the 'BTC: Bitcoin signer equivalent' and 'Solana: Solana signer equivalent' placeholders with the actual signer class and method names (and package) for each chain, mirroring the ETH entries.

For the address and transaction sections, add the exact signer package import or a one-line code snippet so the mapping is copy-paste ready across all chains, not just ETH.

Clarify how a developer should resolve the chain when the request names a coin but no signer package exists (e.g., fall back to raw Command, or stop and ask), so ambiguous-chain cases have an explicit path.

Dimension	Reasoning	Score
Conciseness	Lean, tightly structured sections (Phrasings / Maps to / Note) with no padding explaining what a Ledger is or basic programming concepts; every note earns its place, mostly via security-relevant guidance. Not 2 because there is no unnecessary explanation to trim.	3 / 3
Actionability	Names exact methods with return types and parameter shapes (e.g. 'signerEth.signTransaction(derivationPath, transaction, options)', 'GenuineCheckDeviceAction'), but placeholders like 'BTC: Bitcoin signer equivalent' and 'Solana: Solana signer equivalent' leave those chains' guidance incomplete. Not 3 because key details for non-ETH chains are missing; not 1 because most entries are concrete and specific.	2 / 3
Workflow Clarity	As a lookup/mapping skill it is single-purpose and unambiguous, with explicit gating/checkpoint guidance ('If a derivation path is missing... stop and ask', 'Do not use raw APDU for signing', 'Never configure Speculos... in production'). Per the simple-skills note, this clears the bar. Not 2 because validation/stop-and-ask checkpoints are explicit.	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent), so the body is self-contained and well-organized into clear sections; the only cross-references are one-level-deep, clearly signaled pointers to the separate ledger-dmk-implementation skill ('-> For ... load'). Not 2 because organization is clean and references are shallow and well-signaled.	3 / 3
	Total	11 / 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.

The description is specific, third-person, and explicitly answers both what the skill does and when to use it, with natural trigger phrasings a developer would say. It is clearly distinguishable and unlikely to conflict with unrelated skills.

Dimension	Reasoning	Score
Specificity	Names the concrete action ('Map developer intent and natural language to the correct Ledger Device Management Kit (DMK) components, operations, and API methods') with the domain and multiple specific mapping targets, matching the 'lists multiple specific concrete actions' anchor. Not 2 because the actions are concrete and comprehensive, not partial.	3 / 3
Completeness	Clearly answers both what (map intent to DMK components/operations/API methods) and when, with an explicit 'Use when...' clause enumerating multiple trigger conditions. Matches the score-3 anchor exactly. Not 2 because the when is explicit, not implied.	3 / 3
Trigger Term Quality	Includes natural phrasings a developer would actually say ('how do I...', "what's the difference between...", 'describes a symptom rather than an API', 'phrased informally, incompletely'), giving good coverage of real-world terms. Not 2 because common variations are well represented.	3 / 3
Distinctiveness Conflict Risk	Niche is clearly scoped to Ledger DMK intent-mapping with distinct, domain-specific triggers unlikely to fire for unrelated skills. Not 2 because the triggers are tightly tied to a unique domain rather than broadly overlapping.	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.