CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

wallet-cli-usage

Official Ledger wallet-cli - USB-based CLI for Ledger hardware wallet flows (account discover, receive, balances, operations, send, swap quote/execute/status, genuine-check, assets token / token-by-id), the Ledger Key Ring (ring init/encrypt/decrypt/keys/destroy — LKRP-backed encryption of files and text), and Agent Intent (agent-intent enroll/recover/list/show/sync/send — enroll or recover a remote agent's software identity, import the Ledger Sync accounts it was granted and propose EVM payments for human review, no device required, never broadcasts, a separate trust model from `ring`). Use for any wallet-cli command execution and for mapping informal requests to the right command.

81

1.28x
Quality

86%

Does it follow best practices?

Impact

100%

1.28x

2 of 3 eval scenarios. Add 1 more for a full score.

SecuritybySnyk

Medium

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

The body is a dense, executable reference for a large CLI: every command has copy-paste-ready invocations, destructive flows carry explicit validation checkpoints (dry-run, address verification, fingerprint comparison, confirm-before-live-run), and a full error-to-fix table provides recovery loops. Conceptual rationale is correctly offloaded to a single clearly signaled one-level-deep reference; only minor duplication and Agent Intent internals inlined in the main file keep it from full marks.

DimensionReasoningScore

Conciseness

The body is dense and tool-specific — tables (intent map, command/sandbox/TTY matrix, error table) and full command lines with no concept tutorials, and the 'why' is properly offloaded ('for _why_ a command behaves the way it does ... read references/business-logic.md'). Minor duplication keeps it below 5: WALLET_PASS provisioning guidance is stated three times (the ‡ table footnote, the 'Always provision with a password' callout, and the Non-TTY section) and sandbox-bypass rules appear in both the top callout and the commands table. It is clearly above anchor 3 — the repetition is safety-critical reinforcement rather than unnecessary explanation.

4 / 5

Actionability

Every command ships as an executable invocation with concrete flags and values — e.g. 'wallet-cli send bitcoin-native-1 --to bc1q... --amount 0.001 BTC --fee-per-byte 15 --rbf', the WETH wrap/unwrap example with exact selectors and left-padded hex ('--data 0x2e1a7d4d0000...06f05b59d3b20000'), 'WALLET_PASS=$(security find-generic-password -a default -s ledger-wallet-cli -w) wallet-cli ring encrypt …', and an error table mapping exact error strings to fixes. Copy-paste ready across the common cases.

5 / 5

Workflow Clarity

Multi-step flows are explicitly sequenced with validation checkpoints: 'swap quote -> swap execute -> swap status', 'Always run with --dry-run first to validate calldata before signing', the receive-address mismatch escalation ('do not share or use the address ... run genuine-check before retrying'), the Solana two-phase withdraw ('run once to undelegate ... then re-run with --finalize'), and 'confirm with the user before the live run' for the irreversible first vault deposit. The error table plus 'don't retry blindly / check the frontend before re-running' gives explicit feedback loops, so the destructive-operation cap does not apply.

5 / 5

Progressive Disclosure

One clearly signaled, one-level-deep reference exists in the bundle and is linked at the top ('Concepts & rationale: ... read references/business-logic.md') and again with a section pointer ('§ Receive-address verification'), and internal structure is strong (intent map, command matrix, error table). However, the 528-line body inlines deep internals that could be split out — the ~140-line Agent Intent trustchain/recovery/duplicate-protection semantics and the ring password-injection details — so it sits at anchor 4 ('most content is appropriately placed; minor organization gaps') rather than 5's 'content appropriately split'.

4 / 5

Total

18

/

20

Passed

Description

78%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 highly concrete, third-person, and tool-specific, enumerating nearly the full command surface across wallet, Key Ring, and Agent Intent families with an explicit 'Use for...' trigger clause. Its weaknesses are the complete omission of the earn/staking command family and a when-clause phrased around tool execution rather than the natural user intents that should trigger the skill.

Suggestions

Add the earn/staking command family to the description (e.g. 'earn yields/positions/deposit/withdraw — Solana staking and Ethereum DeFi vault yield') — it is a major body section but entirely absent, capping both specificity and completeness.

Phrase the when-clause around concrete user intents rather than tool execution, e.g. 'Use when the user wants to send or swap funds, check balances or history, stake or earn yield, verify their Ledger device, or encrypt files with their device' — this strengthens both trigger-term quality and completeness.

Include the session commands (session view/reset) in the what-clause, or note them via 'mapping informal requests' context, so the description's command inventory matches the body's actual surface.

DimensionReasoningScore

Specificity

The description enumerates many concrete actions across three command families — 'account discover, receive, balances, operations, send, swap quote/execute/status, genuine-check, assets token / token-by-id', 'ring init/encrypt/decrypt/keys/destroy — LKRP-backed encryption of files and text', and 'agent-intent enroll/recover/list/show/sync/send' — which exceeds anchor 4's example coverage. It is not 5 ('comprehensive coverage') because the earn/staking command family and the session commands, both major sections of the body, are entirely absent from the description.

4 / 5

Completeness

Both parts are present: the 'what' is an explicit, thorough command inventory, and the 'when' is explicit ('Use for any wallet-cli command execution and for mapping informal requests to the right command'). It is 4 rather than 5 because the when-clause is tool-centric — it presumes the user is already running wallet-cli rather than naming concrete user intents (sending funds, swapping, staking, checking balances) as anchor 5's trigger-phrase example does — and the earn flows go unmentioned in the what.

4 / 5

Trigger Term Quality

Good natural-keyword coverage: users do say 'send', 'receive', 'balances', 'swap', 'genuine-check', 'Ledger hardware wallet', and 'encryption of files and text', plus an explicit informal-request trigger ('mapping informal requests to the right command'). It falls short of anchor 5 because common natural phrasings are missing — no staking/yield terms ('stake', 'APY', 'earn'), nor synonyms like 'transfer' or 'transaction history' — but keyword presence is well above anchor 3's 'missing common variations'.

4 / 5

Distinctiveness Conflict Risk

'Official Ledger wallet-cli - USB-based CLI for Ledger hardware wallet flows' names a specific niche tool with distinctive trigger vocabulary (wallet-cli, Ledger Key Ring, agent-intent, genuine-check) that no generic skill would share — a clear niche with distinct triggers and minimal conflict risk, matching anchor 5 exactly.

5 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (529 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

LedgerHQ/agent-skills

Path

skills/wallet-cli/wallet-cli-usage/SKILL.md

Reviewed

Table of Contents

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.