init-onecli

Install and initialize OneCLI Agent Vault. Migrates existing .env credentials to the vault. Use after /update-nanoclaw brings in OneCLI as a breaking change, or for first-time OneCLI setup.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

77%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 thorough, highly actionable multi-phase migration workflow with strong validation and error-recovery structure. Its main weakness is conciseness and progressive disclosure: it is a long monolithic file with some tighten-able prose and no external reference split.

Suggestions

Move the git-over-HTTPS and Troubleshooting sections into separate reference files (e.g. references/git-over-https.md, references/troubleshooting.md) and link to them, so the main SKILL.md stays a lean overview.

Trim redundant prose — the opening paragraph rephrases the frontmatter description, and the standalone "Principle" line could fold into the relevant phases or be dropped.

Convert the verbose Troubleshooting paragraphs into a compact cause→fix table to cut tokens while keeping the same actionable content.

Dimension	Reasoning	Score
Conciseness	Largely command- and table-dense and assumes competence, but several prose passages (the opening paragraph restating the description, the "Principle" line, and verbose troubleshooting paragraphs) could be tightened without losing clarity.	2 / 3
Actionability	Provides copy-paste-ready, fully executable commands with specific flags, plus mapping tables (env variable → secret type → host pattern) that leave no ambiguity about what to run.	3 / 3
Workflow Clarity	A clearly sequenced five-phase workflow with explicit validation checkpoints (onecli version, secrets list, /health polling, build-fix-restart, log grep) and error-recovery feedback loops; destructive .env edits are guarded with "remove only credential lines, keep others".	3 / 3
Progressive Disclosure	No bundle files exist, so everything is inline in one ~308-line document; well-sectioned, but self-contained chunks like git-over-HTTPS and Troubleshooting could be split into reference files to shorten the main body.	2 / 3
	Total	10 / 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 tight, third-person description that names concrete actions and gives an explicit use-when clause tied to a specific breaking-change trigger. It clearly answers both what the skill does and when to invoke it without padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Install and initialize OneCLI Agent Vault" and "Migrates existing .env credentials to the vault" — rather than vague language.	3 / 3
Completeness	Explicitly answers what (install, initialize, migrate credentials) and when ("Use after /update-nanoclaw brings in OneCLI as a breaking change, or for first-time OneCLI setup").	3 / 3
Trigger Term Quality	Covers natural domain terms a user would say — "OneCLI", "Agent Vault", ".env credentials", "/update-nanoclaw", "OneCLI setup" — tied to real triggering situations.	3 / 3
Distinctiveness Conflict Risk	The OneCLI Agent Vault niche plus the /update-nanoclaw trigger make it clearly distinguishable and unlikely to fire for unrelated skills.	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: nanocoai/nanoclaw
Path: .claude/skills/init-onecli/SKILL.md
Commit: 641963c

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.