boltz-cli-setup

Boltz CLI setup and auth. Use when installing, updating, verifying, or authenticating `boltz-api`, or fixing missing CLI, PATH, sandbox, browser login, or auth errors.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

85%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.

A highly actionable, well-sequenced skill body: all guidance is executable commands, workflows include explicit check/fix/retry loops, and sandbox detail is properly deferred to a single clearly signaled reference file. The main weakness is moderate verbosity from the duplicated installer-confirmation policy, which is argued twice in the body and again in the reference.

Suggestions

State the installer-confirmation requirement once (in Verify Installation) and drop the repeated phrasing in the sandbox paragraph ("The host approval must cover the exact command; do not treat an ordinary setup request as authorization..."), keeping the escalation detail only in references/sandbox.md.

Trim the sandbox paragraph in the body to a one-line summary plus the reference pointer; it currently re-explains what the sandbox can block, which references/sandbox.md already covers.

Condense the two consecutive "Before downloading..." and "A general request to use or install Boltz is not confirmation" paragraphs into a single tighter confirmation instruction.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, command-first prose, but the installer-confirmation requirement is stated twice ("show the exact platform command and obtain the user's explicit confirmation" in Verify Installation, then "The host approval must cover the exact command; do not treat an ordinary setup request as authorization" in the sandbox paragraph), and the sandbox policy prose overlaps references/sandbox.md. Not 4-5 because this duplication could be trimmed by deferring policy detail entirely to the reference.	3 / 5
Actionability	Every step is copy-paste executable: `boltz-api --version`, platform-specific curl/PowerShell installers, `boltz-api auth status`, `boltz-api auth login --device-code`, and a shell test for `BOLTZ_API_KEY`. Specific commands cover the common install, auth, and version cases.	5 / 5
Workflow Clarity	Clear sequences with explicit validation checkpoints and feedback loops: verify version → install → re-check PATH if still missing; `auth status` → device-code login if unauthenticated → retry. The installer step is gated on explicit user confirmation, a well-defined checkpoint.	5 / 5
Progressive Disclosure	The body is a lean three-section overview with one well-signaled, condition-scoped reference ("Read references/sandbox.md when an agent sandbox blocks the installer, browser auto-open, OAuth callback, credential storage, temp files, or global install path") that exists in the bundle and is exactly one level deep. The minor body/reference overlap on sandbox policy is the only blemish.	5 / 5
	Total	18 / 20 Passed

Description

87%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.

A strong description: it names the domain and concrete actions in third person, includes an explicit "Use when" clause with natural trigger terms, and is tightly scoped to `boltz-api` so conflict risk is minimal. Keyword coverage could add common synonyms like "log in" or "command not found" to reach the top anchor.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "installing, updating, verifying, or authenticating `boltz-api`, or fixing missing CLI, PATH, sandbox, browser login, or auth errors" — with minor gaps (API key configuration and version-check policy are not mentioned). Not 5 because coverage is not fully comprehensive; not 3 because it goes well beyond 1-2 actions.	4 / 5
Completeness	"Boltz CLI setup and auth" clearly answers what, and "Use when installing, updating, verifying, or authenticating `boltz-api`, or fixing missing CLI, PATH, sandbox, browser login, or auth errors" explicitly answers when with concrete trigger phrases. The when-clause is fully explicit, exceeding the level-4 anchor's "could be more specific".	5 / 5
Trigger Term Quality	Natural user phrasings like "installing", "PATH", "sandbox", "browser login", and "auth errors" give good keyword coverage. Not 5 because common synonyms such as "sign in"/"log in" or "command not found" are missing.	4 / 5
Distinctiveness Conflict Risk	The description is scoped to the named CLI `boltz-api` with its own distinct trigger set (CLI/PATH/auth/sandbox errors), giving a clear niche with minimal conflict risk against other skills.	5 / 5
	Total	18 / 20 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: openai/plugins
Path: plugins/boltz-api-cli/skills/boltz-cli-setup/SKILL.md
Commit: 5fd93af

Reviewed: 2 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.