wizard

生成一个交互式 bash wizard，引导人完成一项手动流程——第三方 setup、一次性 migration、A→B 状态迁移——打开 URL、捕获值、逐步确认，并写入 .env 文件和 GitHub Actions secrets。

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/in-progress/wizard/SKILL.md

Quality

Content

92%

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

The body is concise, highly actionable, and structured as a clear multi-step workflow with explicit done-conditions and verification. The one gap is progressive disclosure: the skill depends on a template.sh that is referenced but not bundled.

Suggestions

Ship template.sh alongside the skill (e.g. in a scripts/ bundle) so the referenced template actually exists, or inline the minimal template the author must copy.

If template.sh stays external, note where to obtain it and confirm its presence before authoring, to keep the reference resolvable.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude's competence (no explanation of bash, .env, or what GitHub secrets are), and every section delivers substantive guidance without padding.	3 / 3
Actionability	Concrete executable guidance throughout — named library helpers (stage, say/step, open_url, ask/ask_secret, write_env, set_secret/set_var, pause/confirm) and exact commands (bash -n, shellcheck, chmod +x) — copy-paste ready for an instruction skill.	3 / 3
Workflow Clarity	A clear four-step sequence each ending in an explicit 'Done when' checkpoint, with a dedicated verify-and-hand-off step (bash -n, shellcheck, static value tracing) providing validation before handoff.	3 / 3
Progressive Disclosure	Sections are well organized and the single reference to [template.sh](template.sh) is one level deep and clearly signaled, but the referenced template.sh is not present in the bundle (references/scripts/assets are absent), so navigation is effectively broken.	2 / 3
	Total	11 / 12 Passed

Description

67%

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 and distinctive, clearly conveying the concrete actions and outputs of the skill. Its main weakness is the absence of an explicit 'Use when...' trigger clause, leaving the invocation condition only implied.

Suggestions

Add an explicit trigger clause, e.g. 'Use when guiding a user through a one-time manual setup, migration, or state transition that requires capturing values into .env or GitHub secrets.'

Surface more natural trigger phrasings users would actually say ('set up third-party service', 'run a one-time migration') alongside 'bash wizard'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — '打开 URL、捕获值、逐步确认，并写入 .env 文件和 GitHub Actions secrets' — naming exact outputs rather than vague verbs.	3 / 3
Completeness	Clearly states what the skill does, but the 'when' is only implied through examples (third-party setup, migration, A→B transition) with no explicit trigger clause, which caps completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	Includes relevant terms ('setup', 'migration', 'GitHub Actions secrets', '.env') but 'bash wizard' is jargon and there is no explicit 'Use when...' phrasing with common natural variations, so coverage is incomplete.	2 / 3
Distinctiveness Conflict Risk	The niche is narrow and distinctive — an interactive bash wizard capturing values into .env and GitHub secrets — with triggers unlikely to collide with other skills.	3 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: vinvcn/mattpocock-skills-zh-CN
Path: skills/in-progress/wizard/SKILL.md
Commit: f2b2464

Reviewed: 1 day 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.