CtrlK
BlogDocsLog inGet started
Tessl Logo

deploy-staging

将当前分支部署到测试环境。当用户要求部署、发布到测试或在 staging 环境测试时使用

67

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 tight, command-driven deployment runbook with clear sequencing and real validation plus rollback guidance. Its main weaknesses are a placeholder health-check URL, a couple of vague instruction bullets, and the absence of an explicit health-gate before reporting success.

Suggestions

Replace the placeholder https://staging.example.com/health with guidance to use the project's actual staging health endpoint, or instruct Claude to read it from config.

Add an explicit gate after the curl health check such as 'Only report success when the health check returns 200; otherwise treat as failure and run rollback'.

Tighten vague bullets like '显示部署进度 / 捕获并显示错误信息' into concrete commands (e.g. tail -f on the deploy log, or capture exit code) to reach copy-paste-ready actionability.

DimensionReasoningScore

Conciseness

The body is lean and command-driven with no concept explanations or padding; every section adds actionable steps Claude would not already know, fitting the score-5 anchor.

5 / 5

Actionability

Concrete executable commands appear throughout (git status, npm test, npm run build:staging, ./scripts/deploy-staging.sh, curl -f), but the placeholder domain staging.example.com and vague bullets like '显示部署进度' leave minor gaps versus copy-paste-ready 5.

4 / 5

Workflow Clarity

A clear sequence runs pre-checks to build, deploy, verify (curl health), and report, with validation (npm test stop-on-fail, health check) and a rollback error-recovery path; it falls short of 5 because there is no explicit 'only proceed when healthy' gate or fix-and-redeploy loop.

4 / 5

Progressive Disclosure

The content is a single well-sectioned file (前置条件检查, 部署流程, 错误处理, 部署后检查) with no nested references, but at ~57 lines it exceeds the under-50-line simple-skill threshold and references ./scripts/*.sh that are not bundle files, leaving minor organization gaps.

4 / 5

Total

17

/

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 clearly communicates a single concrete capability and includes an explicit 'Use when' trigger clause with natural synonyms, making it strongly complete. Specificity is slightly limited by naming only one action, and the generic 'deploy' verb carries minor conflict risk with related deploy skills.

DimensionReasoningScore

Specificity

"将当前分支部署到测试环境" names the domain (staging deployment) and one concrete action (deploy the current branch), but offers only a single action rather than 1-2 distinct ones, fitting the score-3 anchor better than 2.

3 / 5

Completeness

It explicitly states what ("将当前分支部署到测试环境") and when ("当用户要求部署、发布到测试或在 staging 环境测试时使用") with concrete trigger phrases, matching the score-5 anchor.

5 / 5

Trigger Term Quality

"部署" (deploy), "发布到测试" (publish to staging), and "在 staging 环境测试" (test in staging) are natural user phrases with a couple of synonyms, giving good coverage though not exhaustive enough for a 5.

4 / 5

Distinctiveness Conflict Risk

The staging scoping gives it a clear niche with distinct triggers, but the generic term "部署" could overlap a sibling deploy-production skill, leaving minor overlap risk rather than minimal.

4 / 5

Total

16

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
einverne/dotfiles
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.