CtrlK
BlogDocsLog inGet started
Tessl Logo

django-verification

针对 Django 项目的验证循环:包含数据库迁移、代码检查、带覆盖率的测试、安全扫描,以及在发布或 PR 前的部署就绪检查。

67

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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 verification workflow with strong validation checkpoints, but it is verbose and monolithic — large illustrative blocks and reference-grade material live inline instead of in separate files.

Suggestions

Move the full output template, the GitHub Actions workflow, and the per-phase command details into reference files (e.g. OUTPUT_TEMPLATE.md, CI.md, PHASES.md) and link to them from a concise overview in SKILL.md.

Trim the quick-reference table and remove duplicated commands (e.g. 'python manage.py check --deploy' appears in both Phase 2 and Phase 5) to reduce token cost.

Cut illustrative filler such as the sample populated report unless it teaches a non-obvious output format Claude could not infer.

DimensionReasoningScore

Conciseness

The ~470-line body is mostly executable commands but is padded by an ~80-line illustrative output template, a full ~60-line GitHub Actions workflow, and a quick-reference table that repeats already-shown commands; it could be tightened rather than being a lean, every-token-earns-its-place document.

2 / 3

Actionability

Each phase provides concrete, copy-paste-ready bash/python commands (e.g. 'pytest --cov=apps --cov-report=html', 'python manage.py makemigrations --check'), matching the score-3 anchor of fully executable code.

3 / 3

Workflow Clarity

Twelve numbered phases are clearly sequenced with per-phase report sections, an explicit stop-and-fix checkpoint ('如果环境配置错误,请停止并修复'), migration dry-runs and conflict handling for the destructive/batch operations, and a final pre-deployment checklist.

3 / 3

Progressive Disclosure

No bundle files exist and the entire guide — including the large output template, full CI YAML, and per-phase details — is inlined in one ~470-line monolithic SKILL.md; content that should be split into references is inline despite good section organization.

2 / 3

Total

10

/

12

Passed

Description

85%

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 concise, specific description that clearly states what the skill does and when to use it, scoped to a distinct Django niche. The main gap is the absence of a 'Use when...' clause and broader natural-language trigger variations.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — '数据库迁移' (migrations), '代码检查' (linting), '带覆盖率的测试' (tests with coverage), '安全扫描' (security scanning), '部署就绪检查' (deployment readiness checks) — matching the score-3 anchor of multiple specific concrete actions.

3 / 3

Completeness

It answers both 'what' (the verification-loop activities) and 'when' with the explicit trigger '在发布或 PR 前' (before release or PR), which constitutes equivalent explicit trigger guidance so it is not capped at 2.

3 / 3

Trigger Term Quality

It includes relevant natural terms ('Django 项目', 'PR', '发布/部署') but lacks a 'Use when...' clause and common phrasing variations a user might say, fitting the score-2 anchor of some relevant keywords missing common variations.

2 / 3

Distinctiveness Conflict Risk

The Django-specific verification/deployment-readiness niche is clearly bounded with distinct triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
xu-xiang/everything-claude-code-zh
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.