CtrlK
BlogDocsLog inGet started
Tessl Logo

security-review

当涉及添加身份验证(Authentication)、处理用户输入、操作机密(Secrets)、创建 API 终端节点或实现支付/敏感功能时,请使用此技能。提供全面的安全检查清单和模式。

68

Quality

82%

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

65%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.

The body is highly actionable with executable code and validation checkboxes for ten security domains, but it is a large monolithic file with no progressive disclosure and no sequenced feedback-loop workflow. Splitting the per-domain checklists into reference files and removing the redundant pre-deploy checklist would raise both conciseness and progressive disclosure.

Suggestions

Split the per-domain sections (secrets, input validation, SQL, auth, XSS, etc.) into separate reference files under references/ and keep SKILL.md as a concise overview that links one level deep to them, improving progressive disclosure.

Remove or compress the "部署前安全检查清单" section, which largely duplicates the per-section "验证步骤" checkboxes, to reduce token redundancy.

For the most fragile operations (e.g., RLS policy changes, secret rotation), add an explicit validate→fix→retry feedback loop so the workflow carries explicit checkpoints rather than only flat checkboxes.

DimensionReasoningScore

Conciseness

The body is mostly efficient — it skips concept explanations Claude already knows and goes straight to patterns — but the ~490-line single file includes redundancy, notably the "部署前安全检查清单" repeating the per-section "验证步骤" checklists, and could be tightened.

2 / 3

Actionability

Provides copy-paste-ready, executable TypeScript/SQL/bash examples throughout (zod schemas, parameterized queries, httpOnly cookie headers, DOMPurify, RLS policies, rate limiters) with concrete specifics.

3 / 3

Workflow Clarity

Content is organized into sections with per-section validation checkboxes and a pre-deploy checklist, but there is no sequenced multi-step process with explicit validate→fix→retry feedback loops for risky operations.

2 / 3

Progressive Disclosure

Well-organized into numbered sections, but it is a monolithic ~490-line single file with no bundle files and no references to separate documents; content that could be split (e.g., per-domain reference sheets) is all inline.

2 / 3

Total

9

/

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.

The description is well-crafted: it states a concrete capability and pairs it with explicit, natural trigger conditions covering the security-review domain. It clearly answers both what the skill does and when to use it.

DimensionReasoningScore

Specificity

Names concrete deliverables ("提供全面的安全检查清单和模式") and multiple specific triggers — auth, user input, secrets, API endpoints, payments — rather than vague language.

3 / 3

Completeness

Explicitly answers both 'what' (provides a security checklist and patterns) and 'when' ("当涉及...请使用此技能" = Use when...), matching the anchor for a full what-and-when description.

3 / 3

Trigger Term Quality

Uses natural terms users would actually say ("身份验证", "处理用户输入", "机密", "API 终端节点", "支付"), covering the common variations for the security-review domain.

3 / 3

Distinctiveness Conflict Risk

Clear niche (security review) with distinct triggers around auth/secrets/payments/API endpoints, making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

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.