CtrlK
BlogDocsLog inGet started
Tessl Logo

cyberstrike-eino-demo

满配示例技能包:SKILL.md + scripts/、references/、assets/ 等可选目录;验证 Eino skill 与 HTTP 包内路径(仅授权安全测试与教学)。

48

Quality

50%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/cyberstrike-eino-demo/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

The body is well-structured and highly actionable with concrete endpoints, payloads, tools, and real bundle files, but is held back by missing in-workflow validation feedback loops and two dangling references to non-existent files (FORMS.md, REFERENCE.md).

Suggestions

Remove or create the referenced FORMS.md and REFERENCE.md files so every cited path in the body resolves to a real bundle file.

Add an explicit validate→fix→retry feedback loop in the authorization testing workflow (e.g., re-confirm scope and re-verify findings before reporting) to lift workflow clarity.

Trim the demo-scaffolding narration that restates the package's validation purpose in each section; state it once in the overview.

DimensionReasoningScore

Conciseness

The body is mostly lean (tables, bullet lists, concrete payloads) and does not explain concepts Claude already knows, but it carries recurring demo-scaffolding narration ("用于一次性验证", "用于验证非 scripts/ 的子目录是否被同等对待") and explanatory clauses that could be trimmed.

2 / 3

Actionability

It provides concrete, copy-paste-ready items: specific HTTP endpoints ("GET /api/skills", "resource_path=scripts/check-env.sh"), real payloads ("'\"'", "<script>alert(1)</script>"), named tools (Burp, ffuf, nuclei, sqlmap), and real bundle files (scripts/payloads.txt, scripts/report-snippet.json).

3 / 3

Workflow Clarity

The authorization workflow gives a clear 5-step sequence with a soft checkpoint ("高风险操作前二次确认授权边界") and a closing checklist, but it lacks explicit validate→fix→retry feedback loops for risky testing operations, capping the score at 2.

2 / 3

Progressive Disclosure

Structure is good — an overview with a path/purpose table and one-level-deep references to real files (scripts/payloads.txt, references/citations.md, assets/README.txt) — but the opening line references FORMS.md and REFERENCE.md, which do not exist in the bundle, breaking navigation.

2 / 3

Total

9

/

12

Passed

Description

35%

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 names a concrete domain and action but is padded with bundle-structure detail and relies on platform jargon rather than natural user triggers, with no explicit 'Use when' guidance. It is distinguishable but somewhat generic.

Suggestions

Add an explicit 'Use when ...' clause stating the user situations that should trigger this skill (e.g., validating a skill package's file listing and HTTP resource paths).

Replace platform-internal jargon ('Eino skill', 'HTTP 包内路径', '满配示例技能包') with natural keywords a user would actually say.

Trim the directory-structure enumeration from the description; keep it focused on the capability and trigger, not the bundle layout.

DimensionReasoningScore

Specificity

Quotes like "验证 Eino skill 与 HTTP 包内路径" name a domain and a concrete action (validating skill/HTTP paths) plus bundle structure, but the actions are not comprehensive and lean toward describing what the package IS rather than what it does.

2 / 3

Completeness

It states what the package does ("验证 Eino skill 与 HTTP 包内路径") but lacks an explicit 'Use when...' trigger; "仅授权安全测试与教学" is a constraint, not usage guidance, which caps completeness at 2 per the rubric.

2 / 3

Trigger Term Quality

Terms such as "Eino skill", "HTTP 包内路径", and "满配示例技能包" are platform-internal jargon a user would not naturally say to invoke this skill; there are no natural conversational trigger keywords.

1 / 3

Distinctiveness Conflict Risk

The Eino/HTTP-package-validation niche is fairly distinct, but "示例技能包" (example skill package) is generic and could overlap with other packaging/demo skills.

2 / 3

Total

7

/

12

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
Ed1s0nZ/CyberStrikeAI
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.