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）。

Quality

53%

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/cyberstrike-eino-demo/SKILL.md

Quality

Content

60%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 well-structured demo with a clear authorized-testing workflow and good bundle integration, but it is somewhat padded with general security-tooling knowledge and leans on file pointers rather than embedded executable code, and two referenced files (FORMS.md, REFERENCE.md) do not exist.

Suggestions

Remove general-knowledge padding (descriptions of what SQLi/XSS probes do and the generic Burp/ffuf/nuclei toolchain) to tighten conciseness toward 4-5.

Either create the referenced FORMS.md and REFERENCE.md or remove those mentions so all cited references resolve.

Add an explicit validate->fix->retry feedback loop in the testing workflow (e.g., re-confirm scope after each high-risk finding) to push workflow_clarity to 5.

Dimension	Reasoning	Score
Conciseness	Largely efficient with terse tables and short bullets, but includes general-knowledge padding (explaining what SQLi/XSS probes do, a generic toolchain of Burp/ffuf/nuclei) Claude already knows — 'mostly efficient but includes some unnecessary explanation', not a 4 because several asides could be trimmed.	3 / 5
Actionability	Provides some concrete guidance (inline payload strings like "'" and '<script>alert(1)</script>') but the bulk is high-level direction and pointers to scripts rather than executable code blocks; matches 'some concrete guidance but incomplete', not a 4 because no copy-paste-ready workflow code is present.	3 / 5
Workflow Clarity	The authorized-testing workflow is a clear 5-step sequence with an explicit re-confirmation checkpoint ('高风险操作前二次确认授权边界') and a cleanup step plus verification checklist; not a 5 because there is no explicit validate->fix->retry feedback loop for the destructive testing context.	4 / 5
Progressive Disclosure	Clear ## sections, a path→purpose table, and one-level-deep pointers to real bundle files (scripts/payloads.txt, references/citations.md, assets/README.txt all exist); not a 5 because FORMS.md and REFERENCE.md are referenced but missing, leaving two dangling navigation links.	4 / 5
	Total	14 / 20 Passed

Description

46%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 identifies a specific niche (Eino skill + HTTP path validation) but is terse and lacks a 'Use when...' trigger clause, capping completeness. Trigger terms lean technical/internal rather than natural user phrasing.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should load this skill (e.g., verifying Eino skill packaging or HTTP in-package resource paths).

Surface a few natural trigger phrases a user would actually say (e.g., 'skill bundle', 'package path validation', 'Eino retriever test') instead of only framework-internal jargon.

List one or two more concrete actions (e.g., 'lists packaged skills, reads bundle resources via resource_path, maps section headers to short ids') to lift specificity toward 4-5.

Dimension	Reasoning	Score
Specificity	Names the domain (Eino skill / HTTP in-package path validation) and one concrete action ('验证 Eino skill 与 HTTP 包内路径') plus bundle components, but does not enumerate multiple specific actions — closest to 'names domain and 1-2 concrete actions'; not a 4 because the action list is thin.	3 / 5
Completeness	It states what the skill does (validates Eino skill + HTTP in-package paths) but provides no 'Use when...' trigger clause — only a parenthetical scope note ('仅授权安全测试与教学'); per the rubric a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Keywords are project-internal jargon ('Eino skill', 'HTTP 包内路径') rather than natural phrases a user would spontaneously say to invoke this skill; matches 'one or two generic keywords; missing the natural phrases users say', and not a 3 because common user-facing synonyms are absent.	2 / 5
Distinctiveness Conflict Risk	Tied to a specific framework (Eino) and a narrow demo purpose, giving a clear niche with minimal conflict risk; not a 5 only because the description is too sparse to fully lock in distinct triggers.	4 / 5
	Total	12 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Ed1s0nZ/CyberStrikeAI
Path: skills/cyberstrike-eino-demo/SKILL.md
Commit: 893f134

Reviewed: 2 days 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.