CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

kunlun-m-general

当你要用 Kunlun-M(静态白盒漏洞扫描)扫描 PHP/JS/Solidity/Chrome Ext 源码,或需要通过命令 scan/generate 快速落地 source/sink(tamper/rule)并回归验证时使用。触发命令:kunlun.py scan / kunlun.py generate rule / kunlun.py generate tamper。

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/kunlun-m-general/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

A strongly action-oriented, token-efficient skill body whose commands are copy-paste executable and whose smoke-test section provides real validation. Its one real defect is navigation: all reference links point to non-portable absolute local paths, and one referenced file (platforms/README.md) is missing from the bundle, undermining otherwise good progressive disclosure.

Suggestions

Replace the absolute Windows links (file:///d:/program/...) with bundle-relative paths, e.g. [concepts.md](references/concepts.md) and [report_template.md](references/report_template.md).

Either add the referenced platforms/README.md to the bundle or remove/inlines the platforms section, since the link currently resolves to nothing.

Add brief expected outcomes to the smoke-test section (e.g. what a successful gen-rule/scan prints) so the validation step has an explicit pass/fail signal and a fix-and-retry loop.

DimensionReasoningScore

Conciseness

The body is script-first and lean — '只包含可直接执行的脚本与最小流程' (only executable scripts and minimal process) — with no explanation of concepts Claude already knows; the concept section is reduced to two decision-point bullets ('规则(rule)≈ sink…', '污点策略(tamper)≈ source + repair'). It is not a 5 because the opening meta-commentary about the skill's own philosophy and the multi-platform/install section are non-essential tokens that could be trimmed or moved to a reference.

4 / 5

Actionability

Every workflow ships copy-paste-ready, fully executable commands with concrete flags: bootstrap ('bootstrap_kunlunm.py --repo-dir ./Kunlun-M'), scan ('scan -t <target> -lan php -b vendor,node_modules -d'), gen-rule/gen-tamper with example values ('--controlled "$_GET,$_POST"'), a complete smoke-test sequence, and CI report generation — covering the common cases exactly as the 5 anchor requires.

5 / 5

Workflow Clarity

The sections form a clear sequence (environment prep → daily actions → minimal concepts → smoke test → report) and validation is present via the '测试命令(冒烟验证)' smoke-test block and per-action regression commands ('scan -r <id>', 'scan -tp <proj>'). It stops short of a 5 because there are no explicit expected outcomes or feedback loops — e.g. what the smoke test output should look like or what to do when a scan or generate step fails.

4 / 5

Progressive Disclosure

The overview/detail split is genuinely good in principle — deep material is pushed to references ('更详细的概念与场景说明见:concepts.md', '报告模板参考:report_template.md', both real one-level-deep files) — but the links are broken in practice: they use absolute Windows paths ('file:///d:/program/Kunlun_M/skills/...') that will not resolve, and the referenced 'platforms/README.md' does not exist in the bundle at all. Per the guideline to score against the actual bundle structure, this lands at 'some structure but references not clearly/signally usable' rather than the 4 anchor's 'references mostly clear'.

3 / 5

Total

16

/

20

Passed

Description

71%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.

A specific, tool-focused description with an explicit use-when clause and excellent distinctiveness. Its main weakness is trigger-term coverage: it relies on the tool name and CLI command names and misses the natural synonyms (code audit / SAST / security audit) a user would more plausibly say when they don't already know the tool.

Suggestions

Add natural-language synonyms for the activity so users who don't know the tool name still trigger it, e.g. '代码审计 / SAST / 安全审计' alongside '静态白盒漏洞扫描'.

Broaden the 'when' clause beyond 'when you want to use Kunlun-M' to user-intent phrasing, e.g. '当用户要求审计 PHP/JS/Solidity 代码漏洞、排查漏报/误报、或想自定义 source/sink 时使用'.

Consider mentioning one or two more capabilities (e.g. environment bootstrap, CI JSON report generation) to round out capability coverage.

DimensionReasoningScore

Specificity

The description lists several concrete actions — '扫描 PHP/JS/Solidity/Chrome Ext 源码' (scan source), '快速落地 source/sink(tamper/rule)' (implement source/sink via rule/tamper), and '回归验证' (regression verification) — with named command surfaces. It falls short of a 5 because it omits other real capabilities from the skill (environment bootstrap, CI report generation), leaving minor coverage gaps, but it is well above the 3 anchor's '1-2 concrete actions'.

4 / 5

Completeness

Both parts are present: 'what' via concrete actions (scan source code, generate rule/tamper for source/sink, regression-verify) and an explicit 'when' clause ('当你要用 Kunlun-M...或需要通过命令...时使用' — 'use when you want to scan with Kunlun-M or need to quickly implement source/sink'). This satisfies the explicit trigger-guidance requirement, so the score-3 cap does not apply, but the 'when' leans on the tool name and CLI commands rather than natural user-intent phrases, so it does not reach the 5 anchor's 'concrete trigger phrases'.

4 / 5

Trigger Term Quality

It includes relevant keywords users would say — the tool name 'Kunlun-M', '静态白盒漏洞扫描' (static white-box vulnerability scanning), language names (PHP/JS/Solidity), and the exact trigger commands 'kunlun.py scan / kunlun.py generate rule / kunlun.py generate tamper'. However, common natural variations and synonyms are missing — most notably '代码审计' (code audit), the phrase Chinese-speaking users most often use for this activity, plus terms like 'SAST' or '安全审计' — matching the 'some relevant keywords but missing common variations' anchor rather than the 4 anchor's 'good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

It names a specific niche tool ('Kunlun-M'), a specific activity (static white-box vulnerability scanning), specific languages, and specific subcommands, giving it a clear niche with minimal overlap risk against any generic scanning or code skill — matching the 5 anchor exactly; the 4 anchor's 'minor overlap risk with closely related skills' does not apply since no closely related skill would share these triggers.

5 / 5

Total

16

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

relative_links

Relative link issues: 3 suspicious

Warning

Total

14

/

16

Passed

Repository

LoRexxar/Kunlun-M

Path

skills/kunlun-m-general/SKILL.md

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.