CtrlK
BlogDocsLog inGet started
Tessl Logo

source-code-hunting

源码狩猎:.git泄露,危险函数grep,JS RC4解混淆,semgrep/CodeQL,trufflehog,patch diff,供应链/CI。Use when hunting source leaks, secrets, JS deobfuscation, or supply-chain issues.

70

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

The body is maximally concise and highly actionable, naming real tools and commands, but it is structured as one undifferentiated code block with no sub-sections or navigation and lacks validation checkpoints for its batch scanning workflows.

Suggestions

Break the single code block into labeled sub-sections (e.g., `.git leaks`, `Dangerous-function grep`, `JS deobfuscation`, `Secrets`, `Patch diff`, `Supply chain/CI`) so the content is navigable instead of a monolithic wall.

Add explicit validation/feedback steps for batch secret scanning (e.g., 'verify hits with --only-verified; confirm leaked keys are live before reporting') to lift workflow clarity above 2.

Move the detailed JS RC4 deobfuscation procedure into a separate reference file and link to it from the body, enabling one-level-deep progressive disclosure.

DimensionReasoningScore

Conciseness

The body is an extremely dense reference card with no padding or explanation of concepts Claude already knows; every token earns its place, matching the 'lean and efficient' anchor.

3 / 3

Actionability

It provides concrete executable commands and flags (`semgrep --config=auto`, `git-dumper → git log -p --all`, `trufflehog/gitleaks ... --only-verified`) plus specific grep and secret patterns, well above vague direction or pseudocode.

3 / 3

Workflow Clarity

The JS deobfuscation gives a clear 4-step sequence, but batch operations like scanning git history, docker layers, and tarballs lack explicit validation/feedback checkpoints, capping this dimension at 2.

2 / 3

Progressive Disclosure

The entire body is a single monolithic code-fenced block under one heading, with no sub-sections, navigation, or bundle files; this matches the 'monolithic wall of text; poor organization' anchor.

1 / 3

Total

9

/

12

Passed

Description

100%

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 strong across all dimensions: it concretely lists capabilities, includes a natural explicit 'Use when' trigger, answers both what and when, and occupies a distinct niche. It earns the top score on every dimension.

DimensionReasoningScore

Specificity

Lists multiple concrete techniques and tools (`.git泄露`, `危险函数grep`, `JS RC4解混淆`, `semgrep/CodeQL`, `trufflehog`, `patch diff`, `供应链/CI`) rather than vague language, matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

It explicitly states what the skill does (the technique list) and when to use it via an explicit 'Use when...' trigger, clearly answering both what and when.

3 / 3

Trigger Term Quality

The 'Use when hunting source leaks, secrets, JS deobfuscation, or supply-chain issues' clause provides natural terms a red-team user would actually say, giving good coverage rather than only jargon.

3 / 3

Distinctiveness Conflict Risk

The niche is highly specific (source-code hunting / leaks / secrets / JS deobfuscation / supply-chain), with distinct triggers 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
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.