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.

68

Quality

84%

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

76%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.

An extremely token-efficient, actionable cheat sheet that assumes Claude's competence and delegates taint methodology to another skill. Its weaknesses are structural: it presents parallel techniques without sequenced validation checkpoints, and it uses one monolithic code block rather than navigable sections.

Suggestions

Add explicit validation/error-recovery checkpoints to the batch-oriented workflows — e.g. after trufflehog/gitleaks, state how to triage --only-verified hits (rotate confirmed live keys, ignore false positives) and after git-dumper note verifying recovered credentials before reuse; this would lift workflow_clarity above 3.

Break the single fenced code block into short markdown sections (## .git leak, ## Dangerous-function grep, ## JS deobfuscation, ## Secrets, ## Patch diff, ## Supply chain/CI) so each technique is navigable, improving progressive_disclosure toward 5.

Provide a minimal copy-paste Node.js decoder skeleton for the RC4+base64 string-array pattern (extract array → call decoder with key → print plaintext) to close the actionability gap in the deobfuscation flow.

DimensionReasoningScore

Conciseness

A pure reference card — every line is packed with actionable specifics (commands, function names, key prefixes, payloads) with no padding or over-explanation of concepts Claude already knows, matching the lean-and-efficient anchor.

5 / 5

Actionability

Mostly executable guidance with concrete commands ('git-dumper', 'git log -p --all', 'semgrep --config=auto', 'trufflehog --only-verified', 'npm audit') and concrete indicators (sk-/ghp_/BEGIN RSA, ${{github.event.issue.title}}), but the JS RC4 deobfuscation flow is described procedurally ('Node.js重建解码器批量解码') without copy-paste code, a minor gap that keeps it just below anchor 5.

4 / 5

Workflow Clarity

The content is a set of parallel techniques rather than a sequenced workflow; the deobfuscation sub-flow has numbered steps but no validation or error-recovery, and only '--only-verified' acts as a checkpoint for the otherwise batch-oriented secret-scanning operations, matching the anchor for steps present but validation gaps and implicit checkpoints.

3 / 5

Progressive Disclosure

Under 50 lines with no bundle files needed and one well-signaled one-level reference ('zero-day-discovery' in backticks), but the body is a single monolithic fenced code block with no markdown section headers — a minor organization gap that keeps it below the well-organized-sections anchor 5.

4 / 5

Total

16

/

20

Passed

Description

92%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 strong, specific, bilingual description that clearly states both capabilities and trigger conditions with minimal conflict risk. Its only weakness is trigger-term breadth — the English triggers are natural but lack synonyms and file extensions that would push it to the top anchor.

DimensionReasoningScore

Specificity

Lists many concrete actions — '.git泄露', '危险函数grep', 'JS RC4解混淆', 'semgrep/CodeQL', 'trufflehog', 'patch diff', '供应链/CI' — giving comprehensive coverage of the source-code-hunting domain, matching the anchor for multiple specific concrete actions.

5 / 5

Completeness

It explicitly answers 'what' (the technique list) and 'when' ('Use when hunting source leaks, secrets, JS deobfuscation, or supply-chain issues') with concrete trigger phrases, matching the anchor for clearly and explicitly answering both.

5 / 5

Trigger Term Quality

The English trigger clause covers natural phrases ('source leaks, secrets, JS deobfuscation, supply-chain issues') a user would say, but it stops short of anchor-5 breadth — missing synonyms (e.g. 'git leak', 'hardcoded secrets') and file extensions, so it sits clearly above anchor 3 but below 5.

4 / 5

Distinctiveness Conflict Risk

A highly specialized offensive-security niche (source-leak hunting, secret recovery, JS deobfuscation, supply-chain) with distinct triggers and minimal overlap with general-purpose skills, matching the clear-niche anchor.

5 / 5

Total

19

/

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.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

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.