CtrlK
BlogDocsLog inGet started
Tessl Logo

attack-surface-recon

侦察/攻击面测绘:被动whois/amass/crt.sh/FOFA/Shodan,主动subfinder/httpx/naabu/katana/nuclei,DNS地域/CDN/Nginx catch-all/宝塔/UniApp指纹。开局第一动作,认知写入项目黑板。Use when starting recon, asset mapping, fingerprinting, or CDN/DNS bypass discovery.

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.

Highly actionable and token-efficient command reference for recon, but presented as a single monolithic code block with broken/missing reference files and no explicit validation checkpoints for its batch scanning operations.

Suggestions

Break the monolithic code block into structured sections (## 被动侦察 / ## 主动流水线 / ## 绕过技巧) and move the long BT-panel, UniApp-reversing, and nginx-404 details into the referenced files, then actually create references/nginx-404-differential-fingerprinting.md and references/uniapp-dcloud-apk-reversing.md.

Add explicit validation/feedback checkpoints between batch stages (e.g. 'after dnsx: confirm alive_subs.txt is non-empty before scanning; if empty, fall back to passive sources').

Replace '{domain}/{target}' placeholders with a short parameter legend or a single consistent token so the pipeline is unambiguous to execute.

DimensionReasoningScore

Conciseness

Dense, command-packed block assuming Claude knows the tools; the 🚨 warnings capture non-obvious domain gotchas (CDN 502 vs 404 semantics, BT panel cookie fingerprint) that earn their tokens rather than padding.

5 / 5

Actionability

Copy-paste-ready terminal commands with concrete flags and a {domain}/{target} placeholder convention; covers passive, active enumeration, fuzzing, and nuclei scanning directly.

5 / 5

Workflow Clarity

A clear pipeline sequence exists (passive → subfinder/amass → dnsx → httpx → naabu/nmap → katana/gau → nuclei) but batch/scanning operations lack explicit validation checkpoints or fix-retry feedback loops, capping clarity per the batch-operation rule.

3 / 5

Progressive Disclosure

Everything is inlined in one monolithic code block with no section headers; the two '详见 references/*.md' pointers are signaled but the referenced files do not exist in the bundle, so detail that belongs in separate files is buried.

2 / 5

Total

15

/

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 highly specific, well-triggered description that names concrete tools and techniques and pairs a clear 'what' with an explicit 'Use when' clause. Trigger term coverage is strong but slightly technical, leaving a few natural synonyms out.

DimensionReasoningScore

Specificity

Names concrete tools (whois/amass/crt.sh/FOFA/Shodan, subfinder/httpx/naabu/katana/nuclei) and specific techniques (DNS地域/CDN/Nginx catch-all/宝塔/UniApp指纹) — comprehensive concrete actions, not vague.

5 / 5

Completeness

Explicitly states what (passive+active recon pipelines and fingerprinting) and when ('Use when starting recon, asset mapping, fingerprinting, or CDN/DNS bypass discovery') with concrete triggers.

5 / 5

Trigger Term Quality

Natural trigger phrases present ('recon, asset mapping, fingerprinting, CDN/DNS bypass discovery') but coverage leans technical and misses some common synonyms/extensions a user might say.

4 / 5

Distinctiveness Conflict Risk

Narrow niche (attack-surface recon with named tools and specific bypass techniques like BT Panel / UniApp reversing) makes it clearly distinguishable with minimal overlap risk.

5 / 5

Total

19

/

20

Passed

Validation

81%

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

Validation13 / 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

referenced_paths_exist

Referenced path issues: 4 missing, 1 deeper-than-1-level

Warning

Total

13

/

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.