web2-recon

Web2 recon pipeline — subdomain enumeration (subfinder, Chaos API, assetfinder), live host discovery (dnsx, httpx), URL crawling (katana, waybackurls, gau), directory fuzzing (ffuf), JS analysis (LinkFinder, SecretFinder), continuous monitoring (new subdomain alerts, JS change detection, GitHub commit watch). Use when starting recon on any web2 target or when asked about asset discovery, subdomain enum, or attack surface mapping.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

77%Weight 40%Scale 1-3

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

Highly actionable and well-sequenced recon pipeline with strong decision checkpoints, but it is a long monolithic document with some duplicated commands and no progressive disclosure into reference files.

Suggestions

Split the self-contained monitor scripts (subdomain alerts, GitHub commit watch) and the GitHub-dorking/target-scoring reference material into files under references/ and link to them one level deep, reducing the SKILL.md body length.

De-duplicate the SecretFinder and subdomain-enumeration blocks that appear in both the main pipeline and the later sections — reference the canonical block instead of restating it.

Tighten the commentary around the scoring tables and "Why this matters" notes so every line earns its place, lifting conciseness toward the lean anchor.

Dimension	Reasoning	Score
Conciseness	Mostly efficient command-driven content that does not lecture on basics, but it repeats itself — SecretFinder commands appear in both "JS ANALYSIS" and "SECRET SCANNING IN JS BUNDLES", and subdomain enumeration is restated in "CONTINUOUS MONITORING" — and the ~430-line body could be tightened.	2 / 3
Actionability	Nearly every section is copy-paste-ready bash (e.g. the numbered Steps 0-6 pipeline, the ffuf invocations, the cron monitor scripts) with concrete flags and output paths — fully executable guidance.	3 / 3
Workflow Clarity	Multi-step processes are explicitly sequenced (Steps 0-6, the time-boxed "30-MINUTE RECON PROTOCOL") with decision checkpoints acting as validation gates — the "5-MINUTE RULE" kill signals, "Pre-Dive Hard Kill Signals", and the "TARGET SCORING — GO / NO-GO" threshold table.	3 / 3
Progressive Disclosure	The body is well sectioned with clear headers, but it is a single ~430-line monolithic file with no bundle/reference files at all, so content that could live one level deep (continuous monitoring scripts, GitHub dorking, target scoring) is all inline rather than split out.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 description: concrete capabilities with tool names, an explicit trigger clause, and a clearly distinct recon niche. Third-person voice is maintained throughout.

Dimension	Reasoning	Score
Specificity	Names six concrete capability areas plus the specific tools for each ("subdomain enumeration (subfinder, Chaos API, assetfinder)", "JS analysis (LinkFinder, SecretFinder)"), listing multiple specific concrete actions rather than vague language.	3 / 3
Completeness	It explicitly answers both halves: the what (the enumerated pipeline stages) and the when (an explicit "Use when starting recon... or when asked about asset discovery, subdomain enum, or attack surface mapping" clause).	3 / 3
Trigger Term Quality	The "Use when..." clause surfaces natural terms a user would actually say — "starting recon on any web2 target", "asset discovery", "subdomain enum", "attack surface mapping" — giving good coverage of common phrasings.	3 / 3
Distinctiveness Conflict Risk	"Web2 recon pipeline" carves a clear niche (asset discovery/attack-surface mapping) distinct from exploitation or web3 skills, with triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: shuvonsec/claude-bug-bounty
Path: skills/web2-recon/SKILL.md
Commit: 2009594

Reviewed: 9 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.