shodan-reconnaissance

This skill should be used when the user asks to "search for exposed devices on the internet," "perform Shodan reconnaissance," "find vulnerable services using Shodan," "scan IP ranges with Shodan," or "discover IoT devices and open ports." It provides comprehensive guidance for using Shodan's search engine, CLI, and API for penetration testing reconnaissance.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/shodan-reconnaissance/SKILL.md

Quality

Content

46%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.

The body is highly actionable with concrete CLI/API/Python examples and a clear sectioned workflow, but it is verbose and inlines large reference material that should be split into bundled files. Batch and scan operations also lack explicit validation feedback loops.

Suggestions

Move the filter reference, common-query tables, credit system, and troubleshooting tables into bundled reference files under references/ and link to them from SKILL.md to cut the inline token load.

Add explicit validation/feedback-loop checkpoints to the scanning and bulk-download workflow steps (e.g., verify scan status, validate downloaded JSON with `gunzip -t`, retry on failure before proceeding).

Trim restated Shodan CLI basics and illustrative output blocks that Claude can derive, keeping only non-obvious guidance such as credit costs, rate limits, and authorization constraints.

Dimension	Reasoning	Score
Conciseness	The ~500-line body inlines large reference tables and restates Shodan CLI basics with several padded sections, noticeably verbose beyond the minor over-explanation allowed at 3 but not explaining primitives from scratch (not 1).	2 / 5
Actionability	Concrete executable `shodan` CLI commands, curl API calls, and a runnable Python script with error handling provide mostly copy-paste-ready guidance with only minor illustrative-output gaps.	4 / 5
Workflow Clarity	An 8-section Core Workflow gives a sequence, but batch/scan and bulk-download operations lack explicit validate→fix→retry checkpoints, so the destructive/batch feedback-loop cap of 3 applies.	3 / 5
Progressive Disclosure	No bundle files exist, yet filter/query/credit/troubleshooting reference tables that clearly belong in separate files are inlined with no signaled one-level-deep references, matching the anchor for minimal structure.	2 / 5
	Total	11 / 20 Passed

Description

95%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.

The description is strong: it states a clear purpose, lists concrete interfaces, and provides multiple natural trigger phrases that explicitly answer when Claude should use the skill. The only minor weakness is the soft "comprehensive guidance" claim in place of enumerated concrete actions.

Dimension	Reasoning	Score
Specificity	Names Shodan and three concrete interfaces ("search engine, CLI, and API"), giving several specific facets, but "comprehensive guidance" is a soft claim rather than an enumerated action list, so it falls short of a 5.	4 / 5
Completeness	Explicitly answers both what ("comprehensive guidance for using Shodan's search engine, CLI, and API for penetration testing reconnaissance") and when ("should be used when the user asks to...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Five quoted natural phrases ("search for exposed devices on the internet," "perform Shodan reconnaissance," etc.) plus the brand term give comprehensive coverage of terms users would actually say.	5 / 5
Distinctiveness Conflict Risk	Anchored to the distinct Shodan/pentest-reconnaissance niche with brand-specific triggers, minimizing overlap with other skills.	5 / 5
	Total	19 / 20 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
skill_md_line_count	SKILL.md is long (504 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: zebbern/claude-code-guide
Path: skills/shodan-reconnaissance/SKILL.md
Commit: 9d252b3

Reviewed: 2 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.