ctf-osint

Provides open source intelligence techniques for CTF challenges. Use when gathering information from public sources, social media, geolocation, DNS records, username enumeration, reverse image search, Google dorking, Wayback Machine, Tor relays, FEC filings, or identifying unknown data like hashes and coordinates.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

90%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.

A highly actionable, token-efficient OSINT reference with copy-paste commands and a clear pivot/routing section. Its main weaknesses are the absence of verification feedback loops for high-false-positive techniques and that the three referenced detail files are not present in the bundle.

Suggestions

Add the referenced bundle files (social-media.md, geolocation-and-media.md, web-and-dns.md) under references/, or remove the dangling links — currently every 'See <file>.md' pointer leads to a missing file and breaks progressive disclosure.

For high-false-positive techniques (username enumeration, fake service banners, reverse image search), add a short verification step (e.g. 'confirm via a second source before reporting') to give the workflow explicit validation checkpoints.

Add a brief 'Order of operations' note for the multi-step geolocation flow (identify features -> cross-reference maps -> confirm) so the sequencing is explicit rather than implied.

Dimension	Reasoning	Score
Conciseness	Lean one-liner-per-technique body that assumes Claude's competence — e.g. '40 hex chars -> SHA-1 (Tor fingerprint)' and '(id >> 22) + 1288834974657 = Unix ms' — with every token earning its place and no padding about what OSINT is.	5 / 5
Actionability	Provides fully executable, copy-paste-ready commands across the common cases — 'dig -t any target.com', 'exiftool image.jpg', 'shodan host <ip>', 'curl http://ip-api.com/json/...' — plus concrete formulas and exact URL endpoints; not abstract.	5 / 5
Workflow Clarity	Sequencing is implicit (the skill is a reference catalog, not a linear pipeline) and the explicit 'When to Pivot' section gives clear routing to sibling skills, but there are no validation checkpoints for lookups that can return false positives (e.g. username OSINT, fake banners); a 5 would require explicit verification feedback loops.	4 / 5
Progressive Disclosure	Structure is clean and one-level-deep with well-signaled references ([social-media.md], [geolocation-and-media.md], [web-and-dns.md]) and a concise overview, but the referenced detail files do not actually exist in the bundle (no references/, scripts/, or assets/ directories), so navigation breaks against the real bundle structure; not 5 because the pointers are dangling.	4 / 5
	Total	18 / 20 Passed

Description

96%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, third-person description that explicitly states both what the skill does and when to use it, with comprehensive concrete techniques and natural trigger terms. The only minor weakness is a slightly broad 'public sources' framing that leaves a small overlap risk with general research skills.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions and techniques — 'gathering information from public sources, social media, geolocation, DNS records, username enumeration, reverse image search, Google dorking, Wayback Machine, Tor relays, FEC filings' — providing comprehensive coverage of the domain rather than vague verbs.	5 / 5
Completeness	Explicitly answers both 'what' ('Provides open source intelligence techniques for CTF challenges') and 'when' with a concrete 'Use when...' clause enumerating trigger scenarios; matches the score-5 anchor.	5 / 5
Trigger Term Quality	Comprehensive natural keyword coverage including synonyms and specifics users would actually say (social media, reverse image search, Google dorking, Wayback Machine, Tor relays, FEC filings, hashes, coordinates); not a 4 because it spans both common phrasings and specific tool/category terms.	5 / 5
Distinctiveness Conflict Risk	Has a clear CTF-OSINT niche with distinct triggers (Tor relays, FEC filings, MGRS-style OSINT) and minimal conflict risk, but the broad 'gathering information from public sources' surface could lightly overlap with general research skills; not 5 because of that residual breadth.	4 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 29 missing	Warning

	Total	14 / 16 Passed

Repository: ljagiello/ctf-skills
Path: ctf-osint/SKILL.md
Commit: 36c72e5

Reviewed: 4 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.