ctf-crypto

Provides cryptography attack techniques for CTF challenges. Use when attacking encryption, hashing, signatures, ZKP, PRNG, or mathematical crypto problems involving RSA, AES, ECC, lattices, LWE, CVP, number theory, Coppersmith, Pollard, Wiener, padding oracle, GCM, key derivation, or stream/block cipher weaknesses.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./ctf-crypto/SKILL.md

Quality

Content

65%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 well-organized, terse crypto-attack catalog with executable quick-start commands and clear pivot routing, undermined by absent bundle files, mismatched inline links, and the lack of explicit validation checkpoints in the solving workflow. Fixing the broken references and adding verify steps would lift the content score meaningfully.

Suggestions

Correct the nine inline links where the visible text says modern-ciphers-2.md but the href targets modern-ciphers-3.md (e.g., lines 115, 116, 133, 136-139, 259, 311) so link text and href agree and navigation is reliable.

Ship the referenced detail files (classic-ciphers.md, modern-ciphers.md, modern-ciphers-2.md, modern-ciphers-3.md, rsa-attacks.md, etc.) alongside SKILL.md, or remove dangling references, so the progressive-disclosure index resolves to real content.

Add explicit validation checkpoints to the Quick Start triage workflow (e.g., confirm factorization recovered two primes before computing phi; verify decrypted output matches the expected flag format) to raise workflow clarity above 3.

De-duplicate entries that recur across sections (padding oracle, AES-CBC, Manger oracle, affine-over-composite-modulus) into a single canonical location to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is dense one-liners that assume Claude's competence (e.g., "Wiener's attack: Small d", "Fermat factorization: p and q close together") with no padding explaining what RSA or AES is, but the ~39KB body carries redundancy across sections (padding oracle, AES-CBC, Manger oracle, and "affine over composite modulus" each appear in multiple places), keeping it just below the lean 5 anchor.	4 / 5
Actionability	Provides copy-paste-ready Quick Start commands (python3 -c, openssl, sage -c), concrete formulas (phi = (p-1)*(q-1); d = inverse(e, phi); m = pow(c, d, n)), and named tools (RsaCtfTool, hashpumpy, PadBuster, nonce-disrespect); most technique bullets are concrete descriptions that defer executable code to the bundle files, a minor gap versus the fully copy-paste 5 anchor.	4 / 5
Workflow Clarity	A rough triage sequence exists in Quick Start Commands (identify cipher, RSA quick check, factor, XOR, hash ID, SageMath) and the "When to Pivot" section acts as routing guidance, but there are no explicit validation checkpoints or feedback loops (e.g., verify factorization succeeded, confirm decrypted plaintext is valid flag format), matching the anchor where sequence is present but checkpoints are missing or implicit.	3 / 5
Progressive Disclosure	The design is strong — a dedicated "Additional Resources" index with per-file descriptions plus inline "See [file.md](file.md#anchor)" pointers is textbook one-level-deep disclosure — but the referenced bundle files (classic-ciphers.md, modern-ciphers.md, etc.) are absent from the bundle, and at least nine inline links have mismatched link-text vs href (text says modern-ciphers-2.md while the href points to modern-ciphers-3.md#… on lines 115, 116, 133, 136-139, 259, 311), so references are present but not reliably navigable.	3 / 5
	Total	14 / 20 Passed

Description

87%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 description that clearly states what the skill does and when to use it, with comprehensive crypto-domain trigger terms and a distinct niche. The only weakness is a singular action verb ("provides techniques") where multiple discrete capability verbs would push specificity and trigger phrasing to the top anchor.

Dimension	Reasoning	Score
Specificity	Names the domain and a concrete action ("Provides cryptography attack techniques for CTF challenges") and enumerates many specific sub-areas (RSA, AES, ECC, lattices, LWE, Coppersmith, Pollard, Wiener, padding oracle, GCM), but the action verb is singular ("provides techniques") rather than multiple discrete verbs, leaving it just short of the comprehensive multi-action 5 anchor.	4 / 5
Completeness	Explicitly answers both "what" ("Provides cryptography attack techniques for CTF challenges") and "when" ("Use when attacking encryption, hashing, signatures, ZKP, PRNG, or mathematical crypto problems involving…") with concrete trigger phrases, closely matching the 5 anchor example in both structure and content.	5 / 5
Trigger Term Quality	Excellent keyword coverage spanning broad categories (encryption, hashing, signatures, ZKP, PRNG) and specific named attacks/tools (Coppersmith, Pollard, Wiener, padding oracle, GCM, key derivation); held at 4 rather than 5 because the dense keyword list leans toward enumeration over naturally measured phrasing and lacks the synonym/extension breadth of the 5 anchor.	4 / 5
Distinctiveness Conflict Risk	Targets a clear, narrow crypto-CTF niche with highly specific triggers (Coppersmith, lattices, LWE, CVP, padding oracle) and minimal overlap with sibling CTF skills, reinforced by the body's "When to Pivot" routing away from reverse/forensics/pwn/web.	5 / 5
	Total	18 / 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: 103 missing	Warning

	Total	14 / 16 Passed

Repository: ljagiello/ctf-skills
Path: ctf-crypto/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.