CtrlK
BlogDocsLog inGet started
Tessl Logo

crypto-audit

Audit cryptography implementation — algorithm choice, key sizes, KDF parameters, IV/nonce handling, signature verification, randomness, TLS configuration, and key rotation. Deeper than owasp-audit A02. Use when the user mentions 'crypto review,' 'cryptography audit,' 'encryption review,' 'KDF,' 'PBKDF2,' 'Argon2,' 'bcrypt cost,' 'IV reuse,' 'nonce reuse,' 'AES mode,' 'AES-GCM,' 'AES-ECB,' 'signature verification,' 'TLS configuration,' 'cipher suites,' 'key rotation,' 'libsodium,' 'BoringSSL,' or 'is this crypto right.'

73

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 strong, expert-level audit checklist: highly actionable with specific parameters, grep patterns, and validation steps, well-structured and mostly concise. Main weaknesses are minor editorial padding and a monolithic layout that could benefit from splitting detailed reference material into bundled files.

Suggestions

Trim rhetorical asides (e.g. '< 50 people on Earth ... they don't work at your company', 'the book to read') to tighten the 'Don't roll your own' and References sections.

Move the 'Specific framework patterns' and 'Key lifecycle' detail into separate reference files (e.g. references/frameworks.md, references/key-lifecycle.md) referenced one level deep from SKILL.md to improve progressive disclosure.

Add an explicit ordered audit workflow at the top (e.g. scope → run checklist greps → record findings → verify fixes → emit report) with checkpoints, so the core phase is sequenced rather than only the fix-verification phase.

DimensionReasoningScore

Conciseness

Dense and mostly lean — exact iteration counts, nonce bit-sizes, and grep patterns assume Claude's competence — but a few editorial asides ('< 50 people on Earth who can design new crypto safely, and they don't work at your company', 'the book to read') could be trimmed without losing audit value.

4 / 5

Actionability

Fully executable guidance throughout: concrete grep targets ('AES.*ECB', 'jwt.decode', 'Math.random'), exact parameters (PBKDF2 ≥ 600,000 iterations, 96-bit nonces, bcrypt cost ≥ 12), and copy-ready commands (testssl.sh, sslyze, curl --tlsv1.3) plus a complete output-format template.

5 / 5

Workflow Clarity

Clear implied sequence (checklist dimensions → verify fixes → output format) with explicit validation in 'Verify Fixes at Runtime' (round-trip test, testssl verification, IAM encrypt+decrypt check), but the core audit phase is a dimension scan rather than an explicitly ordered workflow with checkpoints.

4 / 5

Progressive Disclosure

Well-organized with clear section headers and logical grouping, but the ~150-line body is monolithic with no bundle files; detailed sections like 'Specific framework patterns' and 'Key lifecycle' are inlined rather than split into one-level-deep reference files.

4 / 5

Total

17

/

20

Passed

Description

100%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 exemplary: third-person voice, comprehensive concrete actions, an exhaustive list of natural trigger terms, and explicit what/when guidance with clear distinction from related skills. No meaningful gaps.

DimensionReasoningScore

Specificity

Lists multiple concrete audit actions — 'algorithm choice, key sizes, KDF parameters, IV/nonce handling, signature verification, randomness, TLS configuration, and key rotation' — giving comprehensive coverage of the domain.

5 / 5

Completeness

Explicitly answers both 'what' (audit cryptography implementation across the listed dimensions) and 'when' ('Use when the user mentions ...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural-language triggers including synonyms and library names users actually say: 'crypto review,' 'cryptography audit,' 'encryption review,' 'KDF,' 'PBKDF2,' 'Argon2,' 'bcrypt cost,' 'IV reuse,' 'nonce reuse,' 'AES-GCM,' 'AES-ECB,' 'cipher suites,' 'key rotation,' 'libsodium,' 'BoringSSL,' 'is this crypto right.'

5 / 5

Distinctiveness Conflict Risk

Clear crypto-audit niche with distinct triggers, and it explicitly carves out scope from sibling skills ('Deeper than owasp-audit A02'), minimizing overlap risk.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
briiirussell/cybersecurity-skills
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.