CtrlK
BlogDocsLog inGet started
Tessl Logo

securitycards

Apply version-specific secure coding guidance to AI-generated or human-written code that uses supported open source libraries. Use when starting a software project, implementing a security-sensitive feature, or reviewing code for secure defaults, authentication, authorization, input handling, injection, cryptography, file handling, network boundaries, secrets, sessions, and other library-specific security concerns.

73

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 tight, highly actionable workflow skill with strong sequencing, explicit fail-closed validation, and clean separation between the in-file overview and live-fetched detail. Only minor conciseness trims are available.

Suggestions

Tighten the Fetching section's explanation of why a summarizing fetch tool fails into a single directive sentence to reclaim a few tokens.

Consider moving the fixed 24-item category enumeration into a short reference note if it ever grows, so the main flow stays scannable.

DimensionReasoningScore

Conciseness

Lean and assumes Claude's competence with no padding about basic concepts, but a few explanatory sentences (e.g., why a summarizing fetch tool strips code/URLs) could be tightened without losing the guidance.

4 / 5

Actionability

Fully executable guidance: concrete `curl -fsS <url>`, exact URL-construction rules from catalog lines, fixed category set, and a worked flask example showing how to build a category URL.

5 / 5

Workflow Clarity

Clear sequence (Fetch → Resolve version → Find cards → Fail closed → Choose what to read → Apply) with explicit validation checkpoints ("Check the URL you landed on", "Re-run the tests") and a "Before finishing" checklist.

5 / 5

Progressive Disclosure

Well-organized overview whose one bundle reference (`references/catalog.json`, verified present) is clearly signaled and scoped as a possibly-stale snapshot; the detailed rules live one level deep in live-fetched cards rather than inlined.

5 / 5

Total

19

/

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 precise, well-scoped description that clearly states both capability and triggering conditions with rich natural security vocabulary. It could nudge specificity to 5 by naming a few more distinct concrete actions beyond "apply guidance".

DimensionReasoningScore

Specificity

Names the domain and a concrete action ("Apply version-specific secure coding guidance to AI-generated or human-written code that uses supported open source libraries") with broad security-category coverage, but rests on a single primary verb rather than multiple distinct concrete actions.

4 / 5

Completeness

Explicitly answers both what ("Apply version-specific secure coding guidance…") and when ("Use when starting a software project, implementing a security-sensitive feature, or reviewing code for…") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural keyword coverage ("authentication", "authorization", "injection", "cryptography", "secrets", "sessions", "reviewing code") that users would plausibly say, though it enumerates distinct categories rather than synonyms or file extensions.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (version-pinned secure-coding rules for specific open source libraries) with distinctive triggers and minimal overlap with general code-review skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Reware-Labs/securitycards
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.