CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

security-best-practices

Perform language and framework specific security best-practice reviews and suggest improvements. Use when the user explicitly requests security best practices guidance, a security review or report, or secure-by-default coding help. Supports Python, JavaScript/TypeScript, and Go. Do NOT use for general code review, debugging, threat modeling (use security-threat-model), or non-security tasks.

Quality

82%

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

67%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 gives a well-structured, actionable workflow with sound policy on overrides, report format, and cautious fixing, and it points to a clean one-level reference bundle. Its main weakness is redundancy — the decision tree repeats workflow branches and several instructions are stated multiple times — plus a few vague or malformed sentences.

Suggestions

Merge the 'Workflow' and 'Workflow Decision Tree' sections into one structure: the no-matching-guidance branch is currently stated twice in slightly different forms.

Trim duplicated report-delivery instructions ("also report it to the user directly... Also tell the user where the final report was written to") and fix the broken sentence "a full report should be produced describe anyways the project fails to follow security best practices guidance".

Add a brief list of the available reference files (e.g. the 10 `<language>-<framework>-<stack>-security.md` files) so the right file can be picked without listing the directory first.

DimensionReasoningScore

Conciseness

Mostly efficient policy content, but the Workflow and Workflow Decision Tree sections repeat the no-matching-guidance branch, report-delivery instructions are stated twice, and padded asides ("and this is why insecure code lives on for so long") could be trimmed.

3 / 5

Actionability

Concrete executable guidance throughout (filename pattern `<language>-<framework>-<stack>-security.md`, named reference file, report path `security_best_practices_report.md`, severity sections with numeric IDs, one-finding-at-a-time fix policy), though some directions remain vague ("think a little bit about what you know... try to search online") and one report-format sentence is broken.

4 / 5

Workflow Clarity

Clear sequence from language/framework identification, through reference loading and mode selection, to report and fixes, with explicit regression/test validation in the Fixes section; however checkpoints are partially implicit (no verification step after language identification).

4 / 5

Progressive Disclosure

References are one level deep, real, and well-signaled via the documented filename pattern (all named files verified present in references/), with cross-language general advice appropriately inline; minor gap in that no index of available reference files is provided.

4 / 5

Total

15

/

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.

The description is strong: it states concrete capabilities, an explicit 'Use when...' trigger clause, supported languages, and clear negative boundaries against neighboring skills. Minor improvements are possible by naming more capabilities (vulnerability report generation, passive detection) and adding natural synonyms like 'vulnerability'.

DimensionReasoningScore

Specificity

Lists several specific actions ("security best-practice reviews and suggest improvements", "secure-by-default coding help", "security review or report") with minor gaps — report generation and passive detection are not named as actions.

4 / 5

Completeness

Explicitly answers both what ("Perform language and framework specific security best-practice reviews and suggest improvements. Supports Python, JavaScript/TypeScript, and Go.") and when ("Use when the user explicitly requests security best practices guidance, a security review or report, or secure-by-default coding help").

5 / 5

Trigger Term Quality

Good natural-phrase coverage ("security best practices guidance", "a security review or report", "secure-by-default coding help") plus language keywords (Python, JavaScript/TypeScript, Go), but misses common variations like "vulnerability report" or "vulnerability scan".

4 / 5

Distinctiveness Conflict Risk

Clear niche with explicit disambiguation ("Do NOT use for general code review, debugging, threat modeling (use security-threat-model), or non-security tasks") minimizing conflict with adjacent 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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

tech-leads-club/agent-skills

Path

packages/skills-catalog/skills/(security)/security-best-practices/SKILL.md

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.