CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

security

Check code changes for security vulnerabilities

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/pragma/skills/security/SKILL.md
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.

The body is a well-structured, highly actionable security validator with executable diff commands and an exact JSON reporting schema. Its main weaknesses are a missing batch-completion checkpoint in the workflow and minor conciseness trim available in the repeated 'Why HARD' rationale lines.

Suggestions

Add an explicit validation checkpoint after batch processing, e.g. confirm all batches were processed and reconcile the combined file list before reporting, to lift workflow_clarity toward 5.

Consolidate the repeated 'Why HARD:' rationale lines into a single short justification per tier to tighten conciseness.

Consider moving the full JSON schema or the violation-rule catalog into a one-level-deep reference file so SKILL.md reads as an overview, improving progressive_disclosure.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, with terse 'Why HARD' justifications that earn their place; only minor over-explanation (e.g. repeated 'Why HARD' lines) could be trimmed, matching the score-4 anchor.

4 / 5

Actionability

It provides copy-paste-ready bash commands for gathering diffs, a precise JSON output schema, and concrete violation categories with examples, fully covering the common cases as the score-5 anchor requires.

5 / 5

Workflow Clarity

The three steps (get changes, check vulnerabilities, report) are clearly sequenced with a pass/fail output gate, but batch processing (batches of 50) lacks an explicit checkpoint confirming all batches completed, leaving a minor validation gap at score 4.

4 / 5

Progressive Disclosure

Content is well-organized into scoped sections (Scope Declaration, Step 1-3, HARD/SHOULD/WARN tiers) with no nested or buried references, though it is a self-contained single file rather than an overview pointing to one-level-deep references.

4 / 5

Total

17

/

20

Passed

Description

48%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 clear and narrowly scoped to security validation of code changes, but it is terse: it states only one generic action and omits any explicit 'Use when...' trigger guidance. Adding concrete actions and a trigger clause would lift specificity and completeness.

Suggestions

Add a 'Use when...' clause with natural trigger phrases, e.g. 'Use when reviewing code changes for security issues, auditing diffs for vulnerabilities, or checking for hardcoded secrets and injection risks.'

List concrete actions the validator performs (e.g. 'detects hardcoded secrets, flags SQL/command/XSS injection, checks path traversal and auth gaps') to raise specificity from 2 to 4.

Include common synonyms users say ('security review', 'vulnerability audit', 'secret scanning') to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

The phrase 'Check code changes for security vulnerabilities' names the domain and a single action ('Check'), but the action is minimal and generic like the score-2 anchor 'Processes PDF files', rather than listing multiple concrete actions.

2 / 5

Completeness

It has a clear 'what' (check code changes for security vulnerabilities) but no 'when'/'Use when...' clause, which per the guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

It includes relevant keywords ('security vulnerabilities', 'code changes') a user might say, but misses common variations/synonyms such as 'security review', 'audit', or 'vulnerability scan'.

3 / 5

Distinctiveness Conflict Risk

The security-validation niche is clearly distinct from general code-review skills, with only minor overlap risk against closely related review skills.

4 / 5

Total

12

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

allowed_tools_field

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

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

peteski22/agent-pragma

Path

plugins/pragma/skills/security/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.