CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/semgrep-rules

Configures and runs Semgrep - pattern-based SAST across 30+ languages with the Semgrep Registry rulesets (`p/owasp-top-ten`, `p/default`, `auto`) plus custom YAML rules; integrates `semgrep ci` for PR-blocking gates with `--baseline-commit` diff-aware scanning, per-finding inline `nosemgrep` suppressions, `--exclude` / `--include` path filters, output formats (`--json` / `--sarif` / `--gitlab-sast` / `--junit-xml`), and severity filter (INFO/WARNING/ERROR). Use when the user runs Semgrep, asks about pattern rules, or needs a low-friction SAST gate without semantic-DB setup.

76

Quality

95%

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

Overview
Quality
Evals
Security
Files

Quality

Content

96%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 skill body with a well-sequenced workflow, explicit validation, and proper offloading of exhaustive flag/exit-code tables to a one-level reference file. Minor room to surface the bundle reference more prominently in an overview/contents list.

DimensionReasoningScore

Conciseness

Lean, dense reference that assumes Claude's competence — no 'what is SAST' padding, every line is command/flag/rule guidance, and exhaustive flag tables are offloaded to the bundle file.

5 / 5

Actionability

Copy-paste ready commands throughout (install, `semgrep scan --config p/owasp-top-ten`, a complete YAML rule, a working GitHub Actions job, `semgrep validate`), covering the common end-to-end cases.

5 / 5

Workflow Clarity

Six clearly sequenced steps with explicit validation (`semgrep validate --config .semgrep.yml`), a mandatory triage workflow with justification template, and an anti-patterns table providing error-recovery feedback for the batch/destructive CI-gate context.

5 / 5

Progressive Disclosure

Clear one-level reference to references/cli-reference.md for the exhaustive tables (verified real file), with a concise spine; the single reference is well-signaled, though the overview does not enumerate every bundle path upfront.

4 / 5

Total

19

/

20

Passed

Description

92%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, third-person description that states concrete capabilities and explicit use-when triggers with minimal fluff. Slightly jargon-dense on trigger phrasing, but otherwise strong.

Suggestions

Add a couple of plain-language trigger phrases users actually say (e.g. 'scan my code for vulnerabilities', 'PR security lint') alongside the current technical triggers to lift trigger_term_quality.

The description is near the upper length limit; trim a few of the enumerated output formats to a representative subset (e.g. 'output formats including SARIF/JSON') to avoid verbosity.

DimensionReasoningScore

Specificity

Lists many concrete actions (configures/runs Semgrep, integrates `semgrep ci` for PR-blocking gates, diff-aware scanning, `nosemgrep` suppressions, path filters, output formats, severity filter) — comprehensive coverage with no vague padding.

5 / 5

Completeness

Explicitly answers both what (configures/runs Semgrep SAST with registry + custom rules + CI gating) and when ('Use when the user runs Semgrep, asks about pattern rules, or needs a low-friction SAST gate...').

5 / 5

Trigger Term Quality

Strong natural triggers ('the user runs Semgrep', 'asks about pattern rules', 'low-friction SAST gate') but leans technical/jargon-heavy; a few common user phrases (e.g. 'scan my code', 'lint') are not covered.

4 / 5

Distinctiveness Conflict Risk

Semgrep-specific triggers and explicit contrast with semantic-DB tools ('without semantic-DB setup') carve a clear niche distinct from sister scanners like codeql-queries.

5 / 5

Total

19

/

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.

Reviewed

Table of Contents