hjemmesidekongen/code-review
plugins/smedjen/skills/code-review/SKILL.md
Bidirectional code review — supports requesting reviews from the code-reviewer agent and processing received review feedback. Categorizes findings by severity (critical, important, minor) with actionable, direct language.
development
Updated Apr 5, 2026
$ install --global
skillsauthnpx skillsauth add hjemmesidekongen/ai code-reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 5, 2026, 5:27 PM35.5s2 files scanned
SKILL.md
- name:
- code-review
- description:
- >
- user_invocable:
- false
- interactive:
- false
- model_tier:
- senior
- depends_on:
- []
- type:
- data_validation
- - name:
- no_critical_unresolved
- verify:
- No critical findings left unaddressed
- fail_action:
- Address critical findings before marking review complete
- on_fail:
- Review incomplete — address flagged issues
- on_pass:
- Review complete — all findings categorized and addressed
- origin:
- smedjen
- inspired_by:
- superpowers-main code-review + agency code-review
- ported_date:
- 2026-03-09
- iteration:
- 1
- changes:
- Built for smedjen with severity classification and YAML report output
Code Review
Reviews changed files across five dimensions: correctness, security, performance, readability, and testing. Outputs a structured review report with severity-rated findings.
Bidirectional Flow
Requesting a review — Prepare the diff, scope, and context so the reviewer has everything needed without asking follow-up questions. See references/process.md for the request template.
Receiving a review — Process each finding by severity. Critical findings become blockers. Important findings become tasks. Minor findings are addressed or noted with rationale for deferral.
Severity Levels
| Level | Meaning | Action required | |-------|---------|----------------| | critical | Bugs, security holes, data loss risks | Must fix before merge | | important | Performance issues, missing error handling, weak tests | Should fix — document reason if deferred | | minor | Style, naming, simplification opportunities | Nice to have — fix or skip |
Rules
- Review every changed file. No exceptions for "obvious" changes.
- No performative language in review output. State the problem and the fix.
- Rate severity based on production impact, not personal preference.
- When reviewing generated code, focus on the generator config, not the output.
- For dependency updates, check changelogs for breaking changes and CVEs.
- Large diffs (>500 lines): split review by module, review each independently.
Output
Findings written to .ai/reviews/<review-id>.yml — see references/process.md for schema and examples.
Related Skills
hjemmesidekongen/brand-strategy
development
VerifiedTrustedCommunity
Creates a brand from scratch through market research and interactive sparring. Runs competitive research via Perplexity, then guides the user through positioning, audience, voice, values, and content pillars. Produces the full brand guideline set at .ai/brand/{name}/. Use when building a new brand, defining brand strategy for a product, or when /våbenskjold:create is invoked.
SKILL.mdUpdated Apr 5, 2026
hjemmesidekongen/brand-loader
testing
VerifiedTrustedCommunity
Loads brand guidelines from .ai/brand/{name}/ and makes them available to the current context. Progressive disclosure: L1 confirms brand exists, L2 loads summary, L3 loads specific files on demand. Use when a downstream skill or user needs brand context, or when /våbenskjold:apply is invoked.
SKILL.mdUpdated Apr 5, 2026
hjemmesidekongen/brand-evolve
documentation
VerifiedTrustedCommunity
Guided reinvention of an existing brand guideline. Loads current brand from .ai/brand/{name}/, identifies what to keep vs change, and walks the user through targeted evolution. Preserves brand equity while updating positioning, voice, or values. Use when refreshing a brand or when /våbenskjold:evolve is invoked.
SKILL.mdUpdated Apr 5, 2026
hjemmesidekongen/brand-audit
development
VerifiedTrustedCommunity
Codifies an existing brand from materials, samples, and references. Analyzes provided content to extract voice patterns, values, and positioning. Produces the same guideline format as brand-strategy. Use when a brand already exists but isn't documented, or when /våbenskjold:audit is invoked.
SKILL.mdUpdated Apr 5, 2026