hjemmesidekongen/parallel-reviewer
plugins/kronen/skills/parallel-reviewer/SKILL.md
Dispatch 4 specialized reviewers in parallel (security, performance, architecture, testing), each analyzing the code independently. Coordinator consolidates findings, deduplicates, and ranks by severity. Use when reviewing a non-trivial code change that touches multiple quality dimensions, before merging a feature branch, when a PR needs thorough multi-angle review, or when a single reviewer pass may miss domain-specific issues.
development
Updated Apr 5, 2026
$ install --global
skillsauthnpx skillsauth add hjemmesidekongen/ai parallel-reviewerInstall 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, 5:18 PM179.0s2 files scanned
SKILL.md
- name:
- parallel-reviewer
- description:
- >
- user_invocable:
- false
- interactive:
- false
- depends_on:
- []
- type:
- code_validation
- - name:
- coordinator_read_artifacts
- verify:
- Coordinator read artifact files directly; did not paraphrase reviewer responses
- fail_action:
- Read artifact files from disk per forward-message pattern
- on_fail:
- Complete all reviews and consolidate from artifacts before reporting.
- on_pass:
- Parallel review complete. Report ranked by severity and deduplicated.
- model_tier:
- senior
- origin:
- kronen
- inspired_by:
- agents-main/plugins/agent-teams/skills/multi-reviewer-patterns/
- ported_date:
- 2026-03-09
- iteration:
- 1
- changes:
- 4-reviewer parallel dispatch pattern adapted to kronen agent system. Uses forward-message artifact pattern from E1 for lossless result collection.
parallel-reviewer
4 specialized reviewers run in parallel. Coordinator consolidates from artifacts. No telephone game — artifacts read directly per forward-message pattern.
4 Review Streams
| Reviewer | Focus | Artifacts checked | |----------|-------|------------------| | security | Auth, injection, secrets, input validation, OWASP top 10 | All modified files | | performance | N+1 queries, blocking calls, memory allocation, loop complexity | Hot paths | | architecture | Coupling, cohesion, boundary violations, pattern consistency | Module boundaries | | testing | Coverage gaps, missing edge cases, test quality, mock hygiene | Test files + coverage |
Dispatch Protocol
- Collect modified files for review
- Dispatch all 4 reviewers as parallel Agent calls (or sequential subagent tasks)
- Each reviewer writes findings to
.ai/plans/<plan>/artifacts/<name>-review.md - Coordinator reads all 4 artifacts directly (do NOT paraphrase)
- Consolidate: deduplicate, rank by severity, write final report
Full Process
See references/process.md for reviewer prompt templates, deduplication rules,
consolidation format, and severity ranking criteria.
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