hjemmesidekongen/skill-quality-rubric
plugins/smedjen/skills/skill-quality-rubric/SKILL.md
8-dimension quality framework for evaluating smedjen knowledge skills. Provides a scoring template for audits with pass/fail thresholds and actionable remediation guidance.
development
Updated Apr 5, 2026
$ install --global
skillsauthnpx skillsauth add hjemmesidekongen/ai skill-quality-rubricInstall 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, 5:30 PM20.6s2 files scanned
SKILL.md
- name:
- skill-quality-rubric
- description:
- >
- user_invocable:
- false
- interactive:
- false
- model_tier:
- senior
- depends_on:
- []
- type:
- data_validation
- - name:
- remediation_present
- verify:
- Every dimension scored below 3 has a concrete remediation note
- fail_action:
- Add remediation for all failing dimensions
- on_fail:
- Audit incomplete — resolve missing scores or remediations
- on_pass:
- Audit complete — report ready with aggregate score and verdict
- origin:
- smedjen
- inspired_by:
- kronen skill-auditor
- ported_date:
- 2026-03-10
- iteration:
- 1
- changes:
- Smedjen variant with 8-dimension scoring framework
Skill Quality Rubric
Structured 8-dimension scoring framework for auditing smedjen knowledge skills. Use this when a skill needs a formal quality review or before promoting a skill to stable.
The 8 Dimensions
| # | Dimension | What It Measures | |---|-----------|-----------------| | 1 | Accuracy | Technical correctness — no wrong facts, no outdated APIs | | 2 | Completeness | Covers the full scope implied by the skill name | | 3 | Code Quality | Examples compile, follow best practices, are copy-paste safe | | 4 | Anti-pattern Coverage | Explicitly calls out what not to do | | 5 | Up-to-dateness | Reflects current library/framework versions | | 6 | Progressive Disclosure | SKILL.md is a quick-start; depth lives in process.md | | 7 | Trigger Discoverability | Triggers match real user phrasings | | 8 | Reference Depth | process.md has enough detail for edge cases |
Scoring Scale
- 5 — Excellent: No gaps. Production-ready as written.
- 4 — Good: Minor gaps. Usable without changes.
- 3 — Acceptable: Gaps present but skill still delivers value.
- 2 — Weak: Material gaps that reduce reliability.
- 1 — Failing: Fundamentally broken or misleading in this dimension.
When to Audit
- Before promoting a skill from draft to stable.
- After a major framework version change that affects the skill's domain.
- When a skill produces consistently low-quality agent outputs.
- As part of a smedjen quarterly quality sweep.
See references/process.md for per-dimension rubric descriptors, scoring template, aggregation method, and reporting format.
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