hjemmesidekongen/skill-creator
plugins/kronen/skills/skill-creator/SKILL.md
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, optimize a skill's description for better triggering accuracy, or run a TDD baseline eval before writing a skill to target real behavior violations.
testing
Updated Apr 5, 2026
$ install --global
skillsauthnpx skillsauth add hjemmesidekongen/ai skill-creatorInstall 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, 5:24 PM95.2s15 files scanned
SKILL.md
- name:
- skill-creator
- description:
- >
- user_invocable:
- false
- interactive:
- false
- depends_on:
- []
- writes:
- []
- type:
- data_validation
- - name:
- description_triggers
- verify:
- Description includes concrete trigger scenarios
- fail_action:
- Add 'Use when...' phrases with specific user actions
- model_tier:
- senior
- origin:
- kronen
- inspired_by:
- https://skills.sh/anthropics/claude-plugins-official/skill-development
- ported_date:
- 2026-03-09
- iteration:
- 1
- changes:
- Adapted from Anthropic skill-development skill. Enforces our ≤80 line SKILL.md rule, references/process.md overflow pattern, _source block, checkpoint verification, ecosystem.json registration.
Skill Creator
Creates and validates Claude Code skills for any plugin in this workspace.
When to trigger
- Building a new skill from scratch
- Structuring skill content across SKILL.md and references/
- Validating frontmatter fields and line budget
- Porting an external skill to local conventions
Skill structure
| File | Purpose | Required |
|------|---------|----------|
| SKILL.md | Frontmatter + brief body (≤80 lines) | Yes |
| references/process.md | Full specification, tables, examples | When body overflows |
| references/*.md | Additional reference material | No |
| scripts/ | Automation scripts for the skill | No |
| assets/ | Templates, schemas, static resources | No |
Keep SKILL.md short. Overflow goes to references/process.md.
Evaluation
Run evals after creating a skill: trigger eval, task eval, benchmark (A/B), description
optimization. Scripts: scripts/run_eval.py, scripts/aggregate_benchmark.py,
scripts/improve_description.py. Eval agents: agents/grader.md, comparator.md,
analyzer.md. Full eval pipeline and schemas: references/process.md.
NEVER
- Create a skill without frontmatter or with incomplete frontmatter
- Exceed 80 lines in SKILL.md — overflow goes to references/process.md
- Use second-person pronouns ("you") in skill descriptions
- Skip checkpoint definition — every skill needs verification
- Add model_tier values outside junior/senior/principal
Quality scored on 8 dimensions (120 points). Most important: knowledge delta. Full framework: references/quality-dimensions.md. Progressive disclosure: references/progressive-disclosure.md.
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