hjemmesidekongen/prompt-optimizer
plugins/kronen/skills/prompt-optimizer/SKILL.md
Sharpens vague prompts into precise instructions using proven frameworks. Mode A (auto-sharpen): hook-triggered, infers missing context from codebase, rewrites the prompt, shows the sharpened version, proceeds. Mode B (prompt builder): command-triggered via /prompt:create, takes rough intent, applies best framework, outputs a polished prompt for copy or execution.
development
Updated Apr 5, 2026
$ install --global
skillsauthnpx skillsauth add hjemmesidekongen/ai prompt-optimizerInstall 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, 5:20 PM201.4s4 files scanned
SKILL.md
- name:
- prompt-optimizer
- description:
- >
- Mode A (auto-sharpen):
- hook-triggered, infers missing context from codebase,
- builder):
- command-triggered via /prompt:create, takes rough intent, applies
- user_invocable:
- false
- interactive:
- false
- depends_on:
- []
- reads:
- []
- writes:
- []
- type:
- data_validation
- - name:
- audit_passed
- verify:
- Output passes all 6 audit checklist items
- fail_action:
- Address failing audit items and regenerate
- on_fail:
- Re-run framework selection and apply audit checklist
- on_pass:
- Present sharpened prompt (Mode A) or formatted output (Mode B)
- model_tier:
- senior
- origin:
- kronen
- inspired_by:
- antigravity prompt engineering research
- ported_date:
- 2026-03-10
- iteration:
- 1
- changes:
- Initial creation — hook-triggered auto-sharpen + /prompt:create builder
prompt-optimizer
Transforms vague or underspecified prompts into precise, structured instructions.
Two Modes
Mode A (auto-sharpen) — Triggered by hook context when a prompt is too vague. Infer missing context from codebase, apply RSCIT framework, present "I'll approach this as: [sharpened version]", then proceed with the sharpened interpretation.
Mode B (prompt builder) — Triggered by /prompt:create. Takes rough intent,
categorizes it (Technical/Creative/Analysis/Transformation), selects the best
framework, asks 2-3 clarifying questions if needed, outputs a polished prompt
in a code block, then asks "Copy this, or execute it here?"
When to trigger
- Hook detects a vague or ambiguous user prompt (Mode A)
- User invokes
/prompt:create(Mode B) - User asks to improve, sharpen, or optimize a prompt
Process
See references/process.md for the full methodology, diagnostic patterns,
and audit checklist.
Frameworks
See references/frameworks.md for the five supported frameworks with usage
guidance and example structures.
Templates
See references/templates.md for reusable prompt templates organized by
category: Technical, Creative, Analysis, Transformation.
Key Principles
- Instruction hierarchy:
System Context > Task > Examples > Input > Output Format - Progressive disclosure: direct instruction → constraints → reasoning → 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