hjemmesidekongen/verification-gate
plugins/kronen/skills/verification-gate/SKILL.md
Mandatory 5-step verification protocol before claiming any task is done. IDENTIFY the proof command → RUN it → READ the full output → VERIFY it matches expected → ONLY THEN claim done. Bans inference-based completion ("should work", "probably", "seems to", "likely", "I believe it works"). Use when completing any task in a plan wave, finishing a skill or hook implementation, before marking a wave done, or before reporting success on any multi-step change.
testing
Updated Apr 5, 2026
$ install --global
skillsauthnpx skillsauth add hjemmesidekongen/ai verification-gateInstall 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 PM49.8s2 files scanned
SKILL.md
- name:
- verification-gate
- description:
- >
- user_invocable:
- false
- interactive:
- false
- depends_on:
- []
- writes:
- []
- type:
- code_validation
- - name:
- verdict_stated
- verify:
- An explicit pass or fail verdict was stated based on observed output
- fail_action:
- State the verdict explicitly with the evidence
- on_fail:
- Return to the proof step. Do not mark done until all checks pass.
- on_pass:
- Task is verified. Proceed to mark it done in state.yml.
- model_tier:
- senior
- origin:
- kronen
- inspired_by:
- superpowers repo — verification-before-completion gate
- ported_date:
- 2026-03-09
- iteration:
- 1
- changes:
- Adapted from methodology doc to kronen skill + Stop hook pattern
verification-gate
No task is done until there is observed, read, verified evidence. Not inference.
Apply this protocol at the end of every task before marking status: done.
5-Step Protocol
1. IDENTIFY — What is the proof command for this task type?
2. RUN — Execute it. No skipping.
3. READ — Read the full output. Not a summary.
4. VERIFY — Does the output match the expected outcome?
5. CLAIM — Only now: mark the task done and state the verdict.
Banned Phrases
Never use these to claim completion:
- "should work", "should be fine"
- "probably", "likely", "I think"
- "seems to", "appears to", "looks like"
- "I believe it works", "this ought to"
Replace with: "I ran X, output was Y, verdict: pass."
Process
See references/process.md for proof command selection by task type and
integration with plan-verifier.
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