hjemmesidekongen/contradiction-detection
plugins/herold/skills/contradiction-detection/SKILL.md
Analyze Jira ticket descriptions against comments to detect contradictions, modifications, and extensions to requirements. Produces a severity-ranked list of findings with original text, contradicting text, and resolution suggestions. Runs standalone or auto-triggered after jira-ingestion.
tools
Updated Apr 5, 2026
$ install --global
skillsauthnpx skillsauth add hjemmesidekongen/ai contradiction-detectionInstall 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 24, 2026, 8:37 PM3.5s1 file scanned
SKILL.md
- name:
- contradiction-detection
- description:
- >
- user_invocable:
- true
- interactive:
- false
- model_tier:
- senior
- depends_on:
- []
- type:
- data_validation
- - name:
- severities_valid
- verify:
- Each finding has severity of blocker, warning, or info
- fail_action:
- Assign severity based on impact classification rules
- on_fail:
- Report which tickets had incomplete analysis.
- on_pass:
- Report: N findings across M tickets (blockers: X, warnings: Y, info: Z).
- origin:
- herold
- inspired_by:
- original — no external reference
- ported_date:
- 2026-03-09
- iteration:
- 1
- changes:
- New skill. LLM-based requirement contradiction analysis.
contradiction-detection
Reads a normalized task file and uses LLM analysis to find where comments contradict, modify, or extend the original requirements.
When to run
- Automatically after jira-ingestion completes
- Manually when reviewing a task before starting implementation
- When new comments are added to a ticket (re-ingest then re-analyze)
Steps
- Load task — read
.ai/tasks/<KEY>.yml. Extractdescription,acceptance_criteria, andcomments - Classify each comment — determine if it modifies, contradicts, or extends the original spec (see
references/process.mdfor classification rules) - Generate findings — for each detected issue, produce:
original,contradicting,severity,resolution - Write results — update the
contradictionskey in the task YAML - Report — summary of findings by severity
Severity levels
| Level | Meaning | Example | |-------|---------|---------| | blocker | Direct contradiction that changes core behavior | "Don't use REST, use GraphQL" vs spec saying REST | | warning | Modification that changes acceptance criteria | "Empty search shows recent users" vs "shows nothing" | | info | Additive extension, no conflict with existing spec | "Also add search by username" |
Finding schema: severity, original, contradicting, resolution — see references/process.md §5.
Never
- Never assign blocker severity to additive-only comments — those are info
- Never fabricate findings when no contradictions exist — empty array is correct
- Later comments can resolve earlier contradictions — see
references/process.md§6
Output: Contradiction analysis complete. Findings: N (blockers: X, warnings: Y, info: Z)
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