hjemmesidekongen/hypothesis-generator
plugins/kronen/skills/hypothesis-generator/SKILL.md
Generate three competing hypotheses for a debugging problem, then investigate each in parallel and synthesize evidence to identify the root cause. Extends root-cause-debugging with structured hypothesis management. Use when a bug's root cause is unclear after initial evidence gathering, when a previous fix failed and the cause is still unknown, when multiple subsystems could plausibly be at fault, or when confirmation bias in investigation needs to be avoided.
development
Updated Apr 5, 2026
$ install --global
skillsauthnpx skillsauth add hjemmesidekongen/ai hypothesis-generatorInstall 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 20, 2026, 10:04 AM11.9s1 file scanned
SKILL.md
- name:
- hypothesis-generator
- description:
- >
- user_invocable:
- false
- interactive:
- false
- depends_on:
- [root-cause-debugging]
- writes:
- []
- type:
- code_validation
- - name:
- confirmed_hypothesis
- verify:
- One hypothesis scored CONFIRMED before entering Phase 4
- fail_action:
- If none confirmed, return to Phase 1 for more evidence
- on_fail:
- Do not proceed to Phase 4 until synthesis is complete.
- on_pass:
- Root cause confirmed by hypothesis elimination. Proceed to fix.
- model_tier:
- senior
- origin:
- kronen
- inspired_by:
- agents-main + superpowers-main systematic-debugging
- ported_date:
- 2026-03-09
- iteration:
- 1
- changes:
- 3-hypothesis parallel investigation methodology. Structured extension to root-cause-debugging's 4-phase protocol. Evidence synthesis with scoring (CONFIRMED/POSSIBLE/REFUTED).
hypothesis-generator
Generate three competing hypotheses, investigate each, synthesize — then fix. Eliminates confirmation bias by forcing investigation of alternative causes.
When to use
After Phase 1 of root-cause-debugging when evidence doesn't clearly point to one cause. Do NOT use for obvious bugs — only when genuinely uncertain.
3-Hypothesis Protocol
After evidence gathering:
Hypothesis A: most obvious explanation
Hypothesis B: different mechanism, same symptom
Hypothesis C: deeper/systemic cause (the non-obvious one)
Each needs: Cause | Mechanism | Prediction | Test
Investigate all three (parallel if possible)
Score each: CONFIRMED / POSSIBLE / REFUTED
Synthesize → select confirmed hypothesis → enter Phase 4
Synthesis Rules
One confirmed → Phase 3 hypothesis. Two confirmed → find unifying root cause. All refuted → return to Phase 1. All possible → run most discriminating test.
Full process: root-cause-debugging/references/process.md — Hypothesis-Driven Extension.
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