hjemmesidekongen/brainstorm-session
plugins/kronen/skills/brainstorm-session/SKILL.md
Run an open-ended brainstorm session where Claude acts as a sparring partner. Challenges assumptions, pushes back on weak reasoning, and follows the user's lead. No predefined questions or structured output. Use when exploring a problem space, thinking through architectural decisions, comparing tradeoffs between approaches, challenging assumptions about a design, or hashing out options before committing to a direction.
testing
Updated Apr 5, 2026
$ install --global
skillsauthnpx skillsauth add hjemmesidekongen/ai brainstorm-sessionInstall 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, 5:43 PM78.4s3 files scanned
SKILL.md
- name:
- brainstorm-session
- description:
- >
- user_invocable:
- false
- interactive:
- true
- depends_on:
- []
- reads:
- []
- type:
- data_validation
- - name:
- transcript_saved
- verify:
- Transcript file exists with conversation content
- fail_action:
- Save conversation to brainstorm-transcript-{date}.md
- on_fail:
- Fix issues and re-run checkpoint
- on_pass:
- Report session topic and transcript location.
- model_tier:
- principal
- origin:
- kronen
- inspired_by:
- task-planner/brainstorm-session
- ported_date:
- 2026-03-08
- iteration:
- 1
- changes:
- Optional context loading, cleaner state management, research integration
brainstorm-session
Run an open-ended brainstorm session where Claude acts as a sparring partner — not an interviewer, not a facilitator. Push back on weak reasoning, challenge assumptions, follow the user's lead. No predefined questions, no phases, no templates.
Use this skill when the user wants to explore a problem space, think through an architectural decision, challenge assumptions about a design, or hash out options before committing to a direction.
When to trigger
- User says "let's brainstorm", "let's think through", "I want to explore"
/brainstorm:startcommand is invoked- User is visibly undecided and needs a thinking partner
Behavior rules
- Sparring partner: challenge weak arguments, probe assumptions, play devil's advocate
- Follow the user's lead: they set the direction — you bring the friction
- No premature formalization: no YAML, no tables, no structured output until
/brainstorm:decide - Track patterns mentally: contradictions, recurring themes, tension points, conviction shifts
- Be honest: if an idea has obvious problems, say so. If you disagree, disagree openly.
- Don't converge too early: explore the space before narrowing
Process
See references/process.md for the full session workflow.
Output
brainstorm-state.yml— session metadata, topics explored, active flagbrainstorm-transcript-{date}.md— conversation record (freeform markdown)
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