devjarus/ideation-council
skills/practices/ideation-council/SKILL.md
Multi-perspective ideation. Architect researches the query through relevant lenses (product, architecture, security, data, cost) in its own context using Glob/Grep/Context7/Exa. Only runs the perspectives the query actually needs.
testing
Updated May 31, 2026
$ install --global
skillsauthnpx skillsauth add devjarus/coding-agent ideation-councilInstall 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: May 31, 2026, 2:02 AM103.5s2 files scanned
SKILL.md
- name:
- ideation-council
- description:
- Multi-perspective ideation. Architect researches the query through relevant lenses (product, architecture, security, data, cost) in its own context using Glob/Grep/Context7/Exa. Only runs the perspectives the query actually needs.
Ideation Council
When to Apply
- Architect Step 1 research (brownfield or greenfield, before writing spec)
- User asks a broad question that benefits from multiple viewpoints
- Spec requires tradeoff reasoning across domains (security ↔ cost, architecture ↔ deployment)
How It Works
The architect assesses the query and researches only the relevant perspectives in its own context — it does NOT dispatch subagents (only the orchestrator has the Agent tool in this plugin). Each perspective is a focused research mode using Glob/Grep + MCP servers. The architect synthesizes findings into a unified recommendation for the spec.
Perspectives (rules/perspective-prompts.md)
| Perspective | Use When | |-------------|----------| | Product | New features, user-facing changes, MVP scoping | | Architecture | New systems, tech stack decisions, scalability | | Deployment | New services, hosting decisions, going to production | | Security | Auth, user data, payments, LLM integration | | Data | New data models, database choices, migrations | | Cost | Cloud infrastructure, LLM API usage, vendor choices |
Most queries need 2-3 perspectives, not all 6. Assess first, then research.
Process
- Assess -- read the query and determine which perspectives are relevant
- Research -- use Glob/Grep for codebase, Context7 for library docs, Exa for web search. Use interleaved thinking -- reason about each result before the next query. For breadth-heavy lenses (a real stack comparison, an unfamiliar ecosystem), don't grind sequentially in your own context: return
status: needs-researchwith aresearch_requestso the orchestrator fans out parallel investigators and hands back verified, cited findings (see${CLAUDE_PLUGIN_ROOT}/protocols/research.md). - Synthesize (think hard) -- this is the irreversible step; engage extended thinking. Unified recommendation with tradeoffs and open questions -- name a winner and why, don't average conflicting perspectives.
Rules
- Dynamic, not fixed -- never research all 6 perspectives by default; assess the query first
- Synthesize, don't dump -- user gets a unified recommendation, not 6 separate reports; surface conflicts as tradeoffs
- Use the right tool per perspective -- Glob/Grep for codebase, Context7 for docs, Exa for web search
- Brownfield context matters -- existing stack constrains recommendations; don't suggest replacing established choices
Related Skills
devjarus/deep-research
testing
VerifiedTrustedCommunity
Multi-source research method — decompose a question, fan out parallel investigators, interleaved-think each result, verify claims adversarially, synthesize a cited answer. Use for breadth-heavy research, stack comparisons, "which approach wins" questions.
SKILL.mdUpdated May 30, 2026
devjarus/test-doubles-strategy
testing
VerifiedTrustedCommunity
Decide when to use unit vs integration vs e2e tests, and when to mock vs use the real thing per dependency. Dependency injection is the enabler — without it you end up monkey-patching imports. Apply when writing tests of any kind.
SKILL.mdUpdated Apr 25, 2026
devjarus/tdd
development
VerifiedTrustedCommunity
Test-driven development process — write failing test, implement to pass, refactor. Use when implementing any feature or fixing bugs.
SKILL.mdUpdated Apr 25, 2026
devjarus/shared-contracts
development
VerifiedTrustedCommunity
Patterns for sharing types, API contracts, and validation schemas between frontend and backend. Use when multiple domains consume the same data shapes to prevent contract drift.
SKILL.mdUpdated Apr 25, 2026