brainstorming — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited brainstorming (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Launch the Brainstorming AI skill to turn ideas into validated designs through:
lde:brainstormingdeep-research harness (fan-out web search, source-fetching, adversarial fact-checking, cited synthesis).local/brainstorms/, gitignored)/lde:brainstorming [optional: idea to explore]# Without arguments - will ask what you want to explore
/lde:brainstorming
# Product ideas
/lde:brainstorming add real-time notifications feature
/lde:brainstorming redesign onboarding flow for better conversion
/lde:brainstorming freemium vs subscription pricing model
# Engineering decisions
/lde:brainstorming migrate from REST to GraphQL
/lde:brainstorming choose between Redis and Memcached for caching
/lde:brainstorming implement event-driven architecture
/lde:brainstorming monorepo vs polyrepo for microservicesA structured design document saved to .local/brainstorms/<topic>/YYYY-MM-DD-design.md (local-only scratch, gitignored — promote to docs/plans/ if the brainstorm matures into a shippable decision):
When invoked without arguments, you'll see:
Each path has tailored research queries and design considerations.
The skill runs a deep-research pass before presenting options — a single scoped brief that the harness fans out internally across these angles:
| Angle | Product Ideas | Engineering Decisions |
|---|---|---|
| State of the art | Market solutions, competitors, UX patterns, case studies | Architecture patterns, benchmarks, production experiences |
| Technical landscape | Latest API patterns, recommended approaches | Official docs, migration paths for frameworks/libraries |
| Risks & anti-patterns | Failed launches, adoption pitfalls | "Why X failed" post-mortems, scaling/security/cost traps |
Codebase awareness ("existing foundations") comes from the skill's project-grounding step — deep-research covers the web, not your repo.
✅ Research-first: Current data before opinions - no outdated advice ✅ Adaptive intake: Only asks about genuine gaps in context ✅ Deep research harness: Delegates to deep-research — parallel web search, source-fetching, and adversarial fact-checking ✅ Verified, not just gathered: Claims are adversarially checked before they shape the design ✅ Codebase-aware: Considers existing patterns and constraints from project grounding ✅ Source citations: All recommendations backed by verified research ✅ Incremental validation: Check direction at each design section ✅ Local-only by default: Design documents stay in .local/brainstorms/ (gitignored); promote to docs/plans/ only when a brainstorm matures into a shippable decision
This command invokes the lde:brainstorming skill using the Skill tool.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.