Evaluate, refine, and develop business ideas through structured lenses — VC review, TAM, B2B/B2C fit, assumptions, objections, hardware feasibility, dev specs, timelines, social impact — plus an LLM council pattern (subagents or Karpathy clone), synthesis, and Typst PDF outputs for internal and public-facing docs.
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin business-idea-eval in danielrosehill/Claude-Business-Idea-Eval-Plugin. Commands read from the repo's manifest — 6 days ago.
assumptions-and-objectionsSurface the load-bearing assumptions in a captured idea and the most likely objections an investor, customer, or skeptical advisor would raise. Produces an assumption-validation plan and an objection-handling brief. Use when the user wants to pressure-test an idea before committing time or capital.
b2b-b2c-fitExplore B2B vs B2C (and B2B2C, prosumer, marketplace, dev-tool) routings for a captured idea. Lays out pros and cons of each viable model and recommends the best fit given the idea, user context, and capital appetite. Use when the user is unsure which customer segment to target.
brainstorm-pivotsBrainstorm tweaks, additions, or pivots that could improve an idea's feasibility, market readiness, capital efficiency, defensibility, or speed-to-revenue. Produces a ranked list of variants with the trade-off each one buys. Use when an idea has been analysed and the user wants suggestions for how t
capture-ideaCapture a new business idea from text input into a structured workspace. Always preserves the raw input verbatim and offers optional formatted versions — executive summary, elevator pitch, technical deep-dive, and timeline/project plan. Use when the user wants to start a new idea workspace from a wr
capture-voice-ideaCapture a business idea from a voice memo / audio file. Transcribes the recording, preserves the raw transcript, then hands off to capture-idea so the user can optionally generate executive summary, elevator pitch, technical deep-dive, and timeline variants. Use when the user has an audio file or re
compare-ideasCompare multiple captured ideas head-to-head across explicit dimensions — commercial prospect, speed to first revenue, capital intensity, fit-to-user, defensibility, social impact — and produce a ranked recommendation. Use when the user has 2+ ideas in the workspace and wants help choosing where to
council-review-karpathyRun a multi-persona LLM-council review using Andrej Karpathy's original llm-council Python implementation. Clones the repo into a temp scratch dir, configures it for the user's idea, runs it, and copies outputs back into the idea workspace. Use when the user explicitly wants the canonical implementa
council-review-subagentsRun a multi-persona LLM-council review of an idea using Claude Code subagents — six personas (Operator, Financier, Skeptic, Visionary, Customer Advocate, Strategist) each review the idea independently, then a chairman synthesizes. Runs entirely inside the Claude harness — no external code or repo cl
dev-specTranslate a captured idea into a development specification — system architecture sketch, key components, data model outline, third-party dependencies, build phases to MVP, and identified hard problems. Software-focused; for hardware see hardware-feasibility. Use when the user wants to estimate "what
hardware-feasibilityFor ideas that involve a physical product, sketch a bill of materials, identify the hardest engineering risks, propose feasibility tests, and estimate prototyping cost. Only use when the idea has a hardware component — skip for pure-software ideas.
internal-pdfRender an idea's analysis (single lens, full synthesis, or council deliberation) as a Typst PDF for internal/personal use. Picks a clean working-document format with metadata and timestamp. Use when the user wants a portable, archivable version of an analysis for their own records.
name-suggestionsGenerate domain and product name suggestions for a captured idea — themed across categories (descriptive, evocative, abstract, founder-named, compound) — and check basic domain/social-handle availability. Use when the user is ready to give an idea a working name.
onboardFirst-run setup for the business-idea-eval plugin. Asks the user where business-idea workspaces should live on disk, captures user context (background, domains of interest, capital appetite, risk profile) used to personalise lens analyses, and writes config.json. Run once before using other skills.
placeholder-logoGenerate a placeholder logo for an idea via an AI image model (fal / nano-banana). Produces a simple wordmark or icon for use in early decks and one-pagers — explicitly placeholder-grade, not a final brand identity. Use when the user wants a visual stand-in for an idea before committing to design.
public-onepagerGenerate a public-facing one-pager PDF for a business idea — designed for sharing with potential cofounders, advisors, or early customers. Strips internal-only analysis (council dissent, raw assumptions, kill criteria) and presents a clean, persuasive summary. Use when the user wants a shareable art
public-pitch-deck-outlineGenerate a slide-by-slide pitch deck outline (markdown, ready to drop into Slides / Pitch / Keynote) for a business idea. Maps existing analysis into the canonical 10–12 slide investor or partner deck structure. Use when the user wants a pitch deck draft from their analysis materials.
social-impact-lensReview a captured idea from a social-impact and ethics lens — who benefits, who is harmed, second-order societal effects, environmental footprint, accessibility, and alignment with the user's personal values. Use when the user wants to weigh non-financial considerations.
synthesize-analysisConsolidate all available analysis for a single idea (lens outputs, council deliberation, comparisons) into one timestamped unified assessment with a clear verdict and recommended next step. Use after the user has run multiple lenses and wants a single document that pulls it all together.
tam-analysisEstimate Total Addressable Market, Serviceable Addressable Market, and Serviceable Obtainable Market for a captured idea. Uses both top-down (industry reports, public stats) and bottom-up (price × users) approaches and reconciles them. Use when the user wants market sizing for an idea.
timeline-and-projectProduce a milestone-based timeline and project plan for taking an idea from today to first paying customer (or first deployment). Identifies critical path, parallelisable workstreams, and key checkpoints. Use when the user wants to know "what's the realistic path and how long".
vc-lensReview a captured business idea from a venture-capital lens — market size, defensibility/moat, team-market fit, capital efficiency, exit pathways, traction milestones, and investability. Produces a structured analysis with a clear verdict. Use when the user wants to know how a VC would react to the
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
AgentBBS cross-host agent federation (ADR-164). Phase 1: register/publish/watch/human-join room coordination. Phase 2 (v3.40.0): signed cross-host federation — identity, peer_add (pin by nodeId+Ed25519 key), peers, serve (read-only pull), sync (pull + union-merge what verifies). Registry-anchored pinning; works on any network (no tailnet required); coordinates work claims (ClaimIssued/Released/Handoff/Ack). Degrades gracefully when agentbbs is absent.
1 skill
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
Install the "AAS Data Analytics & Business Intelligence" editorial skill bundle for Claude Code.
16 skills
Build, train, evaluate, and use open source AI models, datasets, and spaces.
26 skills · 1 MCP server
Independent auditing for AI agents, open source. Claude discovers your setup, confirms the cost, and audits your agent against the one question other tools skip: is it doing the job it's supposed to do, given your business rules and org structure? Test any model (Anthropic, OpenAI, Gemini, Azure, Bedrock, …) graded by self, one independent judge, or a cross-vendor panel; each provider is billed to its own account via a key in your settings, never the command line. Results render as an interactive artifact (with a static-report fallback).
1 skill · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.