Reverse-engineer a frontend codebase into a PRD. Usage: /code-to-prd [path]
所属插件包：claude-code-skills
Build competitive analysis matrices with scoring and gap analysis. Usage: /competitive-matrix <analyze> [options]
所属插件包：claude-code-skills
/cs:aeo — Answer Engine Optimization workflow. Audit content for E-E-A-T + structure signals that drive LLM citation (ChatGPT, Perplexity, Claude, Gemini, Mistr
所属插件包：claude-code-skills
/cs:andreessen — Marc Andreessen-mode verdict on a venture, idea, feature, or career bet. Market-first, no hedging, no disclaimers, explicit confidence levels,
所属插件包：andreessen
/cs:arquiteto — Builds a company from scratch as an OKF bundle (tree of .md with type + link graph). Guides the 12-phase interview, one at a time, and generates
所属插件包：arquiteto-de-empresa
Backend engineering review — walks the 7 Matt Pocock forcing questions (read/write ratio + QPS, tenancy, sync vs async, data sensitivity, pattern, RPO/RTO, SLO)
所属插件包：claude-code-skills
Top-level Business Operations router. Routes the inquiry to one of six BizOps sub-skills (process, vendor, capacity, comms, knowledge, procurement) and returns
所属插件包：business-operations-skills
/cs:book-to-plugin <compiled-skill-dir> [--domain <domain>] — wrap a compiled book skill in a claude-skills plugin package (manifest + cs-* agent + /cs:* comman
所属插件包：book-to-skill
/cs:book-to-skill <path|folder|glob>... [skill-name] — convert a book, documentation folder, or source collection into a structured agent skill (core frameworks
所属插件包：book-to-skill
Model headcount + tooling capacity for ops teams (CX/Support/CS/BizOps/IT ops/Finance ops) using Erlang-C queueing math. Sizes the team around the bottleneck pr
所属插件包：business-operations-skills
/cs:capture <dump-text-or-path> — Explicit invocation of the brain-dump organizer. Captures an unstructured stream of thoughts/tasks/ideas and returns a 4-secti
所属插件包：capture、capture-skill
/cs:caveman — Activate persistent caveman-mode. Ultra-compressed responses with technical substance preserved. Auto-clarity exception for warnings + destructive
所属插件包：caveman
Direct vs partner-led channel economics — fully-loaded cost-to-serve, channel ROI, optimal channel mix. NOT partnership structure (sibling partnerships-architec
所属插件包：commercial-skills
Activate the claude-coach skill — personal Claude power-user coaching for the rest of the conversation.
所属插件包：claude-coach
Clinical study design. Select and classify endpoints, estimate sample size / power (means / proportions / survival), and score a study plan for a GO / GO-WITH-C
所属插件包：research-ops-skills
Top-level Commercial router. Routes the inquiry to one of seven Commercial sub-skills (pricing, deal, partner, channel, policy, RFP, forecast) and returns a dig
所属插件包：commercial-skills
Forward bookings / billings / ARR forecast with funnel + cohort math + conversion-assumption disclosure. NOT financial close (finance). Direct invocation of the
所属插件包：commercial-skills
Discount matrix designer + T&C library + exception policy. New ground — designs the policy that deal-desk applies per deal. Direct invocation of the commercial-
所属插件包：commercial-skills
Per-deal review. Score margin + risk, route discount approval to the right human, redline T&Cs against commercial policy. Never auto-approves. Direct invocation
所属插件包：commercial-skills
/cs:deep-learning — Study companion for the Deep Learning textbook (Goodfellow, Bengio & Courville, 2016). Answers chapter questions from a compiled knowledge b
所属插件包：deep-learning-book
/cs:deep-research <question> — Disciplined multi-source investigation for a high-stakes question. Reframes into falsifiable hypotheses, plans, fans out parallel
所属插件包：deep-research
/cs:deep-work — Plan a deep work day the Cal Newport way: audit the task list deep vs shallow against a budget, build an energy-first time-blocked schedule with
所属插件包：deep-work
Run the one-time markdown-html design-system onboarding wizard. Captures brand primary/accent (HEX) + heading/body Google Fonts + design style (editorial/techni
所属插件包：markdown-html-skills
/cs:dl-diagnose — Diagnose a training run against Chapter 11's decision tree: read training error before deciding anything, and never diagnose a NaN as overfitt
所属插件包：deep-learning-book
