Results for “test”

Provides battle-tested PyTorch training recipes for LLMs, vision, diffusion, and biomedical domains, covering training loops, optimizer selection, LR scheduling, mixed precision, and debugging.

Translates stakeholder feature requests into validated outcome statements before any work is committed. Use this skill — proactively and without waiting to be asked — whenever a stakeholder, exec, or customer arrives with a pre-packaged solution: "we need a dashboard", "add a Slack notification", "build an export feature", "create a report", "let's add a filter", "can we just add X". Also triggers for: "how do I push back on this request", "what outcome does this feature solve", "outcome vs output", "outcomes not features", "what are we really trying to achieve", "we're being a feature factory", "I need to reframe this as a problem", "the stakeholder is pushing a specific solution", "discovery before delivery", "assumption testing", "translate this request into an outcome", "ship outcomes not features". Runs the 'One Framework. Four Questions.' protocol (Liatti + Cagan + Torres): Behavior Change → Assumption Test → Cheapest Test → Success Metric. Produces an Outcome Brief with embedded AI prompts ready to pas

Build an Opportunity Solution Tree from outcomes to opportunities, solutions, and tests. Use when a stakeholder request needs problem framing before you decide what to build.

Orchestrates a full software development pipeline by sequentially loading and executing seven role-specific skills (BA, TechLead, PM, BE Dev, FE Dev, Tester, QA/QC), with configurable project levels and gate checks.

Workflow 1: Full idea discovery pipeline. Orchestrates research-lit → idea-creator → novelty-check → research-review to go from a broad research direction to validated, pilot-tested ideas. Use when user says "找idea全流程", "idea discovery pipeline", "从零开始找方向", or wants the complete idea exploration workflow.

Create a structured customer interview script with JTBD probing questions, warm-up, core exploration, and wrap-up sections. Follows The Mom Test principles — no leading questions, no pitching, focus on past behavior. Use when preparing for user interviews, creating interview guides, or planning discovery research.

Routes product requests to one of 12 bundled skills covering prioritization, OKRs, UX research, design tokens, competitive teardown, analytics, experiments, discovery, roadmaps, spec-to-repo, landing pages, and SaaS scaffolding.

Plan and synthesize product/user research with method rigor: select the right method for the goal, compute defensible sample sizes with confidence labels, and cluster coded observations into insights while flagging single-source anecdotes.

Translate a vague request or GitHub issue into a concrete, testable spec using five structured elements (problem, scope, acceptance criteria, edge cases, success criterion) before writing any code. Prevents scope creep, PR churn, and mid-implementation pivots.

Clarifies ambiguous or conflicting requests by researching first, then asking only judgment calls. Use when prompts say "grill me", ask hard questions, request relentless interrogation, pressure-test assumptions, clarify scope/requirements, define success criteria, or request system-design/optimization decisions.

Run structured What-If scenario analysis with 4-6 branch possibility exploration (best, likely, worst, wild card, contrarian, second-order). Use for speculative questions about uncertain futures, strategic forks, contingency planning, or stress-testing decisions.

Run a pre-mortem risk analysis on a PRD or launch plan. Categorizes risks as Tigers (real problems), Paper Tigers (overblown concerns), and Elephants (unspoken worries), then classifies as launch-blocking, fast-follow, or track. Use when preparing for launch, stress-testing a product plan, or identifying what could go wrong.

Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning neural networks, debugging loss spikes or OOM, choosing architectures, or optimizing GPU throughput.

Performs a gap analysis between two artifacts (a current state and a desired state) and produces a plain-language, stakeholder-readable report indexed by stable gap IDs. Use when the user wants to compare, evaluate, audit, or reconcile one artifact against another. Does not investigate runtime bugs — use investigate. Does not assess module-level architecture — use architectural-analysis. Does not research open-ended options with no second artifact to compare against — use research.

Produces a plain-language stakeholder summary from an existing feature specification, for sharing with non-technical stakeholders before implementation kicks off. Use when the user wants to draft a stakeholder summary, executive summary, or business summary of a feature spec or PRD. Does not write the spec itself — use plan-a-feature. Does not sequence the build into phases — use plan-a-phased-build. Does not produce an implementation plan — use plan-implementation.

Discovers the core attributes of the current code repository and its projects — languages, frameworks, tooling, and where things live — and writes a concise reference section directly into the project's AGENTS.md or CLAUDE.md for other skills, agents, and hooks to consume. Use when scanning, analyzing, or detecting the project's technology stack, build tools, or repository structure. Does not create or update project documentation — use project-documentation for writing feature or system docs.

Build empowered product teams using discovery and delivery dual-track. Use when the user mentions "product discovery", "empowered teams", "feature factory", "product roadmap", "opportunity assessment", "product vision", "product-led growth", or "discovery vs delivery". Also trigger when restructuring product teams away from output-driven models, setting product strategy, or defining what to build next based on outcomes. Covers product discovery techniques, team structure, and continuous value delivery. For customer interviews, see mom-test. For ongoing discovery systems, see continuous-discovery.

Set up and verify a connection to an NI USRP radio (USRP E320, N300, N310, N320, N321, X300, X310, or X410) using Wireless Testbench. Use when connecting a USRP for the first time, configuring radio hardware, troubleshooting connection failures, or verifying a radio setup. Covers host inspection (OS, NIC type/speed/MTU), device discovery (findsdru, probesdru), UHD version checking, programmatic radio configuration, and basebandTransceiver verification. Also use when the user mentions USRP setup, radio not found, connection errors, dropped samples, or network configuration for SDR hardware.

Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.

Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.

Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.

Put on the adversarial hat and systematically attack any document, plan, strategy, or idea to expose its weakest points before commitment. Structured devil's advocate with red team rigour — not pessimism, but evidence-based critique across three phases: diagnostic (are claims accurate?), creative (is the problem artificially constrained?), challenge (are solutions robust?). Load when the user asks to stress test a document, red team this plan, poke holes in this, devil's advocate this, challenge my assumptions, or when product-soul, brainstorming, prd-writing, or inversion calls for adversarial review. Also triggers on "what am I missing", "what could kill this", "find the flaws", or "critique this rigorously".

Creates and maintains project documentation for features, systems, and components. Use when documenting how a feature, system, or component works — including writing, updating, or organizing docs. Does not scan or detect the project's technology stack — use project-discovery for repository analysis and config detection. Does not create architectural decision records — use architectural-decision-record for ADRs. Does not create or update coding standards — use coding-standard instead. Does not generate PR descriptions — use update-pr-description for that. Does not produce runbooks for operational scenarios — use runbook for that. Does not rewrite existing prose for readability — use edit-for-readability for that. Does not produce an ephemeral, understand-now overview of code or a PR — use code-overview for that.

Orchestrator for the pre-decision business-idea lifecycle — generate ideas, model them, evaluate them, validate them with customers, and only then hand off to product-soul / brainstorming. Routes through `idea-generation`, `business-modeling`, `idea-evaluation`, and `customer-discovery`. Load when the user asks to explore business ideas, find a startup idea, evaluate a venture, validate an idea, says "what business should I start", "should I build this", "is this a good business", "I have a startup idea", "evaluate this venture", "model this business", "validate this idea", "Mom Test this", "Lean Canvas this", "Business Model Canvas", "Value Proposition Canvas", "go/no-go on this idea". Pre-decision suite — once one idea is committed, hands off to `product-soul`. Does NOT design features (use `brainstorming`) or audit built products (use `reality-check`).

World-class autonomous sales and revenue skill system. Use ANY time the user asks to sell, pitch, prospect, close, negotiate, launch, monetize, build funnels, write outreach, craft proposals, develop pricing, design offers, write sales copy, create email sequences, plan campaigns, position products, handle objections, create playbooks, build pipeline, forecast revenue, develop GTM strategy, optimize conversions, write ad copy, create sales decks, score leads, nurture prospects, upsell, cross-sell, retain customers, write case studies, price products, structure enterprise deals, create battle cards, script discovery calls, build affiliate programs, plan product launches, create webinar funnels, design pricing pages, A/B test offers, analyze unit economics, calculate LTV/CAC, or ANY other sales, revenue, monetization, go-to-market, or commercial growth task. If it involves selling, revenue, deals, pipeline, or commercial strategy — USE THIS SKILL. Trigger aggressively.

When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform. Also use when the user mentions 'ad copy variations,' 'ad creative,' 'generate headlines,' 'RSA headlines,' 'bulk ad copy,' 'ad iterations,' 'creative testing,' 'ad performance optimization,' 'write me some ads,' 'Facebook ad copy,' 'Google ad headlines,' 'LinkedIn ad text,' 'static ads,' 'static ad concepts,' 'ad templates,' 'iMessage ad,' 'chat reveal ad,' 'fake DM ad,' 'ChatGPT ad,' 'Apple Notes ad,' 'AirDrop ad,' 'creative strategy,' 'creative roadmap,' 'creative retro,' 'hook writing,' 'creative review page,' 'present ad creative for approval,' 'motion video ad,' 'faceless video ad,' 'animated explainer ad,' 'motion collage ad,' or 'I need more ad variations.' Use this whenever someone needs to produce ad copy at scale or iterate on existing ads. For campaign strategy and targeting, see ads. For landing page copy, see copywriting.

Designs the contract for an API change inside one codebase — a component's props, a function surface, URL or query parameters, an event payload, or a module boundary — through a discovery pass, an options document with one recommendation, a question round, and an adversarial validation round, with every element of the contract justified from one stated goal. Use when you want to design, shape, decide, or nail down an interface, contract, signature, or API change for a capability you can already describe, sized for roughly one pull request. Produces a design document and changes no code. Does not specify what a feature should do — use plan-a-feature. Does not plan delivery or sequencing — use plan-implementation. Does not assess the architecture of existing code — use architectural-analysis. Does not write the code — use tdd. Does not restructure existing code — use refactor. Runs its rounds without pausing for review; to review each round as it lands, use pairing.