Results for “pr”

Guides a structured brainstorm that surfaces user ideas, explores directions, and produces a spec and report for later planning.

Therapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and pharmacological prediction.

Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.

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.

Define company values and culture for a minimalist business, drawing on principles from The Minimalist Entrepreneur.

Prepare and execute negotiations using tactical empathy, calibrated questions, and the Ackerman method.

Create stakeholder alignment artifacts including responsibility matrices, decision frameworks, and communication plans.

Design first-run experiences that get users to value quickly without overwhelming them.

Identifies, classifies, and prioritizes tech debt to build a refactoring roadmap, drawing on twelve classic engineering books.

Prüft Gaming-AGB auf rechtliche Risiken nach BGB §§ 305-310, erstellt Klauselampel, Redline und Ersatzformulierungen mit gerichtsfester Begründung.

Captures important product, technical, or founder decisions as durable context with rationale, tradeoffs, and follow-up implications.

Create a practical onboarding plan for a new team member with outcomes, first-week structure, stakeholder introductions, learning path, and manager check-ins.

Use when delivery work needs structuring into epics — defining a new epic, refining or superseding an existing one, or decomposing a PRD's requirements into durable delivery structures that feed issue decomposition. Writes docs/product/epics/NN-<slug>.md (durable, id-stable, superseded-never-deleted), each epic tracing to the JTBD ids it serves and the PRD requirement IDs it bundles. In the A-Team pipeline this is a definition-phase output ("the Epics"). Do not use for full roadmap/portfolio planning across quarters (deliberately not ported), for delivery tickets or acceptance criteria (ticket-writer), or to create or revise jobs (jobs-to-be-done).

Transform meeting transcripts into structured summaries with date, participants, topic, key decisions, action items, and open questions.

Plan tailored engagement for a specific stakeholder before critical conversations, milestones, or relationship repairs.

Design error prevention, detection, and recovery experiences that minimize user frustration.

Prüft Bonus-Rabatt-Klauseln in AGBs nach BGB, erstellt Redline, Ersatzfassung und Risikoampel mit Verbraucher-/B2B-Unterscheidung.

Identify and improve unclear, confusing, or poorly written interface text to make the product easier to understand and use.

Designs an edit blueprint and uncertainty register for video projects, following a narrative loop and schema constraints.

Build sales playbooks, define pipeline stages, and optimize conversion rates with structured processes and lead scoring.

The Sovereign Litigation Protocol (SLP-2026). A recursive, high-fidelity framework for autonomous advocacy, multi-jurisdictional discovery, and the algorithmic resolution of civil and commercial disputes.

Designing, optimizing, and auditing repository structure: directory design, docs/ layout (PRD, specs, ADR), test/script organization, anti-pattern detection. Use for repo layout or migration planning.

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".

Provides strategic leadership frameworks for vision, fundraising, board management, culture, and stakeholder alignment.

Conduct comprehensive competitive analysis to understand the landscape, identify direct competitors, and uncover differentiation opportunities.

Identify, categorize, and prioritize technical debt into a ranked, defensible backlog that ties each remediation to impact and effort — a register, not a wish list.

Generate project-specific agent teams during workflow Discovery. Trigger: 'set up a team', 'create agents for', or auto-triggered by ijfw-workflow deep mode after Discovery.

When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program," or "experiment playbook." Use this whenever someone is comparing two approaches and wants to measure which performs better, or when they want to build a systematic experimentation practice. For tracking implementation, see analytics. For page-level conversion optimization, see cro.

Create clear roadmap communication artifacts for internal and external stakeholders, including presentations, release notes, changelogs, and feature announcements.

Discovers available Azure OpenAI model capacity across regions and projects, analyzes quota limits, and recommends optimal deployment locations.

Review any business decision, plan, or strategy through the minimalist entrepreneur lens, providing a gut-check and simplification advice.

Calculate TAM, SAM, and SOM with explicit assumptions, methods, and caveats for market sizing.

Establish design review gates with criteria, checklists, and approval workflows to maintain design quality.

Design the structure, hierarchy, and navigation model for a product's content and features.