parzival-save-insight
Save a Parzival insight or learning to Qdrant for cross-session memory
Save a Parzival insight or learning to Qdrant for cross-session memory
Generalised autonomous optimisation loop — soft RLVR for any artifact a user can measure. Use this skill whenever a user wants to iteratively improve an artifact — code, prompts, documents, configs, designs, content — by running structured experiments, evaluating results against a multi-dimensional rubric, and learning from each attempt. Triggers include: "optimise this", "keep improving until it's good", "run experiments on", "autoresearch", "iterate on this overnight", "try different approaches and pick the best", or any request implying repeated evaluate-and-improve cycles. Also use when the user wants to improve a system prompt, a data pipeline, a writing style, or any artifact where quality can be decomposed into measurable tracks. For inference optimisation tasks (model latency, throughput, quantization, GPU deployment), a* delegates the low-level tuning to AITune while maintaining quality tracking and learning.
Create a detailed Linear ticket from a prompt. Asks 5 clarifying questions one at a time, scans the codebase, previews the ticket, and creates it via Linear MCP. Supports prompt templates: /create-ticket /security, /create-ticket /design <area>, /create-ticket <free text>.
Prisma CLI commands reference covering all available commands, options, and usage patterns. Use when running Prisma CLI commands, setting up projects, generating client, running migrations, managing databases, or starting Prisma's MCP server. Triggers on "prisma init", "prisma generate", "prisma migrate", "prisma db", "prisma studio", "prisma mcp".
SEMrush keyword research, domain analytics, backlinks, and competitive intelligence via the local semrush CLI tool
Subdomain enumeration and DNS reconnaissance using subfinder, amass, dnsx, and other tools. Use this skill when user needs to discover subdomains, perform DNS enumeration, gather DNS records, or find hidden subdomains of a target domain.
Research and compare tech stack options (libraries, frameworks, packages) with data-driven recommendations
Refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Use before writing code or implementation plans.
Creates summary for human review - and comprehensive implementation plan for LLM, complete code examples, and verification steps
Manages the persistent file-based work tracker at thoughts/shared/issues/. Use when the user says: "what's next", "what should I work on", "show backlog", "track this", "create an issue", "add to backlog", "mark done", "close issue", "show tasks", "triage issues", "update status", "show roadmap", "priorities", "what's in progress", "move to done", or discusses work item tracking. Not for debugging problems ("I have an issue with X") or one-off planning.
Convenes expert panels for problem-solving. Use when user mentions panel, experts, multiple perspectives, MECE, DMAIC, RAPID, Six Sigma, root cause analysis, strategic decisions, or process improvement.
Generates WAFFLES Declarations for social media posts — preemptive lists of what a post does NOT say. Use when users mention WAFFLES, ask for clarifications on their post, want to prevent misinterpretation, or request disclaimers for controversial/nuanced takes.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Extract keywords from documents using YAKE algorithm with support for 34 languages (Arabic to Chinese). Use when users request keyword extraction, key terms, topic identification, content summarization, or document analysis. Includes domain-specific stopwords for AI/ML and life sciences. Optional deeper extraction mode (n=2+n=3 combined) for comprehensive coverage.
Consults GPT-5.2 with high reasoning for deep analysis. Triggers: "ask the oracle", "consult oracle", "get a second opinion", "ask GPT", "check with GPT", "what would GPT think", "cross-check my reasoning", "external AI". Use for complex debugging, architectural decisions, security audits, or code review requiring deep reasoning. Not for routine tasks.
Analyze AI/ML technical content (papers, articles, blog posts) and extract actionable insights filtered through enterprise AI engineering lens. Use when user provides URL/document for AI/ML content analysis, asks to "review this paper", or mentions technical content in domains like RAG, embeddings, fine-tuning, prompt engineering, LLM deployment.
This skill refines rough ideas into fully-formed designs through collaborative questioning and exploration. Triggers: "help me brainstorm", "let's think through", "explore options", "what are some approaches", "help me design", "think through this with me", "ideate on", "what are my options". Use before writing code or plans when the approach is unclear. Not for mechanical/routine tasks where the solution is already known.