Zpankz

Use this skill whenever the user wants high-quality semantic retrieval, cross-textbook synthesis, reference verification, or authority-ranked question answering over the PageIndex corpus. Trigger on requests like "find which texts cover X", "compare sources", "retrieve semantically", "verify this claim from my textbooks", "build a reading list from the corpus", "cluster by topic", or any PageIndex question where naïve filename search would miss relevant material. This skill teaches a state-of-the-art hybrid retrieval workflow over the PageIndex catalog and live MCP extraction surface.

Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming. Use when you need to build complex AI systems, program LMs declaratively, optimize prompts automatically, create modular AI pipelines, or build RAG systems and agents.

Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.

Real-time observability dashboard for multi-agent Claude Code sessions. Visualize agent interactions, tool usage, and session flows in real-time through a web dashboard. Track multiple agents running in parallel with swim lane visualization, event filtering, and live charts. **Key Features:** - 🔴 Real-time event streaming via WebSocket - 📊 Agent swim lanes showing parallel execution - 🔍 Event filtering by agent, session, event type - 📈 Live charts for tool usage patterns - 💾 Filesystem-based (no database required) **Inspired by [@indydevdan](https://github.com/indydevdan)**'s work on multi-agent observability. **Our approach:** Filesystem + in-memory streaming vs. indydevdan's SQLite database approach.

Track and optimize agent specialization during methodology development. Use when agent specialization emerges (generic agents show >5x performance gap), multi-experiment comparison needed, or methodology transferability analysis required. Captures agent set evolution (Aₙ tracking), meta-agent evolution (Mₙ tracking), specialization decisions (when/why to create specialized agents), and reusability assessment (universal vs domain-specific vs task-specific). Enables systematic cross-experiment learning and optimized M₀ evolution. 2-3 hours overhead per experiment.

Routes tasks to appropriate Task tool agents (subagents). Triggers on complex multi-step tasks, research, code review, exploration, or any task benefiting from specialized agent execution. Matches intent to agent types.

Create irresistible offers and pitches using Alex Hormozi's methodology from $100M Offers. Guides through value equation, guarantee frameworks, pricing psychology, and creating offers "too good not to take" for any product or service.

Routes analysis and debugging tasks. Triggers on analyze, debug, troubleshoot, review, audit, security, performance, optimize, investigate, trace.

Generate .workflow.js scripts that compose agents into automated pipelines using the Claude Code Workflow DSL. Produces both .js scripts and equivalent skills by default. Covers full DSL surface (agent, pipeline, parallel, phase, log, workflow, budget, args), sandbox constraints, anti-patterns, and production-ready generation guidance. Invoked by scaffold or standalone via /generate-workflows.

Generate hooks native to the target tool's runtime — shell hooks, Python register(ctx), TypeScript pi.on(), hookify rules, or quality tool integrations (ruff, pyright, eslint, pytest). Detects the active tool and emits the correct format. Invoked by scaffold or standalone via /generate-hooks.

Generate tool configurations across all categories — MCP servers, CLI commands, internal code tools, and custom scripts. Maps the project's full tool surface for agents, skills, and workflows.

Generate agent definitions native to the target tool's runtime — Claude Code .claude/agents/*.md, Antigravity/Gemini agents with kind field, Hermes plugin-provided agents via register(ctx), Codex agent definitions, or Pi agent configs. Detects the active tool and emits the correct format. Invoked by scaffold or standalone via /generate-agents.

Generate a project CLAUDE.md file — the shared memory layer of the workflow system. Produces minimal, high-signal instructions that every other primitive (rules, skills, hooks, agents, workflows) references. Invoked by scaffold or standalone via /generate-claudemd.

Generate .claude/rules/ files — the constraint layer of the workflow system. Produces focused rule files that hooks enforce and agents follow. Scoped by topic and optionally by file path. Invoked by scaffold or standalone via /generate-rules.

Generate .claude/skills/ definitions — the capability layer of the workflow system. Identifies recurring workflows and creates SKILL.md files that agents execute and workflows compose. Invoked by scaffold or standalone via /generate-skills.

Run a grill-with-docs interrogation session on the current repo. Structured one-question-at-a-time interview that resolves design decisions while maintaining CONTEXT.md glossary and docs/adr/ records inline. Standalone entry point for the grilling pattern used by /scaffold.

Create and configure domain-specific evaluation harnesses for the HyperAgents evolution loop. Defines how tasks are loaded, agents are invoked, predictions are collected, and scores are computed. Triggers when setting up evaluation domains or creating custom fitness functions.

Manage the HyperAgents evolutionary archive — an append-only log of all code generations with fitness scores, lineage tracking, and diff storage. Triggers when working with .hyperagents/ directory, archive.jsonl files, or generation metadata.

Domain-agnostic fitness evaluation for evolved code generations. Defines evaluation harness interfaces, scoring contracts, and multi-domain aggregation. Triggers when evaluating code quality, running benchmarks, or scoring agent outputs.

Evolutionary parent selection algorithms for choosing which generation to mutate next. Implements random, best, score-proportional, and novelty-aware selection. Triggers when selecting parents, managing exploration/exploitation tradeoffs, or configuring evolution strategy.

Apply HyperAgents' self-referential improvement pattern to any code artifact. Triggers when Claude is asked to 'improve', 'optimize', 'evolve', or 'self-improve' code, agents, skills, or prompts. Also triggers on repeated failures as an automatic recovery strategy.

Two-phase evaluation strategy from HyperAgents — run a quick staged check on small samples first, only proceed to full evaluation if the staged eval passes. Saves 90%+ compute on broken mutations. Triggers when evaluating generations, running benchmarks, or optimizing evaluation cost.

Recursive context unification engine that decomposes a target directory into an actionable DAG-oriented modular architecture with explicit cross-skill bridges.

Run and validate recursive control-plane synthesis for the skill corpus: dependency graph extraction, DAG/ontology emission, issue tracking, and release packaging across all SKILL assets. This skill orchestrates decomposition, cross-skill synthesis, and deterministic governance with hard/soft dependency normalization.

Run and validate recursive control-plane synthesis for the skill corpus: dependency graph extraction, DAG/ontology emission, issue tracking, and release packaging across all SKILL assets. This skill orchestrates decomposition, cross-skill synthesis, and deterministic governance with hard/soft dependency normalization.

This skill should be used when calculating physiological parameters, modeling membrane transport, analyzing cardiovascular hemodynamics, computing renal clearance, simulating action potentials, or explaining quantitative relationships in any human physiological system. Use for physiology homework, medical calculations, computational biology modeling, and pharmacokinetic analysis.

This skill should be used when calculating physiological parameters, modeling membrane transport, analyzing cardiovascular hemodynamics, computing renal clearance, simulating action potentials, or explaining quantitative relationships in any human physiological system. Use for physiology homework, medical calculations, computational biology modeling, and pharmacokinetic analysis.

Comprehensive skill for operating the pkg-gkg dual-vault neurosymbolic knowledge system. Integrates mdbase typing, TaskNotes, graph analytics, MCMC traversal, beads issue tracking, Atom-of-Thoughts decomposition, and gh-aw activity watching. Use when working on any vault content, study material, curriculum analysis, or knowledge graph operations.

Install, operate, audit, and extend the fbm Messenger archive CLI while preserving privacy. Use when working on fbm commands, sync, browser-cookie auth, storage, structured categorization, releases, or diagnostics.

Use when an agent needs to operate the screenpipe CLI MCP connector for ScreenApp API tasks, including checking auth, asking questions about ScreenApp recordings, uploading local media, registering webhooks, tagging resources, updating profiles, or discovering generated OpenAPI endpoint tools.

Iterative architecture discovery through disposable builds. Use when facing genuine architectural uncertainty — multiple plausible designs, unfamiliar integrations, or problems where upfront specs would be immediately obsolete. Guides: frame unknowns → build/stress/journal → formalize into spec-based output → delete scaffold.

Use this skill whenever the user wants high-quality semantic retrieval, cross-textbook synthesis, reference verification, or authority-ranked question answering over the PageIndex corpus. Trigger on requests like "find which texts cover X", "compare sources", "retrieve semantically", "verify this claim from my textbooks", "build a reading list from the corpus", "cluster by topic", or any PageIndex question where naïve filename search would miss relevant material. This skill teaches a state-of-the-art hybrid retrieval workflow over the PageIndex catalog and live MCP extraction surface.

macOS resource consumption intelligence using witr — inspect CPU, RAM, I/O, FD pressure, thermal state, and sleep assertions per process; classify drain as appropriate vs inappropriate; and emit structured JSON agent context.

Convert Claude Code plugin repositories into native Pi packages with deterministic MCP-to-CLI bridges, migration reports, and verification prompts.