AI & ML

ctaxnagomi Bundle

Magic MCP server for AI-powered development.

ctaxnagomi Bundle

Nimbalyst AI agent framework.

ctaxnagomi Bundle

Meta-skill authoring capability. Write, structure, and validate SKILL.md files for AI agents, including YAML frontmatter, discoverability, and platform compatibility. Use for creating, editing, or reviewing agent skills.

ctaxnagomi Bundle

Create and maintain a shared domain vocabulary and model that all code and tests reference. Use when establishing domain vocabulary, creating CONTEXT.md, or aligning code with business concepts.

ctaxnagomi Bundle

Fast Agent framework for AI development.

ctaxnagomi Bundle

Google Gemini CLI agent.

ctaxnagomi Bundle

Anthropic Claude Code CLI agent.

ctaxnagomi Bundle

ComfyUI integration via MCP for AI art.

ctaxnagomi Bundle

OpenHarness for AI agent orchestration.

ctaxnagomi Bundle

Pydantic AI for type-safe agent development.

ctaxnagomi Bundle

Enhanced AI agent capabilities and advanced workflows.

ctaxnagomi Bundle

Cursor AI agent for code generation.

ctaxnagomi Bundle

Hermes Agent by Nous Research.

ctaxnagomi Bundle

Write clear, structured prompts and instructions optimized for AI agent consumption. Use when writing SKILL.md files, creating agent instructions, or structuring documentation for AI readability.

ctaxnagomi Bundle

AI agent management and orchestration.

ctaxnagomi Bundle

AI agent improvement and optimization.

ctaxnagomi Bundle

Browser automation with Playwright for AI agents.

newkayak12 Skill

Use when installing, connecting, or verifying the graph-engineering MCP for a Claude Code project. Not for running a graph; use graph:orchestrate.

newkayak12 Bundle

Use when running a whole request through the graph-engineering MCP and driving its harness nodes without holding the payload yourself. Triggers on: "그래프 돌려줘", "노드 단위로 돌려줘", "run it through the MCP", "orchestrate this run". Not for installation.

newkayak12 Bundle

Use when running a whole request through the teams-engineering MCP and driving its harness nodes without holding the payload yourself. Triggers on: "그래프 돌려줘", "노드 단위로 돌려줘", "run it through the MCP", "orchestrate this run". Not for installation.

newkayak12 Bundle

Use when answering questions over an existing linked Markdown vault, local SQLite index, ontology, knowledge graph, RAG corpus, or mixed knowledge assets while preserving citations, uncertainty, and retrieval traceability.

kesslernity Bundle

Reads a process flow diagram (image, PDF or native export) with its job header and returns a provenance-tagged extraction register: equipment, streams, tags, connectivity, instruments already shown, notes and legends, connectivity findings and an explicit UNKNOWN list, then holds at gate G1. Extracts and records only; never enriches, tags or proposes. Use when the user asks to "start a PFD to P&ID job", "read in the attached PFD", "extract the equipment and streams from this PFD" or "read this PFD into a register". Do not use for checking the model, use process-model-check instead; do not use to propose lines, instruments or tags, use piping-enrichment or instrumentation-and-control-enrichment after gate G2. Drafts for human review; never approves, authorises or signs off.

kesslernity Bundle

Proposes the instrumentation and control content a P&ID adds to an accepted PFD process model: instruments drawn carried over as facts, measurement points and control loops the control philosophy requires, tag structure per the project instrument numbering procedure, system interfaces, and alarms, interlocks, trips and fail actions as quoted. Never assigns safety functions, ranges or setpoints. Use when the user asks to "run the instrumentation and control enrichment", "add the instrument section to the P&ID draft", "list the control loops the philosophy requires" or "carry the PFD instruments into the P&ID" after the piping section. Do not use for safety flags, SIL or trip classification, use process-safety-flags instead; do not use to assign tag numbers, use tagging-and-numbering. Drafts for human review; never approves, authorises or signs off.

rudironsoni Skill

Publishes .NET artifacts from GitHub Actions. NuGet push, container images, signing, SBOM.

newkayak12 Skill

Use when designing or refining an ontology for a knowledge system: domain concepts, classes, relationship semantics, constraints, controlled vocabularies, reasoning rules, and mappings to graph/RAG/vault artifacts.

newkayak12 Skill

Use when a task is too large or ambiguous to hand to a single agent without first defining clear subtask boundaries. Triggers on: "큰 작업 분해해줘", "에이전트 분리해줘", "subtask로 나눠줘", "task decomposition", "이 작업 어떻게 나눠야 해?", "agent에게 어떻게 전달해?", "병렬 작업 계획 잡아줘".

newkayak12 Skill

Use when building a knowledge vault end to end, or when eval and competency questions keep failing and the retrieval fix has to be measured — routes catalog, graph, RAG, index, and repair as one loop with a stop condition.

newkayak12 Skill

Use when preparing a retrieval-augmented generation corpus from code, documents, notes, tickets, or mixed sources by chunking, adding metadata, preserving citations, and designing retrieval/evaluation checks.

newkayak12 Bundle

Use when reviewing or quality-checking a skill before shipping. Runs 6 checks: usefulness, authoring, structure, MCP, weight, output quality. Triggers on: 스킬 검토, skill review, validate skill, 배포 전 검토.

newkayak12 Bundle

Use when someone is stuck on a problem and needs a different frame entirely, suspects they have blind spots, or has exhausted obvious solutions. Three instruments: choose the right mental model, systematically surface unknown unknowns, and break...

newkayak12 Skill

Use when building, rebuilding, refreshing, or syncing a local SQLite knowledge index from canonical Markdown plus catalog, RAG, and graph JSONL; not for querying an existing index or creating source artifacts.

newkayak12 Skill

Use when explicitly running the beta harness where Claude chooses Agent Team or Dynamic Workflow for a substantial request. Not the stable harness.

newkayak12 Bundle

Use when turning code, docs, notes, or mixed sources into a small-to-moderate, query-efficient Markdown knowledge base with predictable folders, an AI lookup catalog, source-grounded summaries, and RAG-ready metadata.

rlaope Skill

[omh] Hermes UltraQA workflow: adversarial QA and fix loops. Use when the user says: ultraqa, adversarial qa, hostile scenarios, e2e qa, real-world qa, qa scenario, release qa, 敵対的QA.

rlaope Bundle

[omh] Hermes Loop workflow: agentic interviewer -> planner -> researcher -> builder -> reviewer cycles until a real gate. Use when the user says: loop, goal loop, long horizon goal, never stop, research plan goal feedback, token exhaustion resume, permission profile, star 10k.

rlaope Skill

[omh] Ultraperf - find where a system is actually slow, leaking, or expensive across runtime, memory, token cost, storage, rendering, inference, CI, and query domains, then fix one measured hot path at a time behind a regression budget. Use when the user says: ultraperf, ulw-perf, performance audit, performance bottleneck, find the bottleneck, profile the hot path, memory leak investigation, token cost hotspot.