AI & ML Agent Skills

Main agent orchestrator that coordinates a specialized squad of agents

Self-hosted semantic memory for AI agents via MCP. Save worklogs, decisions, and notes, then recall them across sessions by meaning, not keyword. Postgres + pgvector with auto-tagging.

GPG (GNU Privacy Guard) encryption and signing reference. Covers key generation (Ed25519/RSA), export/import, keyservers, file encryption (symmetric + asymmetric), git commit signing, detached signatures, gpg-agent caching, SSH via GPG, and pass password manager.

Use kordoc for agent-native HWP/HWPX document parsing, JSON extraction, diffing, form-field extraction, and Markdown→HWPX reverse conversion (read/convert only — for binary editing use rhwp-edit).

Fetch any X/Twitter post as clean LLM-friendly JSON. Converts x.com, twitter.com, or adhx.com links into structured data with full article content, author info, and engagement metrics. No scraping or browser required.

Expert CMMC 2.0 (Cybersecurity Maturity Model Certification) advisor for US defense contractors and subcontractors in the Defense Industrial Base (DIB). Use this skill whenever a user asks about CMMC 2.0, CMMC Level 1, Level 2, or Level 3, DoD cybersecurity compliance, NIST SP 800-171, CUI (Controlled Unclassified Information) protection, System Security Plan (SSP), Plan of Action & Milestones (POA&M), C3PAO assessments, DIBCAC audits, self-assessment, SPRS score, or any requirement under DFARS 252.204-7012 or 7021. Also trigger for: "CMMC gap analysis", "CMMC readiness", "FCI protection", "CUI scoping", "CMMC practices", "DoD contract cybersecurity", "defense supply chain security", or "prime contractor flow-down requirements".

Supply-chain malware infection scanner. IoC-based local scan + safe eradication for npm/PyPI worm campaigns (Mini Shai-Hulud 1st/2nd, S1ngularity, lottie-player). Detects OS persistence (LaunchAgent/systemd), IDE-hook implants (.claude/.vscode/.github/workflows), lockfile-pinned malicious versions, and known C2/Session-Protocol exfil traces. Orchestrates credential rotation in the correct order so revocation does not trigger the `rm -rf ~/` retaliation payload. Don't use for static SAST (Sentinel), skill/MCP/`.claude/` supply-chain audit (Chain), Sigma/YARA rule authoring (Vigil), or incident coordination (Triage).

選択肢(A/B/C)の深掘り比較→淘汰→推奨で判断負担を下げ判断の質を上げるスキル。5段階（L1固定3点/L1.5案拡張Diverge・自動/L2評価軸マトリクス/L3複数LLM弁証論/L4過去判断照合）。 「比較して」「深掘りして」「メリデメ教えて」「お勧めは？」「徹底的に」「過去の判断と照合」「前にどう決めたっけ」「/sentaku」等で発火。teian(浅)の深掘り要求を受け取り、brainstorming(深:設計全体)と棲み分け。

ガイド・教科書・チートシート・語彙帳・チュートリアル作成の最初の入り口（ディスパッチャ）。内容から「読む系（詳細ガイド）」「引く系（チートシート/語彙帳）」をLLMが判定し、確認後に guide-builder か textbook-guide に分岐。ユーザーは種別を覚えなくてよい。 「ガイド作って」「教科書作って」「チートシート作って」「語彙帳作って」「チュートリアル作って」「/make-guide」で発火。

SSOTへの記録・振り分けを自動化。内容をLLMが分析して**最適な保管場所を判定（01_DECISIONSはその一候補）**・フォーマット生成・リンク付与・ガイド転記まで一括実行。record-decision の上位互換。 「記録して」「保存して」「メモして」「SSOTに入れて」「ガイドに追加して」等で発火。「これ残して」「決定事項にして」「構想メモ」は構想モード。/ssot-record でも起動。

glm-rate-proxy（localhost:8787・CC CLIのGLM/MiniMaxバックエンドプロキシ）の診断・修復スキル。 プロキシが止まる・エラーが出る・MiniMaxフォールバック失敗等を診断し対処法を案内（ソース自動書き換えなし・確認後実行）。 「/proxy-doctor」「プロキシ直して」「GLMが使えない」「フォールバック失敗」「LLMエラー系（CLIが動かない・4xx/429多発）」等で発火。

Orchestrates AI agent teams with CrewAI, role-based agents, tasks, and sequential/parallel workflows.

Evaluates LLM performance using BLEU, ROUGE metrics and LLM-as-judge. Use for model testing.

Manages vector embeddings with Pinecone for semantic search, recommendation, and RAG pipelines.

Development with Cuda: tools and best practices

Run read-only deep repository analysis and return a ranked synthesis with explicit confidence, concrete file references, and clear evidence-vs-inference boundaries. Use when a user says 'analyze', 'investigate', 'why does', 'what's causing', or needs grounded cross-file explanation before any changes are proposed.

This skill should be used when the user wants to "package an MCP server", "bundle an MCP", "make an MCPB", "ship a local MCP server", "distribute a local MCP", discusses ".mcpb files", mentions bundling a Node or Python runtime with their MCP server, or needs an MCP server that interacts with the local filesystem, desktop apps, or OS and must be installable without the user having Node/Python set up.

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Agent skill for agent - invoke with $agent-agent

Agent skill for coder - invoke with $agent-coder

Agent skill for swarm - invoke with $agent-swarm

White-label AI chat interface built on HuggingFace Chat UI with OIDC auth, MCP tool integration, and branded assets

Agent skill for planner - invoke with $agent-planner

OpenAPI/Swagger documentation agent for creating and maintaining comprehensive API specifications with schemas, examples, and security definitions

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.

Agent skill for payments - invoke with $agent-payments

Agent skill for swarm-pr - invoke with $agent-swarm-pr

Agent skill for workflow - invoke with $agent-workflow

Agent skill for app-store - invoke with $agent-app-store

Byzantine fault-tolerant consensus and distributed coordination. Queen-led hierarchical swarm management with multiple consensus strategies. Use when: distributed coordination, fault-tolerant operations, multi-agent consensus, collective decision making. Skip when: single-agent tasks, simple operations, local-only work.

Agent skill for challenges - invoke with $agent-challenges

Per-group MCP JSON-RPC proxy routing AI tool calls to multiple backend MCP servers with tool group filtering

Agent skill for pseudocode - invoke with $agent-pseudocode

Agent skill for refinement - invoke with $agent-refinement

Agent skill for researcher - invoke with $agent-researcher