メニュー
Chain web research, atomic extraction, and durable knowledge capture into a repeatable workflow when the same research-to-notes sequence is needed.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
Spec-Driven Development (SDD) methodology for AI software factories — where structured specifications are the input, AI agents generate the code, and quality gates enforce correctness at each pipeline phase. Use when designing a spec → review → decompose → implement → verify pipeline that any AI coding tool (Claude Code, Cursor, Hermes Agent, Devin, OpenHands) can follow.
Query your Jellyfin media server from the terminal — recently added media, search, item details, next-up episodes, library browsing, server info, and stats. Use when the user asks about Jellyfin, media server, movies, TV shows, next episodes, or their media library.
Multi-agent structured debate system. Spawn a panel of expert agents to debate any question, with convergence-aware iteration and typed synthesis output. Run via `agent-council` CLI. Compatible with any AI agent harness that supports agentskills.io skills (Claude Code, Cursor, Hermes Agent, OpenHands, etc.).
Reference for the Agent Skills open format — the directory structure, SKILL.md frontmatter schema, naming conventions, progressive disclosure model, and best practices for creating skills. Use this whenever creating, reviewing, or editing skills in this repository to ensure they follow the standard spec.
Verify work against explicit criteria using evidence, reproducible checks, and clear pass, conditional, or blocked verdicts. Use before declaring an artifact, implementation, or claim complete.
Manage Linear teams, projects, cycles, issues, comments, workflow state, and documents from a terminal through Linear's public GraphQL API. Use when a user asks to list, search, inspect, create, update, move, or comment on Linear work, or to find Linear documents. Do not use to embed a live agent inside Linear or to build an MCP integration.
SOC 職業分類に基づく
| name | research-and-vault |
| description | Chain web research, atomic extraction, and durable knowledge capture into a repeatable workflow when the same research-to-notes sequence is needed. |
Load this skill when the task requires the full research-to-note sequence.
Use this thin orchestrator when a task needs the same sequence repeatedly:
This skill composes existing capabilities; it does not duplicate their methodology. If the task is a single lookup or a single note, load the domain skill directly instead.
