菜单
Search past agent conversations to recall prior discussions, decisions, and context. Activate this skill when users ask about previous conversations, want to resume past work, or reference earlier decisions.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Create and edit Obsidian Canvas (.canvas) files — text/file/link/group nodes and the edges between them, using the JSON Canvas spec. Activate this skill when users want to build a canvas, mind map, flowchart, or visual board of notes.
Create and configure Obsidian Bases — database-like views of notes. Activate this skill when users want to create bases, write filters, formulas, or set up table/cards/list/map views.
Write and edit Obsidian Flavored Markdown — wikilinks, embeds, callouts, block references, tags, comments, highlights, and math. Activate this skill when users want to link notes, embed content, add callouts, or use Obsidian-specific Markdown syntax.
Run the eval harness against a real Obsidian instance, monitor for the harness's known reliability gotchas (concurrent runs, CLI-bridge hangs, stale child processes), and bless a result as a baseline only when the run is clean. Use when the user asks to "run the evals", "bless a baseline", "measure the impact of <change> on solve rate", "run a model sweep", or similar. Has Obsidian-CLI side effects (drives the agent view, creates eval-scratch fixtures, may set chatModelName for the duration of the run); does NOT modify plugin source code or commit unless explicitly asked.
Use this skill whenever the user asks for a Quill Shipping Company tracking code or shipping reference. It defines the exact, non-obvious format every tracking code must follow.
Answer questions about Gemini Scribe plugin features, settings, and usage, and diagnose plugin errors by reading the user's debug.log (when File Logging is enabled). Activate this skill whenever the user asks how to use the plugin or configure settings, OR reports that something went wrong with the plugin — bug, error, crash, broken behavior, "not working", "what just happened" — especially when they mention the debug log, log file, console output, or want help troubleshooting. Always activate this skill before searching the vault for plugin log files; debug.log lives in the plugin state folder which the standard read_file tool blocks.
| name | recall-sessions |
| description | Search past agent conversations to recall prior discussions, decisions, and context. Activate this skill when users ask about previous conversations, want to resume past work, or reference earlier decisions. |
Find and retrieve past agent conversations using the recall_sessions tool. This enables recalling prior discussions, decisions, and context from earlier sessions.
Use this skill when the user:
Call the recall_sessions tool with these parameters:
query (optional) — Search term to match against session titles (case-insensitive substring match).filePath (optional) — Find sessions that accessed a specific file (e.g., notes/meeting.md).project (optional) — Find sessions linked to a specific project name.limit (optional) — Maximum results to return. Default is 10, maximum is 50.At least one of query, filePath, or project should be provided for meaningful results.
query when the user asks about a discussion topic: recall_sessions(query="refactoring")filePath when the user references a specific file: recall_sessions(filePath="projects/website-redesign.md")project when the user mentions a project: recall_sessions(project="website-redesign")recall_sessions(query="API design", project="backend")The tool returns session summaries only — title, date, files accessed, project linkage, and a historyPath.
To see the full conversation from a past session, use read_file on the returned historyPath. This two-step approach avoids loading unnecessary conversation data.
recall_sessions to find relevant sessionsread_file on the historyPath of the session(s) the user is interested inquery or search by the files currently in context using filePath.