Knowledge
Knowledge from SiTaggart/.agents.
Skills in this plugin
11- ▌ Agents Md · sitaggartThis skill should be used when the user asks to "create AGENTS.md", "update AGENTS.md", "maintain agent docs", "set up CLAUDE.md", or needs to keep agent instructions concise. Guides discovery of local skills and enforces minimal documentation style.
- ▌ Chronicle · sitaggartAllows you to view the user's screen as well as several hours of history. Use when the user makes a reference to their recent work, for which it'd be helpful to see the screen. This skill MUST be used whenever you need to resolve ambiguity in a user request, where the user hasn't specified enough context to do the task. Examples include disambiguating the specific user/app/document/error the user is referring to. You must also use this skill if the user asks about any question regarding Chronicle or asks what you can see from the screen.
- ▌ Ce Handoff · sitaggartCompact the current conversation into a durable handoff document for another agent or future session. Use when the user asks to hand off, pause with context, summarize work for the next session, or prepare a continuation brief.
- ▌ Ce Compound · sitaggart bundleDocument a recently solved problem into .ai/solutions/ and, when domain terms surface, CONCEPTS.md — the project's shared domain vocabulary.
- ▌ Ce Sessions · sitaggart bundleSearch coding agent session history across Claude Code, Codex, Cursor, OpenCode, and Hermes. Use for past work, previous attempts, or prior investigations.
- ▌ Obsidian Vault · sitaggart bundleManage a local Obsidian vault from the command line using the Obsidian CLI. Use when the user wants to create, read, search, or organize notes, manage tasks, work with daily notes, handle properties/tags, or automate vault operations. Triggers on mentions of Obsidian, vault, notes, daily notes, or PKM workflows.
- ▌ Ce Improve Skills · sitaggartImprove agent guidance from evidence. Use for continual-improvement loops that patch skills, AGENTS.md, or CLAUDE.md from recurring corrections and verified session friction across local coding agents.
- ▌ Ce Slack Research · sitaggart bundleUse only when the user explicitly asks to search Slack or wants Slack discussions, decisions, or organizational context about a named topic.
- ▌ Qmd Knowledge Base · sitaggart bundlePreflight non-trivial tasks against this machine's indexed knowledge base (~12k markdown docs of wikis, specs, decisions, prior plans, and session retros) when prior decisions, product intent, ownership, conventions, expected behavior, or known failures could change the correct solution—even when the prompt does not request history. Skip only mechanical work fully defined by live source. Routes searches to relevant collections and classifies evidence authority; use the installed QMD surface for query mechanics.
- ▌ Ce Compound Refresh · sitaggart bundleRefresh stale .ai/solutions learnings against current code. Use for "refresh my learnings", audit stale learnings, or consolidate overlapping docs.
- ▌ Learnings Researcher · sitaggartSearch .ai/solutions/ for applicable past learnings via frontmatter metadata — bugs, architecture, design patterns, conventions, workflow lessons. Use before implementing features, making decisions, or starting work in a documented area so institutional knowledge carries forward.