Skill Claude CodeCodex
Author figures in Quarto documents using the quarto-livefigures extension — editable, version-controlled figure sources (Excalidraw, Vega-Lite, Graphviz, PlantUML, and 14 more) rendered at build time. Use when creating or editing diagrams, charts, schemas, or timing figures in a Quarto project, when the user asks for…
Skill Claude CodeCodex
Vault hygiene meta-skill. Scans / for decay: stale goals.md, dormant now.md, projects with no recent activity, broken wiki-links, orphan notes, decisions without revisit dates, stale people records, zombie inbox items. Outputs a vault health score, top fixes, and offers low-risk auto-fixes with confirmation. Use when…
Skill Claude CodeCodex
Scheduled revisit of decisions whose Review Date has passed. Reads /decisions/, filters to open decisions with overdue or due-today review dates, walks through each one comparing prediction vs reality, appends a revisit entry, and updates status. Use when user says 'revisit decisions', '/decide-revisit', or monthly on…
Skill Claude CodeCodex
Capture a decision prospectively in Patrick Collison / Farnam Street format. Writes to /decisions/YYYY-MM-DD-slug.md with context, alternatives, prediction, confidence, key factors, emotional state, and a revisit date. Forces articulation before action. Use when user says 'decide', '/decide', 'capture this decision'…
Skill Claude CodeCodex
Closing ritual for the daily journal. Reads today's journal, lifts completed items to completed.md with strategic context, prompts for atomic notes / decisions captured during the day, asks Franklin's evening question, optionally prompts a diary entry, carries forward incomplete items to tomorrow. Use when user says…
Skill Claude CodeCodex
First-run personalization for a freshly-cloned LifeOS vault. Asks for the user's name, vault root path, timezone, and tool preferences (email scanner, etc.), then substitutes throughout all skill files + CLAUDE.md. Optionally walks the user through writing their first plan.md / values.md. Idempotent — safe to re-run.…
Skill Claude CodeCodex
Generate meeting prep briefs for upcoming calendar events. For each meeting, pulls people/[name].md, recent journal mentions, open inbox items touching the person, open decisions, and last commitments. Outputs a per-meeting brief: 3 things to know, 3 questions to ask, 1 risk, last commitments. Use when user says…
Skill Claude CodeCodex
Daily journaling, reflection, and planning. Use when the user says 'morning', 'let's plan the day', 'journal', or similar. Loads calendar + email scan, reviews yesterday, checks emotional state, runs inbox hygiene, creates today's journal, offers an honest reality check, sets 1-3 priorities that ladder up to annual…
Skill Claude CodeCodex
Playbook for operating this Obsidian vault via the obsidian CLI when it's installed — link resolution, graph hygiene (backlinks / orphans / unresolved), task reconciliation across files, frontmatter/tag/property queries, full-text search, version history. Use when doing substantial work over the vault's link graph…
Skill Claude CodeCodex
A 5-minute guided tour of the LifeOS vault. Walks the user through the 5-layer architecture (Foundation, Knowledge, Connections, Execution, Feedback), names the files and skills in each layer, and shows what to do tomorrow morning to start the daily rhythm. Use when user says 'orient', '/orient', 'tour', 'how does…
Skill Claude CodeCodex
Generates a structured progress report across projects, people, and time. Parses the journal and completed.md for effort and milestones, grouping by grant, project, and person. Use when the user asks for a 'progress report', 'effort accounting', or asks 'what did I accomplish on project X'.
Skill Claude CodeCodex
Heavy strategic review, run quarterly. Reads plan.md (10-year), goals.md (annual), last 90 days of journals + completed.md + decisions + weekly reviews, surfaces themes and patterns, forces a goals.md rewrite if conditions have changed, sets next quarter's 3 priorities, optionally updates plan.md. Use when user says…
Skill Claude CodeCodex
Weekly review of the life-OS vault. Reads the past 7 days of journal entries, inbox.md, now.md, goals.md, completed.md, decisions/, calendar, and GitHub state; surfaces what got done, what's stuck, what's drifting; updates now.md; flags inbox staleness and goals.md decay; drafts week-WW.md; forces one decision via…
Instructions file
Claude Code instructions for seandavi/lifeos-template, covering claude.md — operating manifest for this vault, preferences, philosophy, co-thinking mode and file layout.
MCP server Claude CodeCodexCursor +2
MCP server "ols-mcp-server" as configured in seandavi/ols-mcp-server. Runs locally from the ols-mcp-server Python package.
Instructions file
Claude Code instructions for seandavi/biomedical-agent-kg, covering claude.md, what this is, running, core invariant — fix the generator, never the record and architecture.
Agent
Agent Hospital is a multi-agent, self-evolving system built by [[org:wisdom-pan]] that simulates a complete clinical environment. By utilizing LLMs as autonomous agents, the system models the interactions between patients, nurses, and doctors to facilitate the treatment process. The platform exposes both a cli and a…
Agent
Agent Laboratory is an autonomous research workflow designed to assist human researchers by automating repetitive tasks such as literature reviews, experiment execution, and report writing. Built by [[org:samuelschmidgall]], the system utilizes a multiagent architecture to facilitate collaboration across the research…
Agent
The AI co-scientist is a multi-agent, self-evolving system built by [[org:the-swarm-corporation]] to augment the process of [[domain:scientificdiscovery]]. By utilizing a generate, debate, and evolve methodology, the system assists researchers in formulating novel hypotheses and research proposals. It is available as…
Agent
AI-Researcher is an autonomous system built by [[org:hkuds]] designed to facilitate [[domain:scientificdiscovery]]. Utilizing a multiagent architecture, the platform provides end-to-end research automation, supporting workflows that range from detailed idea development to reference-based ideation. The system is…
Agent
AIPatient is a simulated patient system designed to support medical education and clinical decision-making through an LLM-powered multi-agent architecture. By integrating a rag framework with six task-specific agents, the system replicates high-fidelity doctor-patient interactions and complex medical reasoning. It is…
Agent
Alhazen is a biomedical LLM-agent system designed to facilitate advancements in [[domain:scientificdiscovery]]. By leveraging automated reasoning and data synthesis, the system assists researchers in navigating complex biological datasets.
Agent
Almanac Copilot is a singleagent system designed to assist clinicians with electronic medical record navigation, including information retrieval and order placement. By automating routine documentation tasks, the agent aims to reduce clinician burnout and improve the efficiency of clinical workflows.
Agent
Apex Metabolic AI Lab is a specialized biomedical system designed to address complex challenges in metabolic research. It focuses on synthesizing high-dimensional biological data to support advanced analytical workflows.