core
Identity, routing, communication style, memory protocol, task protocol, decision frameworks, and clarification for TARS
npx skills add majiayu000/claude-skill-registry --skill core-ajayjohn-tars-work-assistant-2 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Defines TARS as the strategic intelligence layer with identity, routing rules, communication style, memory protocol, task protocol, and decision frameworks. Establishes integrations via MCP servers for calendar and task data, and sets proactive learning triggers and truth-source priorities. Outlines a comprehensive routing table and automation side-effects that occur when certain signals are detected. Also specifies session housekeeping and memory coordination rules.
How it works
Describes the agent’s role as TARS and how to route requests through an intelligent router using signals and a routing table. Lists triggers (e.g., meeting transcripts, memory updates, task extraction) and the target skill paths (e.g., skills/meeting/, skills/tasks/, skills/learn/, etc.). Specifies that identity and memory are maintained in memory and under memory protocols with priorities that favor user input, session context, memory files, integrations, then clarification. Proactively suggests memory persistence when triggers occur, and defines how session-start gate performs housekeeping with version checks, staleness evaluation, and daily scripts (archive, health-check, sync). Details the exact scripts to run for daily maintenance and how notifications (P0, P1, P2) are delivered. Outlines the COOP rules for memory, journal, and task writes, and the workflow to keep references up to date via a plugin system.
When to use it
Uses are implicit in its role as the foundational framework loaded every session. It triggers routing to the appropriate specialized skills based on signals such as: meeting processing, memory updates, task extraction, and briefing needs. It also initiates maintenance routines at session start according to the housekeeping rules if conditions indicate staleness or outdated references.
What it can touch
Mentions integrations with MCP servers for calendar and task data (read/write via MCP server preferred), and legacy providers. Interacts with memory files, _index.md references, and reference/integrations markdown as configurations. Mentions the following tool paths: skills/meeting/, skills/tasks/, skills/learn/, skills/communicate/, skills/think/, skills/briefing/, skills/initiative/, scripts/archive.py, scripts/health-check.py, scripts/sync.py, and python3 scripts.
Caveats
No explicit licensing or usage caveats beyond maintenance and upgrade procedures are described in this summary. It states that MCP v2.1 is preferred for reliability, and that updates may modify reference files automatically with a fallback notification if failures occur. It emphasizes not persisting memory changes without confirmation in some learning scenarios and outlines cautious update behavior during plugin/version changes.
<!-- MAINTENANCE: If modifying this skill, run tests/validate-docs.py to check for broken cross-references. See CONTRIBUTING.md. --> # Core framework ## Identity ### Role You are the strategic intelligence layer for the user. You operate as TARS, a trusted advisor who combines deep organizational context with rigorous analytical capability. ### Integrations TARS uses MCP (Model Context Protocol) servers for calendar and task integrations (v2.1+). Legacy HTTP/CLI integrations (v2.0) remain supported during transition. **Calendar integration** -- Read/write access via MCP server (preferred) or legacy provider. Check `<mcp_servers>` context first, then `reference/integrations.md` for legacy config. Use for schedule, agenda, meetings, availability queries. Always resolve dates to YYYY-MM-DD before querying. **Task integration** -- Read/write access via MCP server (preferred) or legacy provider. Check `<mcp_servers>` context first, then `reference/integrations.md` for legacy config. Use for all task creation, editing, completion, and queries. **Optional integrations** -- Project tracker, documentation, and other MCP servers enhance functionality but are not required. **Migration note**:
- Identity
- Role
- Integrations
- User profile
- Organization
- Truth source priority
- Proactive learning triggers
- TARS invocation
- Routing
- Intelligent router
- Signal table
- Routing rules
- File map
- Automatic housekeeping
Archive expired content
python3 scripts/archive.py {workspace_path} --auto
Health check (index validation, broken wikilinks, naming issues)
python3 scripts/health-check.py {workspace_path}
Sync scheduled items and detect memory gaps
python3 scripts/sync.py {workspace_path}What does the core skill do?
Identity, routing, communication style, memory protocol, task protocol, decision frameworks, and clarification for TARS
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill core-ajayjohn-tars-work-assistant-2 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.