Calendar queries, schedule questions, meeting history, task queries, people profiles, initiative status, and organizational context. Handles "When did I meet X?", "What's my schedule?", "Am I free?", "What do I know about X?" Fast lookups with index-first pattern.
Searches memory, tasks, calendar, and journal to answer questions about schedule, people, meetings, and organizational context.
npx claudepluginhub ajayjohn/tars-work-assistantThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Defines how to search across information sources for answering queries, analysis, or communication.
| Priority | Source | Contains |
|---|---|---|
| 1 (first) | Memory (memory/) | Quick facts, relationships, decisions |
| 2 | Tasks (via task integration) | Action items, deadlines, assignments |
| 3 | Journal (journal/) | Meeting summaries, briefings |
| 4 | Contexts (contexts/) | Deep reference material, full docs |
| 5 | MCP tools | project tracker, documentation, additional integrations |
| 6 (last) | Web | External, current information |
Every search reads an _index.md BEFORE opening individual files. This is the most important scalability rule.
memory/_index.md routes to the correct subfoldermemory/{category}/_index.md maps aliases to filenamesjournal/YYYY-MM/_index.md lists entries by date, type, participants, initiativesNever scan all files in a folder. Always use the index.
People, initiatives, products, vendors, competitors, past decisions.
What needs to be done, deadlines, assignments, follow-ups.
Recent discussions, who said what, decisions from meetings, prior briefings.
_index.md_index.md files firstmemory/decisions/ firstDeep detail beyond memory: full product docs, schemas, org charts, specs.
Priority flow:
<mcp_servers> context for calendar MCP server (preferred)list_events, get_event, create_event)reference/integrations.md for legacy providerAlways resolve dates to YYYY-MM-DD before querying.
Priority flow:
<mcp_servers> context for reminders/tasks MCP server (preferred)list_reminders, create_reminder, complete_reminder)reference/integrations.md for legacy providerMarket information, competitor news, regulatory updates, current events. External only.
Identify:
Entities may have alternate names. Check _index.md alias columns.
_index.md to find target file[[Entity]] wikilinks for related contextExecute the task integration list operation for configured lists (default: Active, Delegated, Backlog). Filter by owner (from notes field), due date, or initiative.
journal/YYYY-MM/_index.md for recent monthsLook in contexts/ for full documentation, product specs, schemas.
When using information from searches, cite the source:
[From memory/people/jane-smith.md]
Jane prefers data-driven summaries and email over Slack.
[From journal/2026-01/2026-01-18-planning-session.md]
Discussed moving the deadline to end of February.
For fast factual lookups:
Start with the calendar integration FIRST. Read reference/integrations.md Calendar section for provider details, resolve the target date to YYYY-MM-DD format, then execute the list_events operation. TARS has calendar access via configured integration. Never respond that calendar access is unavailable without checking integration status. If the calendar integration is unreachable, state the specific connection error. Then check memory for people context, then task integration for related tasks.
Follow standard hierarchy: memory -> tasks -> journal -> contexts -> MCP -> web.
After searching, apply clarification protocol if critical context is still missing.
_index.md + up to 5 targeted files_index.md + up to 3 entrieslist operation for Active only (unless other lists explicitly needed)When answering, tag each piece of information with its confidence tier:
| Source | Confidence |
|---|---|
| Memory files, user input | High |
| Native tools (calendar, tasks) | High |
| MCP tools (project tracker, docs) | Medium-High |
| Web search | Medium-Low |
| LLM knowledge (no source) | Low -- flag explicitly |
Universal constraints from the core skill apply (date resolution, index-first pattern, integration constraints). Additionally:
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill automatically when working in Next.js projects that have `cacheComponents: true` in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best practices to all React Server Component implementations. **DETECTION**: At the start of a session in a Next.js project, check for `cacheComponents: true` in next.config. If enabled, this skill's patterns should guide all component authoring, data fetching, and caching decisions. **USE CASES**: Implementing 'use cache' directive, configuring cache lifetimes with cacheLife(), tagging cached data with cacheTag(), invalidating caches with updateTag()/revalidateTag(), optimizing static vs dynamic content boundaries, debugging cache issues, and reviewing Cache Component implementations.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.