PluginBench
Skill
Official
Pass
Audit score 90

update

anthropics/knowledge-work-plugins

Sync tasks and refresh memory from your current activity.

What is update?

The update command keeps your task list and memory current by syncing external task sources, triaging stale items, and filling memory gaps. Use it when pulling new assignments into TASKS.md, checking for overdue tasks, or running a comprehensive scan to catch buried todos and suggest new memories.

  • Sync tasks from external sources like project trackers and GitHub Issues
  • Triage stale or overdue tasks in TASKS.md
  • Decode task entities and identify memory gaps for people, projects, and acronyms
  • Fill memory gaps by prompting for context on unknown terms
  • Extract and enrich memory with links, status changes, and relationships from tasks
  • Deep scan chat, email, calendar, and documents in comprehensive mode to flag missed todos

How to install update

npx skills add https://github.com/anthropics/knowledge-work-plugins --skill update
Prerequisites
  • TASKS.md and memory/ directory should exist (or run /productivity:start first)
  • Optional: MCP connectors configured for project trackers, chat, email, calendar, or documents
Claude Code
Cursor
Windsurf
Cline

How to use update

  1. 1.Run /productivity:update to sync tasks and triage stale items
  2. 2.Review the diff of new tasks from external sources and confirm additions
  3. 3.Address flagged stale tasks by marking done, rescheduling, or moving to Someday
  4. 4.Answer prompts for memory gaps (unknown people, projects, acronyms)
  5. 5.Run /productivity:update --comprehensive for a deep scan of recent activity and missed todos
  6. 6.Review suggested new people and projects, then confirm which to add to memory

Use cases

Good for
  • Pull new assignments from Asana, Linear, or Jira into your task list
  • Review and reschedule tasks that have been in Active for 30+ days
  • Identify unfamiliar people or projects mentioned in tasks and add them to memory
  • Run a comprehensive scan to surface action items buried in chat and email
  • Update project status and cross-reference relationships between people and projects
Who it's for
  • Knowledge workers managing multiple projects and task sources
  • Teams using external project trackers like Asana, Linear, or Jira
  • Users maintaining memory files for people, projects, and glossaries
  • Anyone needing to keep task lists and context synchronized

update FAQ

What happens if I don't have external task sources connected?

The command skips the sync step and proceeds to triage stale items in TASKS.md and fill memory gaps from your existing tasks.

Will the update command automatically add tasks or memories?

No. The command always presents diffs and suggestions for user confirmation before making changes.

How does fuzzy matching work for task titles?

The command compares task titles between TASKS.md and external sources to detect matches even if wording differs slightly, avoiding duplicates.

What's the difference between default and comprehensive mode?

Default mode syncs tasks and triages stale items. Comprehensive mode adds a deep scan of chat, email, calendar, and documents to surface missed todos and suggest new memories.

How often should I run this command?

Safe to run frequently. It only updates when there's new information, so running it daily or weekly helps keep tasks and memory synchronized.

Full instructions (SKILL.md)

Source of truth, from anthropics/knowledge-work-plugins.


name: update description: Sync tasks and refresh memory from your current activity. Use when pulling new assignments from your project tracker into TASKS.md, triaging stale or overdue tasks, filling memory gaps for unknown people or projects, or running a comprehensive scan to catch todos buried in chat and email. argument-hint: "[--comprehensive]"

Update Command

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.

Keep your task list and memory current. Two modes:

  • Default: Sync tasks from external tools, triage stale items, check memory for gaps
  • --comprehensive: Deep scan chat, email, calendar, docs — flag missed todos and suggest new memories

Usage

/productivity:update
/productivity:update --comprehensive

Default Mode

1. Load Current State

Read TASKS.md and memory/ directory. If they don't exist, suggest /productivity:start first.

2. Sync Tasks from External Sources

Check for available task sources:

  • Project tracker (e.g. Asana, Linear, Jira) (if MCP available)
  • GitHub Issues (if in a repo): gh issue list --assignee=@me

If no sources are available, skip to Step 3.

Fetch tasks assigned to the user (open/in-progress). Compare against TASKS.md:

External taskTASKS.md match?Action
Found, not in TASKS.mdNo matchOffer to add
Found, already in TASKS.mdMatch by title (fuzzy)Skip
In TASKS.md, not in externalNo matchFlag as potentially stale
Completed externallyIn Active sectionOffer to mark done

Present diff and let user decide what to add/complete.

3. Triage Stale Items

Review Active tasks in TASKS.md and flag:

  • Tasks with due dates in the past
  • Tasks in Active for 30+ days
  • Tasks with no context (no person, no project)

Present each for triage: Mark done? Reschedule? Move to Someday?

4. Decode Tasks for Memory Gaps

For each task, attempt to decode all entities (people, projects, acronyms, tools, links):

Task: "Send PSR to Todd re: Phoenix blockers"

Decode:
- PSR → ✓ Pipeline Status Report (in glossary)
- Todd → ✓ Todd Martinez (in people/)
- Phoenix → ? Not in memory

Track what's fully decoded vs. what has gaps.

5. Fill Gaps

Present unknown terms grouped:

I found terms in your tasks I don't have context for:

1. "Phoenix" (from: "Send PSR to Todd re: Phoenix blockers")
   → What's Phoenix?

2. "Maya" (from: "sync with Maya on API design")
   → Who is Maya?

Add answers to the appropriate memory files (people/, projects/, glossary.md).

6. Capture Enrichment

Tasks often contain richer context than memory. Extract and update:

  • Links from tasks → add to project/people files
  • Status changes ("launch done") → update project status, demote from CLAUDE.md
  • Relationships ("Todd's sign-off on Maya's proposal") → cross-reference people
  • Deadlines → add to project files

7. Report

Update complete:
- Tasks: +3 from project tracker (e.g. Asana), 1 completed, 2 triaged
- Memory: 2 gaps filled, 1 project enriched
- All tasks decoded ✓

Comprehensive Mode (--comprehensive)

Everything in Default Mode, plus a deep scan of recent activity.

Extra Step: Scan Activity Sources

Gather data from available MCP sources:

  • Chat: Search recent messages, read active channels
  • Email: Search sent messages
  • Documents: List recently touched docs
  • Calendar: List recent + upcoming events

Extra Step: Flag Missed Todos

Compare activity against TASKS.md. Surface action items that aren't tracked:

## Possible Missing Tasks

From your activity, these look like todos you haven't captured:

1. From chat (Jan 18):
   "I'll send the updated mockups by Friday"
   → Add to TASKS.md?

2. From meeting "Phoenix Standup" (Jan 17):
   You have a recurring meeting but no Phoenix tasks active
   → Anything needed here?

3. From email (Jan 16):
   "I'll review the API spec this week"
   → Add to TASKS.md?

Let user pick which to add.

Extra Step: Suggest New Memories

Surface new entities not in memory:

## New People (not in memory)
| Name | Frequency | Context |
|------|-----------|---------|
| Maya Rodriguez | 12 mentions | design, UI reviews |
| Alex K | 8 mentions | DMs about API |

## New Projects/Topics
| Name | Frequency | Context |
|------|-----------|---------|
| Starlight | 15 mentions | planning docs, product |

## Suggested Cleanup
- **Horizon project** — No mentions in 30 days. Mark completed?

Present grouped by confidence. High-confidence items offered to add directly; low-confidence items asked about.

Notes

  • Never auto-add tasks or memories without user confirmation
  • External source links are preserved when available
  • Fuzzy matching on task titles handles minor wording differences
  • Safe to run frequently — only updates when there's new info
  • --comprehensive always runs interactively