Skill Tracer
Skills › Knowledge Work Plugins › update

update

skill · 168 lines · Apache-2.0 · productivity/skills/update/SKILL.md

The facts

Its 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.

The description the agent reads to decide when to use it.

From its settingsline 3

When it starts

The agent picks this skill when someone wants their task list and memory brought up to date — pulling new assignments from a project tracker into TASKS.md, triaging stale or overdue tasks, filling in context for unknown people or projects, or running a deeper scan of chat and email for todos that were never captured.

Things a person might say (the model's guesses)

  • “Sync my tasks from Linear into TASKS.md”
  • “My task list is stale — help me triage what's overdue”
  • “Scan my chat and email for anything I said I'd do but never tracked”

A model's summary of when it is used.

A model's reading

What it takes when started

[--comprehensive]

What to type after its name when you start it.

From its settingsline 4

What it leads to

  • requires start only if TASKS.md or memory/ is missing line 27

Other skills this one hands off to, calls, requires or offers instead, as a model read them.

A model's reading

What leads to it

Other skills that hand off to this one, call it, require it or offer it instead, as a model read them.

A model's reading

Licence

Apache-2.0, from productivity/LICENSE

The terms its author shares it under, which let it be shown here.

From the repositorylicence text

The text

Open on GitHub

Most marks come from matching words in the file, so treat them as pointers.

1---
2name: update
3description: 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.
4argument-hint: "[--comprehensive]"
5---
6
7# Update Command
8
9> If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](../../CONNECTORS.md).
11Keep your task list and memory current. Two modes:
13- **Default:** Sync tasks from external tools, triage stale items, check memory for gaps
14- **`--comprehensive`:** Deep scan chat, email, calendar, docs — flag missed todos and suggest new memories

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
Raw lines 1 to 15
16## Usage
18```bash
19/productivity:update
20/productivity:update --comprehensive
21```

Usage

/productivity:update
/productivity:update --comprehensive
Raw lines 16 to 22
23## Default Mode

Default Mode

Raw lines 23 to 24
25### 1. Load Current State
27Read `TASKS.md` and `memory/` directory. If they don't exist, suggest `/productivity:start` first.

1. Load Current State

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

Raw lines 25 to 28
Names a skill start :27
29### 2. Sync Tasks from External Sources
31Check for available task sources:
32- **Project tracker** (e.g. Asana, Linear, Jira) (if MCP available)
33- **GitHub Issues** (if in a repo): `gh issue list --assignee=@me`
35If no sources are available, skip to Step 3.
37**Fetch tasks assigned to the user** (open/in-progress). Compare against TASKS.md:
39| External task | TASKS.md match? | Action |
40|---------------|-----------------|--------|
41| Found, not in TASKS.md | No match | Offer to add |
42| Found, already in TASKS.md | Match by title (fuzzy) | Skip |
43| In TASKS.md, not in external | No match | Flag as potentially stale |
44| Completed externally | In Active section | Offer to mark done |
46Present diff and let user decide what to add/complete.

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.

Raw lines 29 to 47
Uses an outside tool MCP :32
48### 3. Triage Stale Items
50Review Active tasks in TASKS.md and flag:
51- Tasks with due dates in the past
52- Tasks in Active for 30+ days
53- Tasks with no context (no person, no project)
55Present each for triage: Mark done? Reschedule? Move to Someday?

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?

Raw lines 48 to 56
57### 4. Decode Tasks for Memory Gaps
59For each task, attempt to decode all entities (people, projects, acronyms, tools, links):
61```
62Task: "Send PSR to Todd re: Phoenix blockers"
64Decode:
65- PSR → ✓ Pipeline Status Report (in glossary)
66- Todd → ✓ Todd Martinez (in people/)
67- Phoenix → ? Not in memory
68```
70Track what's fully decoded vs. what has gaps.

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.

Raw lines 57 to 71
72### 5. Fill Gaps
74Present unknown terms grouped:
75```
76I found terms in your tasks I don't have context for:
781. "Phoenix" (from: "Send PSR to Todd re: Phoenix blockers")
79 → What's Phoenix?
812. "Maya" (from: "sync with Maya on API design")
82 → Who is Maya?
83```
85Add answers to the appropriate memory files (people/, projects/, glossary.md).

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).

Raw lines 72 to 86
87### 6. Capture Enrichment
89Tasks often contain richer context than memory. Extract and update:
90- **Links** from tasks → add to project/people files
91- **Status changes** ("launch done") → update project status, demote from CLAUDE.md
92- **Relationships** ("Todd's sign-off on Maya's proposal") → cross-reference people
93- **Deadlines** → add to project files

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
Raw lines 87 to 94
Project instruction file CLAUDE.md :91
95### 7. Report
97```
98Update complete:
99- Tasks: +3 from project tracker (e.g. Asana), 1 completed, 2 triaged
100- Memory: 2 gaps filled, 1 project enriched
101- All tasks decoded ✓
102```

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 ✓
Raw lines 95 to 103
104## Comprehensive Mode (`--comprehensive`)
106Everything in Default Mode, plus a deep scan of recent activity.

Comprehensive Mode (--comprehensive)

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

Raw lines 104 to 107
108### Extra Step: Scan Activity Sources
110Gather data from available MCP sources:
111- **Chat:** Search recent messages, read active channels
112- **Email:** Search sent messages
113- **Documents:** List recently touched docs
114- **Calendar:** List recent + upcoming events

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
Raw lines 108 to 115
Uses an outside tool MCP :110
116### Extra Step: Flag Missed Todos
118Compare activity against TASKS.md. Surface action items that aren't tracked:
120```
121## Possible Missing Tasks
123From your activity, these look like todos you haven't captured:
1251. From chat (Jan 18):
126 "I'll send the updated mockups by Friday"
127 → Add to TASKS.md?
1292. From meeting "Phoenix Standup" (Jan 17):
130 You have a recurring meeting but no Phoenix tasks active
131 → Anything needed here?
1333. From email (Jan 16):
134 "I'll review the API spec this week"
135 → Add to TASKS.md?
136```
138Let user pick which to add.

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.

Raw lines 116 to 139
140### Extra Step: Suggest New Memories
142Surface new entities not in memory:
144```
145## New People (not in memory)
146| Name | Frequency | Context |
147|------|-----------|---------|
148| Maya Rodriguez | 12 mentions | design, UI reviews |
149| Alex K | 8 mentions | DMs about API |
151## New Projects/Topics
152| Name | Frequency | Context |
153|------|-----------|---------|
154| Starlight | 15 mentions | planning docs, product |
156## Suggested Cleanup
157- **Horizon project** — No mentions in 30 days. Mark completed?
158```
160Present grouped by confidence. High-confidence items offered to add directly; low-confidence items asked about.

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.

Raw lines 140 to 161
162## Notes
164- Never auto-add tasks or memories without user confirmation
165- External source links are preserved when available
166- Fuzzy matching on task titles handles minor wording differences
167- Safe to run frequently — only updates when there's new info
168- `--comprehensive` always runs interactively

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
Raw lines 162 to 168

From anthropics/knowledge-work-plugins at 2574e29, 2026-10-27. Skills read by DeepSeek V4.1 Flash on 2026-11-04. Summary and techniques by Claude Opus 5.5 on 2026-11-06.