spark-recipe-team-workload — Claude Code skill: team workload audit
Walks through a Spark team and shows who carries how much, what you delegated, and which work sits without an owner.
npx skills add readdle/spark-cli-skills --skill spark-recipe-team-workload -a claude-code
npx skills add readdle/spark-cli-skills --skill recipe-team-workload -a claude-codeWhat spark-recipe-team-workload does
The skill audits how work is spread across a team. It starts with a team overview to grab the member list and shared inboxes, then pulls assignments per person with spark emails --filter "assigned_to:...". Two more passes cover what you assigned yourself (assigned_by:me) and what nobody owns (assigned_to:unassigned).
It also compares open and done items in shared inboxes. That ratio tells you whether the team keeps up with incoming mail. The report lists counts per member, stale assignments, workload outliers, and the number of unowned items.
Access is read-only, so nothing in your mail changes. The skill needs the use-spark base skill for command reference and filter syntax. The author suggests running it weekly to catch imbalances early, and on large teams focusing on outliers instead of writing up every member.
What it helps with
- spot who on the team carries far more assignments than the rest
- find assignments that have been sitting untouched for a week or more
- count work with no owner across shared inboxes
- check which items you delegated are still open
- judge whether the team keeps up from the open-to-done ratio
Example prompts for the agent
- show the workload for the Support team this week
- find unassigned emails in the [email protected] inbox
- what did I delegate that is still open
How to install spark-recipe-team-workload
1Skills CLI (Vercel)
npx skills add readdle/spark-cli-skills --skill spark-recipe-team-workload -a claude-codenpx skills add readdle/spark-cli-skills --skill recipe-team-workload -a claude-code2Manually: put the files in place
~/.claude/skills/recipe-team-workload/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/recipe-team-workload/
1Skills CLI (Vercel)
npx skills add readdle/spark-cli-skills --skill recipe-team-workload -a codex2Manually: put the files in place
.agents/skills/recipe-team-workload/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add readdle/spark-cli-skills --skill recipe-team-workload -a cursor2Manually: put the files in place
.cursor/skills/recipe-team-workload/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install readdle/spark-cli-skills recipe-team-workload2Manually: put the files in place
.github/skills/recipe-team-workload/SKILL.md1Skills CLI (Vercel)
npx skills add readdle/spark-cli-skills --skill recipe-team-workload -a gemini-cli2Platform CLI
gemini skills install https://github.com/readdle/spark-cli-skills --path skills/recipe-team-workloadManually: put the files in place
.devin/skills/recipe-team-workload/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add readdle/spark-cli-skills --skill recipe-team-workload -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about spark-recipe-team-workload
How do I install spark-recipe-team-workload in Claude?
Run npx skills add readdle/spark-cli-skills --skill spark-recipe-team-workload -a claude-code. The skill lands in ~/.claude/skills/recipe-team-workload/SKILL.md.
What does spark-recipe-team-workload do?
It audits how work is distributed across a team: per-member load, items you delegated, unassigned work, and imbalances. It finishes with a summary report.
What does the skill need to run?
The use-spark base skill, which holds the command reference and filter syntax. Access level is read-only, so the skill only reads data.
Source text
SKILL.md · MIT
---
name: spark-recipe-team-workload
description: >-
Audit team assignment distribution: per-member loads, delegated items,
unassigned work, and workload imbalances.
metadata:
version: 1.0.0
requires:
skills:
- use-spark
accessLevel: read-only
---
# Recipe: Team Workload
Deep audit of how work is distributed across a team. Surfaces per-member assignment loads, items you've delegated, unassigned work, and imbalances.
**Prerequisite:** Read the `use-spark` base skill for command reference and filter syntax.
**Access level required:** read-only.
## Steps
### Step 1: Get the team overview
```bash
spark team "Team Name"
```
Note the member list, shared inboxes, and the assignment summary. This gives you the high-level distribution.
### Step 2: Review per-member assignments
For each team member, pull their current assignments:
```bash
spark emails --filter "assigned_to:[email protected]"
spark emails --filter "assigned_to:[email protected]"
spark emails --filter "assigned_to:[email protected]"
```
Note the count and scan subjects/dates to spot stale items (old assignments that may be stuck).
### Step 3: Check what you've delegated
```bash
spark emails --filter "assigned_by:me"
```
These are items you assigned to others. Cross-reference with per-member lists to see which are still open.
### Step 4: Find unassigned work
```bash
spark emails --filter "assigned_to:unassigned"
```
If the team uses shared inboxes, also check each one:
```bash
spark emails [email protected]:Inbox --filter "assigned_to:unassigned"
```
### Step 5: Check open vs. done in shared inboxes
```bash
spark emails --filter "is:shared_inbox_open"
spark emails --filter "is:shared_inbox_done"
```
The ratio of open to done gives a sense of whether the team is keeping up.
### Step 6: Present the workload report
Summarize:
- **Per member:** assignment count and any notably old items
- **Imbalances:** flag members with significantly more or fewer assignments than average
- **Delegated by you:** N items still open, any that look overdue
- **Unassigned:** M items with no owner
- **Throughput:** open vs. done ratio across shared inboxes
## Tips
- Run this weekly to catch imbalances before they become problems.
- The `team` command's assignment summary is a quick snapshot; the per-member `emails` queries give the full picture.
- Stale assignments (older than 7-14 days) are worth flagging - they may be stuck or forgotten.
- `assigned_by:me` is useful for managers and leads who delegate frequently.
- Compare this week's numbers to last week's (if you track them) to spot trends.
- Combine with `recipe-shared-inbox-status` for a shared-inbox-focused view, or use this recipe for the broader team picture.
- For large teams, focus on outliers rather than reporting every member - highlight who's overloaded and who has bandwidth.
© readdle · MIT · readdle/spark-cli-skills