Generate comprehensive lab member rosters in both markdown and CSV formats. Analyzes member profiles, git history, and alumni information to create detailed rosters with role transitions, team assignments, and career tracking. Use when user mentions roster, team list, lab members, or updating member information.
This skill generates comprehensive rosters of all lab members with detailed tracking of roles, dates, team assignments, and career progressions.
Use this skill when the user requests:
Fast automated generation using git history analysis.
When to use: Quick updates, routine refreshes
Output: lab_roster.csv
Careful information gathering using subagents for each member.
When to use: First-time generation, complex updates, verification needed
Output: ROSTER.md + lab_roster.csv
Ask the user which mode they prefer, or choose based on context:
Run the roster generation script:
python3 .claude/skills/lab-roster/scripts/generate_roster_csv.py
Validate output:
Present results to user with summary
Check if ROSTER.md exists
Get list of all members
ls _members/*.md | grep -v "friends"
Launch subagents to gather information
_members/[name].mdgit log --follow --format="%aI|%s" -- _members/[name].mdgit show <commit>:_members/[name].mdteam/index.mdUpdate ROSTER.md
Generate CSV from ROSTER.md
python3 .claude/skills/lab-roster/scripts/roster_md_to_csv.py
Validate and present
Use these keyword mappings to infer team from bio text:
software_engineering:
phenoinformatics:
virtual_biology (highest priority):
Note: Check virtual_biology keywords first, then software_engineering, then phenoinformatics.
Look for these patterns in bio text:
Remove markdown links and extract just the name.
Previous positions - look for:
Next positions - look in team/index.md alumni section:
**Next:** [position]Before presenting results:
Always show:
✓ Generated roster with [N] entries
✓ Saved to: lab_roster.csv
Summary:
Total entries: [N]
Unique members: [N]
Currently active: [N]
Alumni entries: [N]
Team distribution:
- software_engineering: [N]
- phenoinformatics: [N]
- virtual_biology: [N]
If script fails:
If subagents miss information: