Manage research portfolio
Skill allenlee0430/allenlee-lab-skills/.claude/skills/manage-research-portfolio
Six Claude Code skills for running a research lab: grant writing, manuscript revision, literature scouting, file triage, reimbursement tracking, and PI operations. Install into ~/.claude/skills/.
npx -y skills add allenlee0430/allenlee-lab-skills --skill manage-research-portfolioAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Build and maintain a PI-level command view of Bowen Li's grants, manuscripts, experiments, trainees, collaborations, talks, deadlines, decisions, and risks. Use for weekly planning, deadline radar, project prioritization, workload balancing, status reporting, and converting scattered files or notes into an actionable research portfolio.
SKILL.md
1.4 KB, 203 tokens by cl100k_base, as published. Nobody here has run it
Manage research portfolio
- Gather current evidence from
00_Active_Now, recent files, calendar or email when authorized, and existing trackers. - Create one row per outcome-bearing project, not one row per file.
- Record objective, current stage, next irreversible decision, next action, owner, deadline, dependency, risk, confidence, and source evidence.
- Distinguish hard external deadlines from internal targets and undated aspirations.
- Rank work by scientific or strategic value, deadline pressure, dependency leverage, and PI attention required.
- Produce a weekly command brief: wins, deadlines in 14/30/90 days, blocked items, decisions only Bowen can make, delegated actions, and projects to pause.
- Never infer a commitment from an early draft or old file. Mark stale or conflicting evidence.
- Maintain a decision log so the same issue is not repeatedly reopened without new evidence.
Read references/portfolio-schema.md before creating or revising the tracker.