agentleFS
jjfroehlichjjfroehlich/agent-skills-for-academic-research/skills/mentoring-management-and-lab-culture/SKILL.md

mentoring-management-and-lab-culture

Skill2 starsChanged 31 days agoMITView on GitHub

Improve research-group mentoring, shared policies, collaboration and credit arrangements, feedback, and management using compacts, handbook sections, onboarding plans, feedback messages, or accounts of group practices. Exclude personal job choices and clinical or legal determinations.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When diagnosis is needed, consider policies, roles, resources, incentives, and power dynamics before attributing individual fault.

    line 33
  2. Distinctive:

    Keep observations separate from interpretations.

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Mentoring Management And Lab Culture

Purpose

Help research leaders, mentors, and lab members turn values into explicit routines, documents, conversations, and escalation paths. Treat unclear expectations and power asymmetries as management design problems before treating them as individual failures.

Use this skill when

  • The user is drafting or revising a lab handbook, onboarding plan, mentoring compact, AI guideline, or lab policy.
  • The user needs a feedback script, conflict diagnosis, performance concern workflow, or repair conversation.
  • The user is planning IDP meetings, annual reviews, mentoring routines, hiring, onboarding, or group-management systems.
  • The request concerns lab health, belonging, work-life boundaries, credit, status, psychological safety, or whole-person support.

Do not use this skill when

  • The user mainly needs personal job-search, promotion, or career-strategy advice without a lab-management angle.
  • The task is scientific writing, grant writing, peer review, presentation design, or research-project design.
  • The request asks for clinical, legal, or institutional-policy determinations. Provide non-clinical, non-legal structure and tell the user to use qualified institutional routes.

Core workflow

  1. Classify the problem: mentoring, lab manual, lab leadership, healthy culture, IDP planning, or conflict and feedback.
  2. For conflict or management diagnosis, inspect roles, dependencies, expectations and actual authority. A supervisor's influence over funding or references does not establish a right to decide everything. For a local policy or message edit, use the supplied context and resolve only issues that affect that edit.
  3. When diagnosis is needed, consider policies, roles, resources, incentives, and power dynamics before attributing individual fault.
  4. Choose the smallest concrete output: a script, checklist, handbook section, meeting agenda, role rubric, support plan, or escalation map.
  5. For a work agreement or change plan, identify responsibilities, available support and a relevant review point. Include exceptions or support routes where the work or risk requires them. A narrow message edit may need only revised wording.
  6. Keep observations separate from interpretations. Label offered support, proposed arrangements, agreed actions and completed outcomes accurately. Do not infer motivation, health conditions, consent or institutional authority from silence or a written document.

Output formats

Select only the format that fits the requested deliverable; these are patterns, not mandatory response sections.

  • Lab handbook section or outline.
  • Mentoring expectations compact.
  • IDP or yearly-planning agenda.
  • Feedback, repair, or distress-support script.
  • Performance-diagnosis checklist.
  • Hiring, onboarding, or collaboration kickoff checklist.
  • Lab-health review and action plan.

Reference routing

  • Open references/mentoring.md for mentor-mentee expectations, adaptive mentoring, hidden curriculum, co-mentoring, and malpractice risks.
  • Open references/lab-manuals.md for handbooks, onboarding policies, AI guidelines, safety, privacy, authorship, and escalation sections.
  • Open references/lab-leadership.md for PI systems, hiring, onboarding, capacity, group review, evaluation, collaboration and the separate contribution, authorship and order decisions.
  • Open references/healthy-lab-culture.md for belonging, inclusive participation, work-life boundaries, mental-health-sensitive support, credit, and status risks.
  • Open references/individual-development-plans.md for IDPs, yearly planning, goal translation, feedback, and career-development routines.
  • Open references/conflict-and-feedback.md for unclear expectations, structural conflict diagnosis, performance concerns, criticism norms, failed experiments, and support scripts.
  • Open references/handbook-access.md when a fuller explanation or worked example would help with the current task.

Quick checklist

Apply only the checks relevant to the requested scope and artifact. Inspect supplied context first; treat identify or clarify as analysis when the answer is already available, and ask only for missing information that could change the result.

  • How was the expectation communicated, and what indicates it was understood? A written record helps but does not establish understanding or agreement.
  • Is this an individual behavior issue, a role-design issue, a resource constraint, or a power-asymmetry issue?
  • Does the requested plan identify relevant expectations, feasible support and follow-up? Are additional support routes needed given the issue and power relationship?
  • Are private or sensitive details excluded from public-facing text?
  • For distress, health, harassment, retaliation, or legal risk, are qualified institutional routes named instead of overpromising?

Common pitfalls

  • Turning values into vague slogans rather than routines, responsibilities, and follow-up dates.
  • Giving hard feedback without owning unclear expectations or offering concrete support.
  • Treating mentoring as a single PI relationship when co-mentoring or institutional support is needed.
  • Treating long hours, prestige, or visibility as evidence of contribution.
  • Requiring direct confrontation, joint mediation, personal disclosure or an entire management plan for every request.
  • Equating a contribution record with authorship eligibility, a supervised run with independent readiness, or a requested resource with confirmed support.

Quality bar

  • Advice must be power-aware, operational, and specific to research groups.
  • Mental-health content must remain non-clinical and route to qualified support.
  • Preserve consequential conditions in the advice itself: local preferences, conceptual tools and survey priorities do not become universal requirements or proven interventions.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.