All skills
anthropics avatar

/scientific-problem-selection

@7c35640

This skill should be used when scientists need help with research problem selection, project ideation, troubleshooting stuck projects, or strategic scientific decisions. Use this skill when users ask to pitch a new research idea, work through a project problem, evaluate project risks, plan research strategy, navigate decision trees, or get help choosing what scientific problem to work on. Typical requests include "I have an idea for a project", "I'm stuck on my research", "help me evaluate this project", "what should I work on", or "I need strategic advice about my research".

Use this Skill: https://skilld.dev/gh/anthropics/knowledge-work-plugins/scientific-problem-selection

This session only. Nothing lands on disk.

references06-adversity-planning.md

≈1.2k tokens on demand. Your agent reads this file only when SKILL.md points to it.

SKILL 6: Adversity Response Planning ("The Adversity Feature")

Overview

This skill helps you prepare for inevitable crises and reframe them as opportunities. The term "adversity feature" (like a "rock garden" on a mountain bike trail) captures the mindset: adversity is not an obstacle—it's an opportunity to develop skill and improve your project.

Core Principle

"Capitalize on the 'adversity feature'"

Adversity in a project is inevitable AND opportune:

  • Inevitable: Almost every project suffers existential crisis or sharp turn
  • Opportune: Two valuable outcomes possible:
    1. Fix the problem AND upgrade the project simultaneously
    2. Develop reasoning-your-way-out skills (best growth opportunity)

Key Concepts

Why Adversity Is Inevitable:

  • Technology doesn't work as advertised
  • Biological assumptions prove false
  • You get scooped
  • Key collaborator leaves
  • Funding runs out
  • Results don't support hypothesis

Why Adversity Is Opportune:

  • Forces you to think deeply about alternatives
  • Removes sunk-cost bias (path is blocked anyway)
  • Often leads to better projects than original plan
  • Develops critical problem-solving skills
  • Makes you resourceful

The Crisis Mindset:

  • Wrong: "This is a disaster that delays me"
  • Right: "This is the crisis I've been waiting for—don't waste it"

Workflow

Phase 1: Anticipate Failure Modes

For your project, list likely adversity scenarios:

  1. Technical failures: Method doesn't work, signal too low, etc.
  2. Biological surprises: System behaves unexpectedly
  3. Competition: Someone scoops you
  4. Resource issues: Funding, equipment, access
  5. Timeline pressures: Takes longer than expected

For each, rate:

  • Likelihood (Low/Medium/High)
  • Impact if it happens (Low/Medium/High)
  • When it might surface (early/mid/late)

Phase 2: Upgrade Opportunities

For each high-likelihood or high-impact failure mode:

Question 1: How could you fix this AND make the project better? Not just: "Get it working" Instead: "Use this as opportunity to improve the approach"

Example: Your Cell Type Can't Be Isolated

  • Fix: Develop new isolation method
  • Upgrade: Make method work for whole class of cell types
  • Result: Better project (technology paper) + original biology

Question 2: What skill would you develop by solving this?

  • Computational: Learn new analysis method
  • Technical: Master challenging technique
  • Conceptual: Reason through biological complexity

Phase 3: The Ensemble View

Critical Insight: You're not picking ONE project path—you're picking an ENSEMBLE of possible projects that share core elements.

Your Project Ensemble:

Core Theme: [What stays constant]

Path 1: [Original plan]
Path 2: [If assumption A fails]
Path 3: [If technical barrier B encountered]
Path 4: [If scooped on C]

All paths lead to impactful results, just different ones

This reframing is liberating: when adversity strikes, you're not failing—you're discovering which path in the ensemble you're actually on.

Phase 4: Historical Examples

Example 1: PROTAC Discovery

  • Original Plan: Create molecules to degrade specific kinase
  • Crisis: Didn't work for intended target
  • Upgrade: Test across kinome systematically
  • Result: Better project (mapped degradable kinome, discovered that target engagement ≠ degradation)
  • Impact: More influential than if original plan succeeded

Example 2: Steroid Receptor Study

  • Original Plan: Identify THE receptor for a steroid
  • Crisis: Binds multiple receptors at different affinities
  • Upgrade: Reframe question: How does finite receptor pool sense infinite lipids?
  • Result: Combinatorial sensing model (like piano chords)
  • Impact: More interesting than "receptor X binds steroid Y"

Output: Adversity Playbook

Page 1: Anticipated Crises

Crisis Likelihood Impact Timeline Growth Opportunity
[Crisis 1] H/M/L H/M/L Early/Mid/Late [Skill developed]

Page 2: Upgrade Strategies For each high-priority crisis:

  • The Crisis: [Description]
  • Fix Strategy: [How to solve it]
  • Upgrade Strategy: [How to make project better while fixing]
  • Alternative Path: [New direction if fix doesn't work]
  • Ensemble Position: [How this fits in project family]

Page 3: Resilience Rituals

  • Weekly check-in: Review what went wrong, what was learned
  • Monthly ensemble review: Update the family of possible projects
  • Crisis protocol: When major setback hits, take 2 days to think before acting
  • Growth tracking: Document skills developed through adversity

Source: SKILL.md on GitHub

1 warning16d5 checks · Risk SAFE
  • Gen Agent Trust Hub16d

    This skill provides a structured conversational framework for scientific problem selection based on established academic research. It guides users through ideation, risk assessment, and strategic planning. No security issues were detected.

  • Socket16d

    No alerts

  • Snyk16d

    Risk: LOW · No issues

  • Runlayer7mo

    11/11 files flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 7c35640. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Activeupdated 8 months ago

README badge

README badge for anthropics/knowledge-work-plugins/scientific-problem-selection