Skip to content

nota-america/forgecat-agent-profiles / profiles/anthropics/knowledge-work-plugins/anthropics_knowledge-work-plugins_bio-research/for-forgecat/skills/scientific-problem-selection

scientific-problem-selection

Verified

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".

references/08-integration-synthesis.md

View on GitHub
# SKILL 8: Integration and Synthesis

## Overview
This final individual skill synthesizes all previous skills into a coherent project plan and communication strategy. You'll create a complete package that demonstrates thoughtful problem selection and rigorous planning.

## Core Principle
**"Tell a compelling story with your choices"**

Humans love stories. Your project should have:
- **Setting:** Background and problem framing
- **Problem statement:** Clear, general enough to be interesting, specific enough to be distinctive
- **New idea/approach:** Your angle (perturbation/measurement/theory: logic vs. technology)
- **Iteration:** Loop of "we wondered X → did Y → found Z → interpreted as W"
- **Conclusion:** What we learned and/or what's now possible
- **Passion:** Authentic enthusiasm

## Workflow

### Phase 1: Gather Your Skill Outputs

Collect your completed documents:
- ☐ Skill 1: Problem Ideation Document
- ☐ Skill 2: Risk Assessment Matrix
- ☐ Skill 3: Impact Assessment Document
- ☐ Skill 4: Parameter Strategy Document
- ☐ Skill 5: Decision Tree Map
- ☐ Skill 6: Adversity Playbook
- ☐ Skill 7: Problem Inversion Analysis (if applicable)

### Phase 2: Create Narrative Arc

**Story Structure for Your Project:**

**1. Setting (Background)**
- What's known in the field?
- What's the gap or opportunity?
- Why does this matter?

**2. Problem Statement**
- General enough: connects to broad principle
- Specific enough: distinctive and tractable
- Your framing from Skill 1

**3. Your Approach**
- Perturbation/Measurement/Theory
- Logic vs. Technology
- What's novel about your angle (from Skill 1)
- How your optimization function shapes approach (from Skill 3)

**4. Strategy**
- Fixed vs. floating parameters (from Skill 4)
- Decision points mapped out (from Skill 5)
- Risk mitigation built in (from Skill 2)
- Adversity contingencies (from Skill 6)

**5. Why You**
- Your competitive advantage
- Lab expertise
- Your passion and alignment
- Timeline and resources

### Phase 3: Communication Formats

**Format 1: 3-Slide, 5-Minute Presentation**

**Slide 1: The Opportunity**
- Setting + Problem statement
- One key figure or schematic
- Why this matters (optimization function)

**Slide 2: Your Approach**
- New idea/angle
- Key experiments or analyses
- What makes this feasible
- Decision tree highlights

**Slide 3: Impact and Timeline**
- What you'll learn or enable
- Success metrics
- Timeline with milestones
- Your advantage

**Slide Design Tips:**
- Minimal text (bullets are fine here)
- Strong visuals
- Tell story, don't catalog facts
- Passion shows through

**Format 2: 1-Page Written Summary**

**Paragraph 1:** Setting and problem (2-3 sentences)
**Paragraph 2:** Your approach and novelty (3-4 sentences)
**Paragraph 3:** Why it will work (risk mitigation, your advantage) (2-3 sentences)
**Paragraph 4:** Impact and timeline (2-3 sentences)

**Total:** ~250-300 words that could be abstract or summary

**Format 3: 1-Minute Elevator Pitch**

**Structure:**
- "I'm working on [problem] because [why it matters]"
- "Current approaches are limited by [gap]"
- "My angle is [approach] which is novel because [what's new]"
- "This will [impact] and I have [advantage]"

**Practice until:** Natural, passionate, memorable

### Phase 4: Integration Document

**Complete Project Plan Integrating All Skills:**

**Section 1: Problem Selection Rationale**
- How you generated this idea (Skill 1 intuition pumps)
- Why this problem matters (Skill 3 optimization function)
- Your competitive advantage

**Section 2: Risk Management**
- Assumption analysis table (Skill 2)
- Go/no-go experiments
- Timeline with checkpoints
- Mitigation strategies

**Section 3: Execution Strategy**
- Fixed vs. floating parameters (Skill 4)
- Decision tree navigation plan (Skill 5)
- Adversity response protocols (Skill 6)
- Project ensemble (alternative paths)

**Section 4: Communication Plan**
- Presentations (3-slide deck)
- Written summary (1-page)
- Elevator pitch (1-minute)
- Key messages for different audiences

**Section 5: Career Alignment**
- How this fits your trajectory
- Skills you'll develop
- Network you'll build
- Next steps after this project

## Output: Complete Project Package

**Document 1: Integrated Project Plan (4-6 pages)**
- All sections above
- References to individual skill outputs
- Timeline and milestones
- Resource requirements

**Document 2: Communication Materials**
- 3-slide presentation
- 1-page summary
- Elevator pitch script
- Talking points for different audiences

**Document 3: Living Documents**
- Decision tree (to update regularly)
- Risk assessment (to review quarterly)
- Adversity playbook (to consult in crisis)
- Parameter strategy (to revisit if stuck)

## Key Principles

1. **Integration, Not Duplication:** Each skill output serves a purpose in the whole
2. **Story Over Catalog:** Communicate choices, not just facts
3. **Passion Matters:** Authentic enthusiasm is persuasive
4. **Living Plan:** This evolves; revisit quarterly
5. **Alignment:** Project, values, and career fit together
6. **Preparation:** You've thought through contingencies
7. **Communication:** You can pitch this clearly to anyone

## Ready to Synthesize

With all skills complete, you now have a comprehensive, thoughtful, rigorous approach to problem selection and project planning. This is the highest-leverage work you can do in science.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall