naman10parikh/agentgrid / .claude/skills/deep-think
deep-think
VerifiedActivate multi-modal thinking for complex decisions. Combines Socratic thinking, self-critique, second/third-order effects, and adversarial debate.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.9 KB |
SKILL.md
View on GitHub---
name: deep-think
description: Activate multi-modal thinking for complex decisions. Combines Socratic thinking, self-critique, second/third-order effects, and adversarial debate.
---
## When to Use
- Architectural decisions with long-term consequences
- Feature design where multiple valid approaches exist
- Debugging when the root cause is unclear
- Any moment where the first answer is probably wrong
## Thinking Protocol
### Phase 1: Socratic Questioning
Ask yourself:
- What am I actually trying to solve? (not the symptom, the root cause)
- What assumptions am I making?
- What would happen if my assumption is wrong?
- Who has solved something similar before?
### Phase 2: Self-Critique
For every proposed solution:
- What's the weakest part of this approach?
- What would a skeptic say?
- What breaks first at 10x scale? 100x? 1000x?
- Am I solving the right problem or building what's easy?
### Phase 3: Second-Order Effects
- If we do X, what does that force us to also do?
- What doors does this close?
- What technical debt does this create?
- How does this affect the AutoLab improvement loop?
### Phase 4: Third-Order Effects
- How does this affect the agent ecosystem 6 months from now?
- What will users build on top of this that we didn't intend?
- What competitive response does this invite?
### Phase 5: Adversarial Red Team
Argue AGAINST your own recommendation:
- Build the strongest case for a different approach
- Find the scenario where your recommendation fails
- Only proceed if you can counter the adversarial argument
## Output Format
```
QUESTION: {one sentence}
APPROACH A: {description} — STRENGTH: {x} — WEAKNESS: {y}
APPROACH B: {description} — STRENGTH: {x} — WEAKNESS: {y}
SECOND-ORDER: {what happens next}
RED TEAM: {strongest argument against recommendation}
DECISION: {chosen approach} because {reason}
SACRIFICE: {what we're giving up}
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |