Deep Thinking — Development skill for Claude Code
Reason by the Claude Fable 5.1 protocol: grounded claims, multi-hypothesis diagnosis, self-review, Floor checks for trick questions, Constraint Loops for exact formats.
How to install Deep Thinking
Installs to ~/.claude/skills/ainative-build-skills-deep-thinking/SKILL.md
mkdir -p ~/.claude/skills/ainative-build-skills-deep-thinking && curl -fsSL https://raw.githubusercontent.com/ainative-build/skills/HEAD/commands/deep-thinking.md -o ~/.claude/skills/ainative-build-skills-deep-thinking/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Deep Thinking does
description: "Reason by the Claude Fable 5.1 protocol: grounded claims, multi-hypothesis diagnosis, self-review, Floor checks for trick questions, Constraint Loops for exact formats." argument-hint: "[task or question to reason through]"
/aif:deep-thinking
Run the `aif-deep-thinking` skill on `$ARGUMENTS`.
Read and follow `${CLAUDE_PLUGIN_ROOT}/skills/engineering/aif-deep-thinking/SKILL.md` in full, then execute its workflow against `$ARGUMENTS`. Load its `references/` files only wh
Alternatives in Development
- n8n MCP Tools Expert — MCP tools guide with tool selection and node formats 3.6k ★
- Octo Docs — Document delivery with export to PPTX, DOCX, PDF formats 2.8k ★
- Ideation — Ideation — Literature Search & Hypothesis Generation 613 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Pharn Dev Plan
Plan ONE increment of PHARN. Discovery-first, grounded in live state, pins the architecture content-hash, halt
Claude Code Game Builder
Claude Code skill: multi-agent build → capture → blind critic → fix loops that push a game toward a reference-
Generate First Touch
Write one short first touch grounded in company {{company_evidence}}, person {{person_evidence}} and scoring r
Twin Sparrow Grounded Collaboration
Multi-agent collaboration discipline: claims must carry evidence, requests must be read for their object befor
Feynman
why explain in words when diagram do trick
Adapt
Adaptive Re-Evaluation (Constraint Change)
Related Agents
Miner High
Delegate worker pinned to HIGH reasoning effort, the Opus 4.8 model default. Pick for diagnosis, multi-constra
Prospector
Generates candidate data center sites from first principles across a region by constraint intersection, then w
Fk Benchmarker
Owns the measurement protocol - noise floor, warm-up, clock ramp, repeats, CUDA sync, peak VRAM, launch counts