Think Research Framework — Development skill for Claude Code
Research a thinking framework and produce its evidence-graded dossier plus a schema-valid proposed registry entry, or discover candidate methods in a family.
How to install Think Research Framework
Installs to ~/.claude/skills/product-on-purpose-thinking-framework-skills-think-research-framework/SKILL.md
mkdir -p ~/.claude/skills/product-on-purpose-thinking-framework-skills-think-research-framework && curl -fsSL https://raw.githubusercontent.com/product-on-purpose/thinking-framework-skills/HEAD/commands/think-research-framework.md -o ~/.claude/skills/product-on-purpose-thinking-framework-skills-think-research-framework/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Think Research Framework does
description: Research a thinking framework and produce its evidence-graded dossier plus a schema-valid proposed registry entry, or discover candidate methods in a family. Use to vet a method before building it into a skill, reproduce the evidence-and-overlap vetting, or shortlist new candidates. argument-hint: "[framework-name | discover N in family ]" maps-to: think-research-framework
Invoke the think-research-framework skill to research and grade the request.
Input ($ARGUMENT
Alternatives in Development
- Battle — Head-to-head graded battle card between two sites — eight dimensions, bar-by-bar, verdict line 3.6k ★
- Vet — Vet the staged change: run the implement-review review loop (short alias) 239 ★
- Kaogong Shenlun — 申论训练与批改:五大题型出题,按真实评分标准踩点给分并给出参考答案 68 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Build Dossier
Deep source-cited dossier on a subject (person, business, family/principals, panel, entity warranting multi-se
Validation Gating
Turn proposed harness changes into candidate-first changes with explicit replay, regression, and rollback expe
Think
Structured Thinking Analyst
Ultra Think
Deep analysis and problem solving with multi-dimensional thinking
Vault Think
10-principle structured thinking framework saved to vault
Ccexplorer
A browser-based inspector for Claude Code JSONL session transcripts. Think Chrome DevTools' Network tab, but f
Related Agents
Critical Thinking
Critical thinking mode that challenges assumptions and probes reasoning. Use when you want a second opinion on
Daily Copilot
The everyday work partner. Use for prioritization, thinking out loud, "remember this", "challenge this", "what
Chadi Think
Deep thinking/planning subagent. Spawned by agent-chadi when task needs complex reasoning, architecture design