Community研究&データ分析github.com

product-on-purpose/thinking-framework-skills

Evidence-graded, agent-executable thinking-method skills - 56 frameworks reduced to their working mechanism, honestly graded, and producing a concrete artifact. 56 frameworks + 4 tools + 9 recipes for Claude Code, Codex, and other AI agents. Advanced (Gold) tier.

対応Claude CodeCodex CLI~Cursor
npx skills add product-on-purpose/thinking-framework-skills

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

ドキュメント

REPLACE Display Name

REPLACE: one paragraph. State the durable cognitive MECHANISM (not the trademarked ritual) and the concrete ARTIFACT this skill produces. Make clear the output is a structured artifact, not prose.

When to Use

  • REPLACE: concrete situations that should trigger this skill.

When NOT to Use

  • REPLACE: where this misleads, or is the wrong tool (point to the right one). Pull these from the dossier's failure modes; this section guards against cargo-cult execution.

Instructions

When asked to REPLACE, follow these steps:

  1. REPLACE step (bold lead-in). Imperative, bounded, concrete.
  2. REPLACE step.
  3. REPLACE step. Include the step that converts raw output into the artifact.

Output Format

Use the template in references/TEMPLATE.md. The deliverable is the filled artifact plus a short summary, not a prose essay.

Quality Checklist

Before finalizing, verify:

  • REPLACE checks, derived from the dossier's documented failure modes.
  • The output is the artifact, not prose.
  • No overclaiming: claims match what evidence/dossier.md actually supports.

Evidence

Tier REPLACE. REPLACE: one or two sentences, honest about what the evidence does and does not show, and noting that it is transferred from human studies (not AI-validated). Full grading, sources, and caveats: evidence/dossier.md.

Examples

See references/EXAMPLE.md for a completed run.

関連スキル