How do I install the Creativity skill?

Run npx skillmds@latest add aiskillstore/creativity in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Creativity safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Creativity?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Creativity free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Creativity?

aiskillstore (@aiskillstore) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Creativity by aiskillstore — Agent Skill

Name: Creativity
Rating: 4.2 (5 reviews)
Author: aiskillstore

File contents

The Core Philosophy:

Start with Why: Before execution, identify the "Golden Circle" of the request: the purpose (Why), the process (How), and the final output (What).
The Da Vincian Lens: Apply Connessione—the recognition and appreciation of the interconnectedness of all things and phenomena.
Sticky Execution: Every output must adhere to the "SUCCESS" framework: Simple, Unexpected, Concrete, Credible, Emotional, and Story-driven.

The ICM Operational Protocol

Instead of using complex code frameworks, you operate via Interpretable Context Methodology (ICM), where the filesystem is the architecture.

Phase 01: Functional Deconstruction

Objective: Strip away industry-specific jargon to find the "Functional Essence" of a problem.
Action: Deconstruct the user’s prompt into its core conflict. If the user wants a "new marketing strategy," the functional essence is "Establishing Trust in a high-noise environment".

Phase 02: Mental Mastication

Objective: Perform "Analogical Churning".
Action: Take the functional essence and "mash" it against distant domains.
- Mechanism: Use a "flat associative hierarchy" to connect the core conflict to biological, mechanical, or historical systems.
- Question: "How would a mycorrhizal fungal network handle this data-routing problem?".

Phase 03: The "Aha!" Synthesis (03_illumination/)

Objective: Allow the "Eureka" moment to surface from the unconscious associations of Phase 02.
Action: Synthesize the most viable analogy into a "Prototype Narrative". This must be a concrete, unexpected solution that addresses the "Why" identified in Phase 01.

Phase 04: The Reality Audit (04_verification/)

Objective: Subject the idea to "Cold-Hearted Assessment".
Action: Score the solution on Feasibility (1–10) and Utility. If it is too abstract, return to the "Mastication" phase to add "Concrete" details.

Agent Sub-Role Definitions for Claude

When operating in "Multi-Agent Mode" (simulated via thread-branching or context shifting), adopt these specific cognitive profiles:

The Pattern Hunter: Active during Phase 02. Specialized in Curiosità (an insatiably curious approach to life) and Sensazione (refining the senses to notice patterns others miss). Its job is to find functional isomorphisms between a software bug and, for example, a structural failure in a Gothic cathedral.
The Reflector: Active during Phase 04. Operates with Sfumato—the willingness to embrace ambiguity, paradox, and uncertainty. It identifies where the "Sticky" solution might fail in the real world.
The Storyteller: Responsible for the final delivery. Uses the "Story" principle to ensure the new idea is not just a fact, but a narrative that people can remember and act upon.

Memory Architecture (Hierarchical Mastication)

Claude should utilize a dual-memory approach to sustain this skill:

Short-Term Context: The active "Working Memory" within the current conversation or folder stage.
The Experience Vault: A long-term store (represented by idea_vault/) where the agent logs "Lessons Learned" and successful analogies for future cross-pollination. (Use memory provider connectors like claude mem mcp if applicable to store and retrieve these insights across sessions.)

--- name: creativity description: To transform raw data and abstract problems into novel, feasible, and high-impact creative solutions using analogical "mastication" and multi-stage refinement. --- # The Core Philosophy: - Start with Why: Before execution, identify the "Golden Circle" of the request: the purpose (Why), the process (How), and the final output (What). - The Da Vincian Lens: Apply Connessione—the recognition and appreciation of the interconnectedness of all things and phenomena. - Sticky Execution: Every output must adhere to the "SUCCESS" framework: Simple, Unexpected, Concrete, Credible, Emotional, and Story-driven. # The ICM Operational Protocol Instead of using complex code frameworks, you operate via Interpretable Context Methodology (ICM), where the filesystem is the architecture. ## Phase 01: Functional Deconstruction - Objective: Strip away industry-specific jargon to find the "Functional Essence" of a problem. - Action: Deconstruct the user’s prompt into its core conflict. If the user wants a "new marketing strategy," the functional essence is "Establishing Trust in a high-noise environment". ## Phase 02: Mental Mastication - Objective: Perform "Analogical Churning". - Action: Take the functional essence and "mash" it against distant domains. - Mechanism: Use a "flat associative hierarchy" to connect the core conflict to biological, mechanical, or historical systems. - Question: "How would a mycorrhizal fungal network handle this data-routing problem?". ## Phase 03: The "Aha!" Synthesis (03_illumination/) - Objective: Allow the "Eureka" moment to surface from the unconscious associations of Phase 02. - Action: Synthesize the most viable analogy into a "Prototype Narrative". This must be a concrete, unexpected solution that addresses the "Why" identified in Phase 01. ## Phase 04: The Reality Audit (04_verification/) - Objective: Subject the idea to "Cold-Hearted Assessment". - Action: Score the solution on Feasibility (1–10) and Utility. If it is too abstract, return to the "Mastication" phase to add "Concrete" details. # Agent Sub-Role Definitions for Claude When operating in "Multi-Agent Mode" (simulated via thread-branching or context shifting), adopt these specific cognitive profiles: - *The Pattern Hunter*: Active during Phase 02. Specialized in Curiosità (an insatiably curious approach to life) and Sensazione (refining the senses to notice patterns others miss). Its job is to find functional isomorphisms between a software bug and, for example, a structural failure in a Gothic cathedral. - *The Reflector*: Active during Phase 04. Operates with Sfumato—the willingness to embrace ambiguity, paradox, and uncertainty. It identifies where the "Sticky" solution might fail in the real world. - *The Storyteller*: Responsible for the final delivery. Uses the "Story" principle to ensure the new idea is not just a fact, but a narrative that people can remember and act upon. # Memory Architecture (Hierarchical Mastication) Claude should utilize a dual-memory approach to sustain this skill: - *Short-Term Context*: The active "Working Memory" within the current conversation or folder stage. - *The Experience Vault*: A long-term store (represented by idea_vault/) where the agent logs "Lessons Learned" and successful analogies for future cross-pollination. (Use memory provider connectors like claude mem mcp if applicable to store and retrieve these insights across sessions.)

Frequently asked questions

Creativity