Universal behavioral standards for autonomous agents. Defines HOW agents execute work: Uninterrupted Flow, Self-Verification, and Handoff protocols. This is the behavioral brain shared across all builder operations. <example> Context: Any autonomous execution user: "Execute this task autonomously" assistant: "I'll use execution-core standards to run in Uninterrupted Flow with self-verification." </example> <example> Context: Task encounters blocker user: "Task failed with auth error" assistant: "Following execution-core auth-gate protocol, I'll create HANDOFF.md and exit." </example> <example> Context: Verifying task completion user: "Check if the task is done" assistant: "Using execution-core observation-points, I'll verify programmatically and log evidence." </example>
/plugin marketplace add Git-Fg/thecattoolkit/plugin install git-fg-builder-plugins-builder@Git-Fg/thecattoolkitThis skill is limited to using the following tools:
references/auth-gates.mdreferences/handoff-protocol.mdreferences/observation-points.mdThis skill defines universal behavioral protocols for autonomous agent execution.
It answers: "HOW should agents behave?" (not "WHAT should they do").
Behavioral Protocols:
references/observation-points.md - Self-verification and evidence collectionreferences/auth-gates.md - Authentication error handlingreferences/handoff-protocol.md - Standard handoff formatAgents execute autonomously without pausing for human input.
Protocol: references/observation-points.md
Every task must be verified automatically.
Standard Pattern:
**Self-Verification Results:**
✓ [Verification 1 passed]
✓ [Verification 2 passed]
Next: Continue to next task
Authentication errors are NORMAL, not failures.
Protocol: references/auth-gates.md
Standard format for pausing execution.
Protocol: references/handoff-protocol.md
Use for:
Format:
# HANDOFF Required
**Reason**: [AUTH_GATE | CONFLICT | AMBIGUOUS]
**What Happened**: [Description]
**What You Need to Do**: [Specific action]
**Verification**: [How to confirm fix]
**Next Step**: Restart execution after [action]
Skills reference execution-core for behavioral standards:
Example from project-strategy:
Use execution-core observation-points for self-verification
Use execution-core auth-gates for authentication handling
Example from software-engineering:
Apply execution-core verification protocols during TDD
Use execution-core handoff format for blockers
Execution-core sits at the BASE of the behavioral stack:
execution-core (HOW to behave)
↓
project-strategy (WHAT documents to create)
software-engineering (WHAT code patterns to use)
↓
director/worker agents (Execute using these standards)
Critical: Execution-core is UNIVERSAL. All builder agents must follow these behavioral protocols.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.