Agent skills

This skill should be used when the user asks to "create MongoDB model", "define Beanie document", "write MongoDB query", "create…

Use this skill when the user wants to make their app look better, says it looks like a template, asks how to achieve Stripe/Linear…

Generates 9:16 vertical synesthetic video commercials for cosmetics, skincare, and fragrance products using sensory translation and AI…

Independent local multi-model review for contested, security-sensitive, high-risk, or merge-critical plans and changes.

Automate Beeminder tasks via Rube MCP (Composio).

Bug condition/postcondition formalization as testable Behavior Contracts.

Behavior tree design and implementation skill for game AI.

Use when a Journal of Economic Behavior & Organization (JEBO) manuscript needs a behavioral or bounded-rationality model to organize…

Go behind a program to discover what it ACTUALLY uses — its real dependencies, libraries, syscalls, files, network endpoints, env/config…

../../../engineering/behuman/skills/behuman/SKILL.md

Use when the user wants more human-like AI responses — less robotic, less listy, more authentic.

Design targeted interventions that strengthen belonging and inclusion for specific classroom dynamics.

Design a performance benchmark for an API — test scenarios, metrics, and tooling.

Design and calibrate a multi-Case capability Benchmark and establish a traceable Formal Baseline.

Agent skill for benchmark-suite - invoke with $agent-benchmark-suite

Manage benchmarks for algorithm engineering experiments and evaluations

Runs an honest before/after evaluation of any change — a model prompt, an algorithm, a feature, or a refactor — against a fair baseline…

Use when designing explicit state-machine behavior for systems with multiple modes (idle/loading/success/error, draft/submitted/approved…

Bounded interrogation between a raw need and a complete specification: an eleven-category ambiguity sweep, at most five questions ranked…

Interactive BPA rule generation for Power BI semantic models; guided discovery, model investigation, and expert rule authoring.

View and manage your personal best practices library with success/failure patterns.