Agent skills for Claude Code

Analyze an existing software or product project, or discover requirements for an empty greenfield project, then design a user-confirmed…

Manages session state and context handoffs for multi-session projects using the Session Handoff Protocol.

Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions

Inspect a coding project and plan the smallest set of project-specific skills, instructions, references, or checks that would improve…

Automatically analyze project state, detect stage, identify gaps, and recommend next steps based on existing artifacts.

Standardizes software project layouts and directory hierarchies across various programming languages and frameworks.

Generating a Word document (.docx) from the documentation-master corpus as a one-off deliverable (snapshot for an audience…

File a librarian query result back into the library as a new page with provenance tracking.

Promotion preflight gate for the agent-skills marketplace.

Camera-and-prompt craft for the video nodes on the Skilyst/Beehive platform — the cross-model structural skeleton, the per-model deltas…

Transforms user prompts into optimized prompts using frameworks (RTF, RISEN, Chain of Thought, RODES, Chain of Density, RACE, RISE, STAR…

Transform weak prompts into high-performance prompts for OpenAI and Codex workflows by asking targeted clarifying questions, preserving…

Analyze and improve plugin prompts, skill definitions, and command instructions

Prompt injection detection and prevention for secure LLM applications

You are an expert prompt engineer specializing in crafting effective prompts for LLMs through advanced techniques including constitutional…

Creates database migrations with proper schema changes, data migrations, and rollback support for various ORMs (Prisma, TypeORM, Alembic…

Builds or extends the tracked AI-answer prompt set from real buyer evidence, structured by buying-journey stage and proximity to the…

Author, edit, or iterate on prompts in the Phoenix prompt playground, including running experiments over a dataset.

Orchestrates parallel prompt validation for Finesse planning sessions

Validate, lint, audit, or fix PromQL queries and alerting rules; detects anti-patterns.

Use when designing the proof technique, algorithm, or simulation protocol for an Operations Research (OR) manuscript — choosing the right…