Productivity & Workflow Agent Skills for Claude Code

Guide beginners through workflow discovery before drafting reusable AI agent skills.

Use when you need a capability you do not already have and you are about to write it from scratch — parsing a format you have not handled…

Manages and synchronizes shared AI agent skills across Claude Code, Cursor, Codex, and Trae with safety-first dry-run verification.

Use the SkillHub CLI to publish, search, install, and manage Hermes Agent skills from a self-hosted registry.

When you want to create, adapt, or update a Claude Code skill in one of your sibling repos (list your own repos in…

Search, download, create, evaluate, analyze and route reusable agent skills with SkillNet.

Comprehensive toolkit for managing large Claude Code skill collections including bulk downloading from GitHub, organizing into categories…

Update this workspace's skills from the claude-skills library, add new skills (local or from other people's repos), or list what is…

Route substantive software-engineering work to the smallest useful set of specialized SkillShop playbooks before analysis or execution.

Use when the user wants to create a new Claude Skill for a specific domain or task — e.g. "make Claude really good at reviewing floor…

USER-INVOKED ONLY. Use when the user explicitly invokes $slice-runner or asks Codex to execute an already-approved multi-slice…

Use when the user dumps several asks at once, changes direction mid-task, or says "slow down" / "am I going too fast" / "break this down".

Intelligent request routing for /toh command.

Use when the user wants to commit, push, and open a pull request for the current changes.

Use when running the final Sociological Methods & Research (SMR) pre-submission check for ScholarOne — double-anonymization, separate…

Use when deciding whether a project clears the Sociological Methods & Research (SMR) bar — a genuine methodological contribution (develop…

Use when sequencing a Sociological Methods & Research (SMR) manuscript from method-contribution fit through derivation and properties…

Generate a Product Requirements Document (PRD) for a new feature.

Interview the user relentlessly until you reach a shared understanding.

Sniff-test a plan for INTENT ALIGNMENT via `/sniff-my-plan {file?}` — a light, pre-execution backstop that answers one question: do we…

Fires when a fellow wants a whole idea pressure-tested fast across five business questions — "is this worth doing", "pressure-test this"…