Expert Forging Master
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md to install @user_924b0a5e/yrns-expertstructor.
About this skill
Problem Addressed
Creating WorkBuddy expert packages can be error-prone: field rules, directory layout, agent versus team classification, scattered source material, missing license, and unstable edits. This skill codifies the expert-manager workflow for maintaining single-expert or multi-role expert packages.
How It Works
- Interactive or source conversion: gathers missing details through questions, or extracts roles, SOPs, scripts, and templates from docs and prompts.
- Display-field mapping: enforces rules for
profession,displayName,expertType,categoryId,tags, andquickPrompts;tagsandquickPromptsare fixed at 3. - Quality checkpoints: designs team SOPs with a plan-execute-integrate flow and checks for plan, draft, and final confirmation.
- Engineering constraints: generates into the fixed expert directory, then initializes, validates, registers, and packages;
plugin.jsonshould includelicense, with a defaultyrns-packaging prefix. - Safe edits: backs up before modification, then reviews
license, version bump, structure validation, and naming consistency.
Boundaries
Best for creating, converting, or updating WorkBuddy expert packages. Not for ordinary Skill creation, merely using existing experts, or renaming name / directory in place. Missing source details are flagged for user input rather than invented.
Use Cases
- Product owners turn sales SOPs, scripts, and pricing templates into a reviewable WorkBuddy business expert.
- Algorithm engineers build a Team expert with plan, execution, and integration SOPs for multi-role data analysis.
- Engineering leads update an existing expert's plugin.json, tags, and Agent MD, then validate, register, and package it.
- Operations staff inject customer profiles, metric definitions, and knowledge-base references into the expert package.
Best For
- WorkBuddy expert authors who want to turn SOPs, role assignments, and prompts into reviewable packages.
- AI application leads who need to maintain Team experts with clear lead, member roles, and confirmation checkpoints.
- Engineering operations staff who split source material scripts, templates, and field specs into bin/, templates/, and references/.
- Compliance reviewers who check license, tags, quickPrompts, and directory naming against release rules.
Related Skills
Automatically searches job postings based on the user profile, AI-scores fit, saves desktop reports, and sends email updates with scheduled tracking.
Activates bionic reasoning for causal judgment, numerical prediction, and hypothesis validation, using hypothesis-driven checks, Bayesian updates, falsifiability tests, bias defense, and physical constraints.
Triggered by /plan, it asks the agent to output a plan, risks, impact scope, and validation approach before execution.
Track and clean agent session files, packages, and Skills via trash-first safety.