agent-customization
**WORKFLOW SKILL** — Create, update, review, fix, or debug VS Code agent customization files (.instructions.md, .prompt.md, .agent.md, SKILL…
Interviews, notes · 42 skills
**WORKFLOW SKILL** — Create, update, review, fix, or debug VS Code agent customization files (.instructions.md, .prompt.md, .agent.md, SKILL…
Create new skills, modify and improve existing skills, and measure skill performance.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree.
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, A…
Create a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue.
Turn the current conversation context into a PRD and publish it to the project issue tracker.
Grilling session that mines the user for fragments — heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts) —…
AI job search command center -- evaluate offers, generate CVs, scan portals, track applications Determine the mode from $mode: | Input | Mod…
Extracts what the user actually wants instead of what they think they should want.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree.
Create structured interview plans with competency-based questions and scorecards.
Track and manage recruiting pipeline stages.
Technical interview preparation expert for algorithms, system design, and behavioral questions A seasoned engineering hiring manager and int…
Create an end-to-end customer journey map with stages, touchpoints, emotions, pain points, and opportunities.
**WORKFLOW SKILL** — Create, update, review, fix, or debug VS Code agent customization files (.instructions.md, .prompt.md, .agent.md, SKILL…
Interprets Culture Index (CI) surveys, behavioral profiles, and personality assessment data.
Generate viral 9:16 YouTube Shorts (or TikTok/Reels clips) from a long-form YouTube URL or local video.
> This skill scaffolds new content for the microsoft/agent-academy repository at https://github.com/microsoft/agent-academy.
Find and set up coding practice problems tailored to your weak areas, then create local files so you can solve them right away.
| Use when the user wants to cherry-pick a PR to a release branch.
Generate structured research questions, testable hypotheses, and candidate empirical strategies from a topic, phenomenon, or dataset descrip…
Transcribe audio/video files to text using Qwen3-ASR.
帮用户搭一个金融投研专用 LLM Wiki(Karpathy 模式):纯 markdown 文件 + [[wikilink]] 互联 + LLM 维护,知识随用复利。
Corrects speech-to-text transcription errors using dictionary rules and AI-powered analysis.
Authors deterministic and LLM rubric graders for skillgrade evaluations.
Interactive system builder.
Interactive repository analysis and project-overview.md generation via task creation.
> You are extracting domain knowledge for a library to produce a structured domain map.
Determine technologies needed to build the product, making build/buy/integrate decisions during PRD v0.5 Red Team Review.
Design and conduct qualitative research using grounded theory and case studies A skill for designing and conducting rigorous qualitative res…
Interview-driven automation design tool.
基于Step 1确立的设计方向定义Token,每个Token选择须有设计意图: 若 {INSTRUCTION_FILE} 设计工具 为 penpot,调用 penpot-sync 将token同步到Penpot项目和 tokens.css 从PRD功能需求推导页面和组件需求:
一套完整的學術研究 Skill 套件,涵蓋從論文閱讀到撰寫、審稿的完整研究流程。支援 Claude Code、ChatGPT/Codex CLI、Gemini CLI。
Interactive hiring wizard to set up a new AI team member.
Comprehensive, research-backed Hinge dating profile optimization.
Interview the user about their goal before any plan or code.
Guide humans through creating effective instruction rules for coding agents (Copilot, Claude Code, Cursor, Windsurf, Aider, AGENTS.md, CLAUD…
Deep interview to reach shared understanding before building.
Claude Code agent infrastructure setup — interview-based, domain-preset-driven.
Scaffold a new project with the full AI-assisted development workflow — Makefile targets, linter/formatter configs, pre-commit hooks, CLAUDE…
> Use when this capability is needed.
Evaluate the quality of existing agent instruction rule sets — CLAUDE.md, AGENTS.md, .cursorrules, copilot-instructions.md, or any coding-ag…