发现 Skills

Design multi-informant assessment approaches for dispositional competencies like curiosity or resilience. Use when assessing character strengths or competencies that written tests cannot capture.

Optimize a learning activity for flow by balancing challenge level, skill, clear goals, and immediate feedback. Use when students are bored, anxious, or disengaged during a task.

Analyse student work against criteria to identify specific gaps between current performance and learning objectives. Use when reviewing submissions, planning feedback, or diagnosing learning needs.

Design a focused lesson observation protocol with specific look-fors and evidence collection methods. Use when planning peer observations, coaching visits, or developmental classroom visits.

Design a learning task where mixed-age students work together with mutual benefit for all age groups. Use when planning cross-age tutoring, vertical grouping, or multi-year group activities.

Design a SEEDS regenerative inquiry cycle connecting place-based learning to ecological awareness for young learners. Use when building early childhood or primary inquiry around ecosystems and community.

Design a fact-checking protocol for AI-generated text, extending SIFT with AI-specific adaptations for hallucination detection. Use when students need to verify AI claims and citations.

Unpack a broad standard or competency descriptor into specific, assessable success criteria and sub-skills. Use when interpreting curriculum standards or writing learning objectives.

PDCA Orchestrator - 통합 자율 워크플로우 (Agent Teams 단일 패턴)

FINAL_CHECK 워크플로우 자동화. E2E 테스트, Phase 3-5 자동 진행.

Expertise in Vercel deployments, managing Preview/Production environments, Edge Functions, environment variable configuration, and CI/CD pipeline integration.

Review a codebase for consistency, patterns, and developer experience. Use when asked to review architecture, assess codebase health, or evaluate whether conventions are followed.

Use when the user wants to build, design, create, or set up a new AI agent or automation for a specific task. Walks them through purpose, access, model choice, risks, and guardrails — then writes the agent file.

用語集を作成するための詳細ガイドとテンプレート。用語集作成時にのみ使用。

Generate optimized prompts for AI image and video generation. Triggers on "generate a prompt for", "write me a prompt", "create an image prompt", "create a video prompt", "optimize this prompt".

ProofPilot brand styling for documents and spreadsheets. Applies exact brand colors, typography, and formatting to Word documents (.docx) and Excel spreadsheets (.xlsx). Use when creating ProofPilot client deliverables including SEO audits, website blueprints, proposals, reports, strategy documents, scorecards, or any professional document for ProofPilot clients. Triggers on keywords like "ProofPilot document", "client report", "audit", "blueprint", "proposal", "branded document", or any request to create professional deliverables.

Build a ProofPilot-branded .docx with python-docx in the terminal, upload it to Google Drive via webhook token capture, share it with anyone, and return the link. Use this whenever delivering a ProofPilot client document (audit, proposal, report, blueprint).

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) creating new spreadsheets with formulas and formatting, (2) reading or analyzing data, (3) modifying existing spreadsheets while preserving formulas, (4) performing data analysis and visualization in spreadsheets, or (5) recalculating formulas.

Help get unstuck on tasks by breaking them down, identifying blockers, or prepping for phone calls. Use when user says "I'm stuck on", "help me with", "I don't know how to", "I keep avoiding", or seems hesitant about a task.

Use when asked to review code, review PR, review diff, check this PR, do a code review, or when mentions include code review, PR review, full diff, cross-file patterns, code quality, or review changes.

Suggest relevant GitHub Copilot prompt files from the awesome-copilot repository based on current repository context and chat history, avoiding duplicates with existing prompts in this repository, and identifying outdated prompts that need updates.

Tactical Blueprint for stateful AI agents and multi-agent systems. Focuses on LangGraph orchestration, state persistence, and procedural loop logic.

Provides patterns for unit testing @ConfigurationProperties classes with @ConfigurationPropertiesTest. Use when validating application configuration binding and validation.

Framer Motion performance optimization guidelines. Use this guidance when writing, reviewing, or refactoring React animations with Framer Motion to ensure optimal performance patterns. It applies to tasks involving motion components, animations, gestures, layout transitions, scroll‑linked effects, and SVG animations.