This skill should be used when content teaches patterns (skills, subagents, ADRs, PHRs, specifications) that have canonical sources elsewhere.
Ship and capture lessons workflow. Creates the PR, updates lessons learned, updates documentation, generates the sprint retrospective, and updates the backlog.
Durable index of lessons learned in past BioMysteryBench harness sessions, numbered L-01, L-02, …, L-NN.
When the user signals you've gone off-track, this skill is the recovery protocol. Read it before re-acting on a correction.
Use when after training a Siamese neural network on MS/MS spectrum pairs, use this skill to quantify prediction performance on a disjoint test set (e.g., 3600+ spectra from 500…
Use this skill when the student asks about dental anatomy, tooth morphology, oral structures, or anatomical relationships.
This skill should be used when the user says "교훈 기록해", "이거 기억해둬", "다음에 이런 실수 하지 마", "패턴 추가해", "lessons learned", or when recording corrections, feedback, or process impro — from…
Use this skill when building evaluation frameworks to measure LLM quality, safety, accuracy, or alignment including test suites, human eval rubrics, automated evals, and metrics…
Use this skill when the user asks to design, generate, review, revise, or assemble an examination paper, test blueprint, item bank, answer key, scoring rubric, or post-exam item…
Activate this skill when a student provides study material (PDF or pasted notes) and a syllabus, and wants to prepare for an exam.
Designs a realistic, execution-aware biomedical study version under explicit constraints of samples, time, budget, data access, lab capacity, team skill, and validation resources.
Teach the agent how a website works by recording a real user-driven Chrome session, then replay the learned action with different inputs.
Evaluate a FlowGoal against its evidence ledger and update lifecycle status to one of {pass, incomplete, fail, needs_human_review, blocked} by running deterministic verification…
Apply Bloom's revised taxonomy to classify learning objectives and design assessments across six cognitive levels.
Apply constructivist learning theory to design instruction based on active knowledge construction, scaffolding, and the zone of proximal development.
Apply Hierarchical Linear Modeling (HLM) to analyze nested data structures with random intercepts and slopes, accounting for intra-class correlation and cross-level interactions.
This skill should be used when the user says \"manage my classroom\", \"create a course\", \"list my classes\", \"add a student to a course\", \"assign coursework\", \"invite a…
Educational pack for holomorphic dynamics, complex iteration, fractal geometry, and data-driven dynamics (DMD/Koopman).
Assign story points to Jira issues using the GCP HCP pointing rubric. Recursively walks feature -> epic -> story/task hierarchies and points everything that isn't already pointed.
Adapts an existing K-12 lesson (math, ELA, science, or social studies) for students at different proficiency levels (below / at / above grade level).
Creates a lesson plan, student-facing materials, and observation template. Load this skill BEFORE asking the teacher any clarifying question about grade, subject, topic, standard,…
Comprehensive guide to Learning Path patterns for the Plataforma B2B de treinamento técnico corporativo educational platform.
Use this skill when a developer wants to annotate their LLM outputs, set up an annotation process, or improve existing annotations.
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions di — from…
Comprehensive guide to localStorage patterns for the Ultrathink educational platform. This skill covers schema design, error handling strategies, quota management, and…
Use ONLY when the user says they do not know which master or which teaching mode to use — 不知道问谁, 该找哪位祖师, 该用哪个模式, 有哪些法师, which master should I ask, help me choose.
This skill trains machine learning models using automated workflows. It analyzes datasets, selects appropriate model types (classification, regression, etc.), configures training…
Use this skill when someone needs to design, build, or structure training content they will deliver to others.
next-generation-education-advisor — 家族宪章起草/家族委员会设计/二代培养。适用情形：用户说"next-generation-education-advisor"...
Build safe Oak Curriculum API learning flows. Use this skill when Oak endpoints, curriculum maps, or child-facing Apps SDK guidance are needed.
个人信息保护影响评估（PIA）顾问——指导企业完成PIPL要求的 个人信息保护影响评估（PIPIA/PIA），评估数据处理活动的风险 并出具评估报告。适用情形：用户说"要做PIA评估"、"个人信息 保护影响评估怎么做"、"PIA报告模板"、"新功能上线前PIA"、 "数据共享需要做PIA吗"。
Designs a structured real-world evidence study using EHR, claims, or registry data, with explicit handling of time zero, eligibility windows, exposure definitions, outcome…
This skill should be used when the user needs human-run reference check prompts and note templates tied to the role rubric.
Refine quiz questions in TelNetQuiz CMS production data at cli/content/data/prod/chapter-*.json. Plan-first audit of each question against PUEBI/EYD ejaan, KBBI vocabulary, SPOK…
Use when after merging methylation calls across all samples using unite() to create a methylBase object, apply this skill to characterize whether replicate samples cluster…
Use this skill when the student asks about the SDLE exam structure, format, scoring, sections, time limits, or passing criteria.
This skill should be used to retrospectively scan all project session logs for unaddressed deferred items and unrecorded knowledge/lessons insights, cross-reference evidence to…
Generate authentic Austrian Matura (SRDP) Language in Use (LiU) tasks at B2 and B2+ levels for Oberstufe / AHS upper secondary (7. and 8. Klasse).
Semantic model for the student_club database (college student club events, members, budgets, expenses, income). Load this skill when the user is querying the student_club database.
Update, edit, and extend the Точка Сборки course project — add new Meetings, insert sections into existing lessons, fix formatting, and automatically cascade changes to INDEX.md,…
This skill automates the adaptation of pre-trained machine learning models using transfer learning techniques.
Make a correct update to Parker's prompts, system docs, rubrics, knowledge docs, training corpus, or brand outputs — and propagate the change everywhere it needs to land.
Validate quiz content quality from two POVs — Guru TKJ (curriculum alignment, technical accuracy, Bloom taxonomy, distractor-as-real-misconception, indicator coverage) and Siswa…
Transform a user's builder vision into a complete, executable GSD mission package. Use this skill whenever a user has described what they want to BUILD (a product, tool, feature,…
Disciplined wine purchase evaluation framework for building a learning-focused cellar with limited storage.
Generate interactive anatomy quizzes for medical education with multiple.
Systematic approaches to curriculum design using backward design and alignment
Annotated deep learning paper implementations with code walkthroughs
참고 자료 분석 → 커리큘럼 생성 → 프리젠테이션 작성 → 강의계획서 생성 워크플로우
A Tour of Go 공식 소스 기반 슬라이드 한글 번역 (프로젝트 파일 분석)
Conference papers on graph neural networks and graph learning
Design personalized learning plans for skills, topics, and career development
Help humans learn through partnership, not instruction.
Design and implement a complete ML pipeline for: $ARGUMENTS
Analyzing MOOC data, learning analytics, and online education metrics
Fırsat puanlama, scoring rubric ve go/no-go karar verme rehberi.
블로그에 새로운 스터디(공부하기) 콘텐츠를 추가하는 워크플로우. 챕터 구조 설계, 인프라 설정, 콘텐츠 생성을 포함.
스터디 콘텐츠에 대해 질문에 답하고, 사용자 승인 시 해당 내용을 마크다운에 추가한 뒤 배포하는 워크플로우.
Build this skill automates the adaptation of pre-trained machine learning
HSK4級レベルから流暢さを目指す学習者向け。中国語表現の使用場面・自然さを分析し、作文を「ネイティブらしい流暢な表現」に改善。bilibili等のコンテンツ理解とネイティブとの会話をサポート。実際の用例をWeb検索で提示