Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction.
A roleplay-based framework to identify product friction and bridge the gap between internal knowledge and the actual customer experience.
Design or audit one end-to-end customer-support operating system across self-service, intake, identity-safe diagnostics, taxonomy, queues, severity, routing, SLAs, grounded…
Эксперт customer training. Используй для onboarding программ, training materials и certification paths.
Aide à créer ou améliorer un CV structuré, percutant et adapté au poste visé. À utiliser quand l'utilisateur veut rédiger, refaire ou optimiser son CV.
Evaluate a resume against the CV Builder rubric and return a scored, schema-valid EvalResult. Use when the user wants their CV or resume scored, critiqued, or checked for ATS…
Real-world ROI case study for healthcare content automation pipeline. Clínica Mente Saudável case with validated metrics - 99.4% time reduction (4h15m to 1.5min), 92.4% cost…
Produce reviewable controlled word list with validation, safety checks, and structured output. Use when a teacher, tutor, or literacy specialist needs this bounded workflow and…
Datenbankrecht für Bildungsdatenbanken: §§ 87a-87e UrhG für Lehrmaterialdatenbanken und Hochschularchive, Schranken nach § 60a UrhG (Bildung und Unterricht), Herstellerrecht bei…
Prüft Datenschutz in Schule, Lernplattform und Elternkommunikation im Schulrecht Länder.
Track case deadlines — add, cross-case rollup report, update, complete, close. Warns at configurable thresholds (default 14/7/3/1 days); overdue items stay flagged until resolved.
Interactive debate and argument practice with structured feedback, counterargument generation, logical fallacy identification, and scoring rubrics.
Build a debt-payoff plan across multiple debts using the avalanche or snowball method. Use when asked to pay off debt, tackle credit cards/loans, or choose between avalanche and…
Judge a past decision by its PROCESS, not its outcome — because good decisions lose and bad decisions win, and teams that can't tell the difference learn the wrong lessons.
Scores and strengthens startup pitch decks (pre-seed through Series A) against 35 investor-grade criteria grounded in Sequoia, DocSend, YC, a16z, and Carta data.
Review a deck against a rubric instead of taste — the five dimensions (argument, evidence, density, arc, honesty), the severity-sorted feedback that separates broken from…
Course-correct when artifacts overfit to conversation context. Invoke when examples, names, or language are too specific to current work.
Use when you have UPLC-HRMS data (ThermoFisher, Agilent, or MSConvert-compatible
Use when when you need to construct a dual-branch neural network encoder that processes two augmented versions of the same input (e.g., ion images in COL or ISO mode) and must…
Use when you have preprocessed mass spectrometry spectra (tokenized m/z and intensity pairs or feature matrices) and a trained deep learning model checkpoint, and you need to…
Use when you have a trained deep learning model and want to quantify prediction uncertainty for each input pair or decision point.
Use when you have downloaded the LC-MS spectral peak dataset (DOI 10.25345/C5FD2F)
Use when you have raw or preprocessed mass spectrometry feature matrices (e.g., from low mass resolution or sparse acquisition) and want to enhance signal quality and spatial…
Use when you have a pre-trained deep learning encoder (e.g., TCN spectrum encoder trained on a large corpus) and want to adapt it to a new task (e.
Expert guidance for deep learning, transformers, diffusion models, and LLM development with PyTorch, Transformers, Diffusers, and Gradio.
Use when when you have an unknown compound's mass spectrum (m/z peaks and intensities in .mgf or equivalent format with mandatory PRECURSOR_MZ and IONMODE tags) and need — from…
Use when training a CNN model from scratch on LCMS peak classification tasks (or similar image-like batched data) where you need to confirm the model reaches target performance…
Deep learning-based variant calling with Google DeepVariant. Provides high accuracy for germline SNPs and indels from Illumina, PacBio, and ONT data.
Builds measurable validation criteria when no existing standards apply. Invoked by team agents during review.
Produce reviewable child-level definition/sentence with validation, safety checks, and structured output.
Use when educators need to validate if their lesson plan covers all 3 Delegation subcategories (Problem/Platform/Task Awareness).
Structures health education program design with behavior change theory and outcome evaluation. Use when designing health education, planning health promotion, or evaluating…
Turn a fuzzy repeatable job into a deterministic, versioned skill so the output is the same quality every single run — not "good when I'm watching, random when I'm not." One skill…
Scaffold a new GPU lesson using forge_scene.h for the rendering baseline
Tags harness-decomposed curriculum items (KUDs, LTs, criteria) with a school's developmental band metadata while preserving source voice and labels.
Eigenanteil und Grundausstattung der Hochschule sauber von DFG-Foerderung abgrenzen: Was muss die Hochschule stellen (Buero, Standardrechner, Sekretariat, Bibliothek), was darf…
Analyzes clinical diagnostic accuracy studies for bias using the QUADAS-2 tool. Use when Claude needs to assess the quality, risk of bias, or applicability of diagnostic accuracy…
Audita diagramas de mediação (path diagrams) em 6 domínios com rubrica de 4 níveis (Excelente, Adequado, Insuficiente, Crítico), score ponderado 0–100 e veredito com prioridades…
Design a diary study plan with prompts, duration, participant criteria, and analysis framework. Use when you need to understand user behavior over time in natural contexts.
Document pedagogical design decisions in educational materials using the didactic LaTeX package and \ltnote command.
Client education, meal planning communication, behavior change counseling, and motivational strategies
Digital art tools, techniques, and workflows for art education. Covers raster and vector workflows, digital painting, photo manipulation, generative and procedural art, 3D…
A two-spread digital e-guide preview — page 1 is a cover (display title, author, "What's inside" stats, table of contents teaser); page 2 is a spread (lesson body with pull-quote…
Identify and navigate genuine dilemmas in curriculum, school, or community contexts — tensions between competing goods that cannot be solved, only navigated.
Write prompts, system instructions, agent directives, slash commands, and skill descriptions using two stacked layers — outcome-first (define the destination, success criteria,…
Design a sequence where students compare AI's handling of the same question across disciplines, developing a mental model of where AI is reliable vs.
Meta-skill that orchestrates the discourse skill suite: routes between steel-man-argument, socratic-questioning, toulmin-argument-analysis, logical-fallacy-detector,…
Visual quality rubric for Triptych display tabs — panel-size constraints (800–1200px), dark theme alignment, hierarchy in a narrow panel, named tabs, "live" vs "dead" displays.
Turn scattered project rules, workflows, and hard-won lessons into a structured skills directory that future agents can route through before making changes.
distillation v2.0（第二輪退役 stub） — 三 phase 拆三層回歸：collect-evidence 進 `.claude/rules/workflow.md` §Distillation 對話準則、propose 進 session-start hook（lesson-pressure）、harden 進 `/harden`…
Use when a bug fix, architectural change, interface contract update, or recurring pitfall has been resolved and has clear reuse value — to record a durable lesson in project…
当你（作为某个经验蒸馏流程的执行者，例如把一份复盘文档里的候选经验落成项目资产）要判断一条候选经验该落成纪律文档 / skill / workflow / subagent 中的哪一种、以及落地时该怎么写才不走样时用。教一套归宿判断决策树 + 四类资产各自的落地手艺与反模式：事实性 / 项目专属的经验归纪律文档（条目带 why）；可复用的判断力 /…
Generalized rubric-driven optimization loop for improving or achieving a goal through repeated evaluation and refinement.
Stap 7 — verwerkt lessons learned van de afgeronde taak en voert compacte systeem-checks uit. Schrijft rapport in task doc. Volledige systeem-checks staan in doc-audit.
Comprehensive guide for creating by-example tutorials - code-first learning path with 75-90 heavily annotated examples achieving 95% language coverage.
Universal methodology for verifying factual correctness in documentation using WebSearch and WebFetch tools.
Generate or update documentation for the AI Hero API by reading the source code at ~/repos/ai/course-builder.
Design a complete document-based history lesson using the Reading Like a Historian four-part structure.
Update documentation based on lessons learned. Use after completing work to capture learnings and prevent future issues.
Prüft Drittversuch, Härtefall und zusätzliche Wiederholung im Prüfungsrecht Hochschule.