See what Claude plans to do for an objective before it starts, so you can course-correct early. Shows the intended approach without creating any files.
Use when loading, listing, composing, or validating graded evaluation rubrics — PASS/WARN/FAIL grading with weighted criteria and balanced PASS/FAIL anchor examples.
Study, quiz, and drill support for the Claude Certified Architect – Foundations exam.
Extract decisions, lessons, patterns, and surprises from completed phase artifacts
Maps query single-cell data to reference atlases using scArches transfer learning with scVI and scANVI models.
Selects informative features for biomarker discovery using Boruta all-relevant selection, mRMR minimum redundancy, and LASSO regularization.
Implements nested cross-validation and stratified splits for unbiased model evaluation on biomedical datasets.
Builds classification models for omics data using RandomForest, XGBoost, and logistic regression with sklearn-compatible APIs.
Explains machine learning predictions on omics data using SHAP values and LIME for feature attribution. Identifies which genes or features drive classifier decisions.
Analyzes time-to-event data using Kaplan-Meier curves, log-rank tests, and Cox proportional hazards regression with lifelines.
Deep learning-based variant calling with Google DeepVariant. Provides high accuracy for germline SNPs and indels from Illumina, PacBio, and ONT data.
Clinical study design skill for medical device trials including IDE studies and post-market studies
Export course content to any LMS. Generates IMS Common Cartridge files (.imscc) compatible with Canvas, Blackboard, Moodle, and D2L, or pushes directly to Canvas via REST — from…
Universal course import from any LMS. Reads IMS Common Cartridge files, pasted course documents, or Canvas REST API.
Evidence-based course quality audit aligned with Quality Matters standards and Community of Inquiry framework.
Apply recognition-primed decision making to agents operating under time pressure, uncertainty, and ambiguous cues.
Semantic synthesis between 2+ document versions (not git-style line merge). Input: N source docs (.tex / .md / .ipynb / .docx).
Expert-level education technology, learning management systems, and ed-tech platforms
Proactively learn about the user through onboarding and ongoing observation. Use at session start and when you notice potential preferences.
Erstellt Moodle-Kurse aus Lernfeld-Materialien (Matchpläne, Präsentationen, Arbeitsblätter). Use when: Lehrer möchte Unterrichtsmaterial in Moodle-Kursstruktur umwandeln,…
Capture, categorize, and retrieve project lessons learned for organizational learning
Intelligent learning system optimizer that analyzes session patterns, identifies improvement opportunities, and continuously enhances Alfred's performance through adaptive…
Run a retrospective after generating a CLI. Identifies systemic improvements to the Printing Press — templates, Go binary, skill instructions, catalog — so the next CLI comes out…
Geometric deep learning-based polygenic risk score prediction using PRS-Net for modeling gene interactions, enhanced disease prediction, and cross-ancestry portability.
Recall, search, continue, or analyze past conversations. Triggers on recall phrases ("what did we discuss", "continue where we left off", "we decided"), retrospective phrases ("do…
Iterative rubric-based evaluation and self-improvement loop. Builds a scoring rubric interactively, evaluates an artifact with multiple models in parallel (Codex, Gemini, Claude),…
Retrospective feedback system with Execute-Verify-Gate structural anti-skip enforcement for DevForgeAI operations.
Design training curricula and learning paths for change initiatives with competency-based learning
[INTERNAL — invocada via ag-4-teste-final] Cria cenarios QAT de alta qualidade seguindo metodologia User Story → QAT Scenario.
Use when a prompt is rough, vague, or under-specified and you want it rewritten to high quality before running it.
Generates a structured "guidelines" markdown study-guide for a book, from a fixed sources/[book]/book.pdf input to a fixed vaults/[book]/book-guidelines.md output.
提议并执行 rubric 或 bucket 升级。两种模式：**完整 rubric bump**（最高风险动作，5 步强制 + 跨模型审核）和 **--bucket-only 轻量重校**（只换 bucket 边界，不动 rubric 公式）。**Phase 2 强制走 cheat-score-blind sub-agent 给校准池重打分**——不接受…
从对标账号导入 script + 数据 → 拆 pattern + 派生 base rubric 信号 → 写到 benchmark.md / script_patterns.md / rubric_notes.md。**这是工具最早期信号的来源**——cold-start 用户没自己历史时全靠对标，发过历史的用户也建议至少 1 个对标做 sanity…
给所有想把"感觉"变成可校准预测的内容创作者。**方法论通用**——打分 → 盲预测 → T+3d 复盘 → 进化 rubric 的循环适用任何能被量化（播放 / 阅读 / 收听 / 点击）的内容。**rubric 是循环的内容，不是循环本身**——当前内置一份观点视频 rubric（参考博主 25+ 视频拟合），其他形态可借这套起步并 bump…
从复盘评论数据派生 / 刷新账号的受众画像，写入 audience.md。这是和 rubric 平行的第二个派生物——rubric 答"怎么打分"，persona 答"谁在看"。cheat-seed 选题 / 写稿时读它。**audience.md 含实绩信号，cheat-score-blind 硬禁读**。触发词："构造受众画像"/"更新…
从 candidates.md 里按当前 rubric 排序推荐 top N 选题，每条带 composite + 一句 rationale + 锚点对比。**candidates 不存在时给引导而非报错**。触发词："推荐选题"/"next topic"/"下一篇做什么"/"recommend topics"/"挑一个选题"。
T+N 天数据回收 + 复盘 + 把实绩观察写入 rubric-memo.md。这是校准循环的反馈环节——不复盘的预测等于占星。触发词："复盘 [path]"/"retro this"/"T+3d 数据来了"/"抓数据 [path]"/"把这篇复盘了"。
给单篇稿子打 rubric 分。**只在控制台输出，不写文件，不预测**。触发词："打分这篇 [path]"/"score this [path]"/"给这稿子打分"/"先打分看看"。是 cheat-predict 之前的轻量探索动作。
INTERNAL sub-agent for blind 9-dim rubric scoring. **NOT a user-facing skill — do NOT invoke from main conversation.** Called via Task tool by cheat-score / cheat-predict /…
Audits a top-level Makefile against 29 deterministic checks (strict-shell pin, `.SHELLFLAGS`, `MAKEFLAGS` warnings, `.PHONY` coverage, tab-indent, header comment, help-target…
Audit and improve project conventions files (AGENTS.md, CLAUDE.md, GEMINI.md). Scans for all conventions files, evaluates quality against a scoring rubric, outputs a quality…
This skill should be used when the user asks to "bootstrap few-shot examples", "generate demonstrations", "use BootstrapFewShot", "optimize with limited data", "create training…
This skill should be used when the user asks to "fine-tune a DSPy model", "distill a program into weights", "use BootstrapFinetune", "create a student model", "reduce inf — from…
This skill should be used when the user asks to "fine-tune a DSPy model", "distill a program into weights", "use BootstrapFinetune", "create a student model", "reduce inf — from…
Take an educational approach to explain a block of code, a function, a coding convention, or a code snippet provided inline.
Bidirectional sync between a fork project and Foundation_template using git subtree. Pull canonical skills/agents/lessons into the fork, or push contributions back.
Sweep the open `` backlog for existing issues that could be labelled as good first issues.
Capture lessons after fixing a bug or receiving a correction — ecto, liveview, oban, iron law mistakes. Use when the user corrects your approach or teaches a pattern.
Закрыть занятие, открытое скиллом /lesson. Финализирует lesson/YYYY-MM-DD.md (frontmatter status, метаданные времени, длительность), делает commit + push в репо personal-guide.
Transform text into Mainland China Mandarin （中國大陸普通話） — the everyday spoken and media register of the People's Republic of China.
Capture reusable lessons after a completed MAP workflow. Use when a MAP run has finished and you want rules written to `.claude/rules/learned/` from a workflow summary or handoff.
操作 BKN（Business Knowledge Network）平台的统一 CLI `openbkn` —— 知识网络 构建/查询（Schema：对象/关系/行动类型、指标、概念组；实例与语义搜索； push/pull/validate；从 Vega Catalog 或 CSV 建网）、资源、Vega Catalog 与 索引构建任务、Context…
Score work/current/plan.md against a 6-dimension rubric using a 3-judge cross-vendor LLM panel; write a structured record to ~/.yakos-state/plan-quality-log.ndjson
Autonomous developer workflow for a single GitHub issue dispatched by the pm orchestrator on the Headball board-game repo.
Triage the review findings on a pull request — read every review and review comment (from the adversarial-review bot or a human), score each finding on a four-dimension rubric…
Prepara lo studente a un esame con una semplice interrogazione conversazionale basata sui riassunti di un'intera materia SpaccaScuola.
Run a prompt against a golden dataset and report per-rubric regression vs the prior pinned version, not just an aggregate score
Test your knowledge with dynamically generated concept questions drawn from your actual projects and experiences
Autonomous QA tester that systematically tests every rdst command via tmux harness, applies a quality rubric, and files bugs in beads
Turn student course evaluations (free-text + numeric) into an actionable teaching-improvement plan — the teaching analogue of /respond-to-referees.