Pianifica una causa civile con calcolo contributo unificato, scadenze processuali post-Cartabia, termini impugnazione e preventivo costi.
Anwendungsfall: der erwartete Leistungserfolg endgültig nicht eingetreten ist. Normen: § 812 Abs. 1 S. 2 Alt. 2 BGB.
Analyze cause-and-effect relationships in the Semantica knowledge graph — causal chains, interventions, counterfactuals, and causal influence scores.
因果基因组学 skill。用于 Mendelian randomization、colocalization、fine mapping、pleiotropy、Steiger filtering、mediation、eQTL/mQTL/pQTL 与 GWAS 信号整合和敏感性分析交接。
Determine cause-and-effect relationships using propensity scoring, instrumental variables, and causal graphs for policy evaluation and treatment effects
Apply causal inference methods for treatment effect estimation and uplift modeling
Expert causal reasoning and mental model construction for diagnosis and prediction in complex domains
Causal inference specialist for causal discovery, counterfactual reasoning, and effect estimationUse when "causal inference, causal discovery, counterfactual, intervention effect,…
Causal reasoning in historical analysis. Covers distinguishing immediate from underlying causes, tracing chains of causation across time scales, identifying unintended…
Systematic Fishbone analysis exploring problem causes across six categories
Produce reviewable starter set with validation, safety checks, and structured output. Use when a teacher, student, or literacy-resource author needs this bounded workflow and will…
Use when intentful behavior evaluation itself is the task and the repo should run Cautilus's checked-in workflow instead of reconstructing compare, held-out, and review commands…
Semi-auto mode. Orchestrates the full implementation pipeline after human-approved spec review. Runs ctdd, simplify, cverify, cupdate-arch, cdocs, then creates a PR.
Use when packaging a CAV (Computer Aided Verification) artifact for the Artifact Evaluation Committee (AEC), covering the three badges (Available / Functional / Reusable), the…
Use when preparing an accepted CAV (Computer Aided Verification) paper for its Springer LNCS open-access camera-ready, covering de-anonymization for the previously double-blind…
Use when strengthening CAV (Computer Aided Verification) reproducibility, covering benchmark provenance (SV-COMP/SMT-COMP/HWMCC/VNN-COMP set revisions), pinned tool and baseline…
Use when reasoning about how a CAV (Computer Aided Verification) submission is evaluated, covering the two-stage reviewing process (two reviews then an early-reject filter, then…
Use when auditing a CAV (Computer Aided Verification) submission for portal readiness, covering the four submission categories (Regular / Short Tool / Short Application /…
Use when deciding what belongs in a CAV (Computer Aided Verification) paper body versus its optional appendix and artifact, covering the LNCS page limits, the rule that reviewers…
Use when deciding whether a formal-methods project belongs at CAV (Computer Aided Verification) or should be routed to TACAS, FMCAD, VMCAI, LPAR/IJCAR, POPL/PLDI/OOPSLA, or a…
Use when planning a CAV (Computer Aided Verification) project timeline from venue and category selection through submission, the two-stage review with early reject and rebuttal,…
Use when revising a CAV (Computer Aided Verification) paper for a precise verification contribution on the first page, an explicit soundness/completeness statement,…
Implementation and maintenance guide for NullPlayer's standalone and embedded Cava spectrum analyzers, including DSP, rendering, scoped settings, skin-following colors, resets,…
Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), o — from…
How to write Cavekit-quality kits that AI agents can consume effectively. Covers implementation-agnostic cavekit design, testable acceptance criteria, hierarchical structure,…
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens.
Find every LLM workflow in the current repository and label it, so Caveman Cloud groups spend by what the code actually does (support-reply, nightly-digest) instead of one…
Review Caveman Cloud evidence read-only: costs, Cave Score, Cave Plan, workflows, traces, latency, errors, compression, routing, and verified savings.
Read-only repository explorer. Use PROACTIVELY for cold-start exploration, broad cross-file localization, or when a direct search has failed and you need to find where something…
Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode.
Close the loop on a Caveman learn report — review the ranked token sinks and apply cost-lowering fixes (trim config, offload recurring context to cavemem) with per-edit consent.
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy.
Turn Caveman's exact report-only repository observations into an operator-chosen optimization candidate with a paired baseline/candidate evaluation.
Terse output mode for Claude Code agents. Injects the Caveman system prompt to force compact phase reports, emoji-only status, single-line summaries, and a minimal final table.
Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix.
Wire the current repository through the Caveman Cloud gateway so every LLM request is measured — cost, tokens, latency — with zero behavior change.
Ультра-сжатый режим общения на русском. Использует специфические приёмы русского языка: pro-drop местоимений, тире вместо связки, краткие формы прилагательных, императив вместо…
Генерация кратких сообщений коммита в формате Conventional Commits. Используй когда пользователь просит сгенерировать коммит, описание изменений для git, или вызывает…
Қазақ тіліндегі ультра-сығылған сөйлесу режимі. Қазақ тілінің ӨЗ ерекше тәсілдерін қолданады: агглютинация (жалғаулар тізбегі), көсемше -ып/-іп, тәуелдік жалғауы (изафет), ырықсыз…
Ультра-стиснутий режим спілкування українською. Pro-drop, тире замість зв'язки, short forms, наказовий спосіб, English tech terms.
Generate short commit messages in Conventional Commits format. Use when user asks to generate commit, describe changes for git, or calls /cavemenko-commit.
Compress documents, notes, specs to ultra-short version. Use when user asks to compress, shorten, or summarize text, or calls /cavemenko-compress.
One-line code review comments. Use when user asks to review code, check changes, or calls /cavemenko-review.
Translate English tech docs to compressed Ukrainian. Use when user asks to translate docs, README, or technical text, or calls /cavemenko-translate.
Cancer genomics (TCGA et al.) via cBioPortal REST API. Retrieve somatic mutations, CNAs, expression, clinical data (survival/stage/treatment) across thousands of studies.
Register maintained or ephemeral Git checkouts with codebase-memory-mcp, keep long-lived indexes current through non-clobbering Git hooks, and tear down ephemeral indexes by exact…
Drive business growth with partnerships, market expansion, deal-making, and commercial strategy.
Drafts U.S. Customs and Border Protection binding ruling requests under 19 CFR Part 177 for tariff classification, valuation, origin, and marking determinations.
Publish @blit386/kit and create-blit386 to npm following ./PUBLISHING.md. Publishing is manual-only (pnpm publish from
Sync cc-settings with upstream Claude Code (maintainer) or pull the latest cc-settings (user). Triggers "sync with claude code", "changelog sync", "upstream sync" (sync mode);…
Agent 配置設計指南 — 基於 Claude Code 6 個 built-in agent 的逆向分析。Use when: 設計新 agent、優化現有 agent prompt、決定工具/模型配置、撰寫 dispatch prompt。
Use when designing AskUserQuestion tool calls - covers schema constraints, effectiveness patterns, and known issues.
Corpus Callosum CLI dokümantasyon pipeline komutlarını öğretir. TETİKLE: Kullanıcı "doküman üret", "md güncelle", "doc yap", "doc pipeline", "tree oluştur", "NLM sync", "schema…
Review code formatting and documentation using 74-item checklist from Code Complete. Two modes: CHECKER executes checklists with evidence tables, APPLIER guides layout decisions…
CC-Codex 协作讨论。自由话题驱动的 CC-Codex 协作工具，Battle Loop 辩论机制。关键词: 审查, review, 让codex看看, codex审查, 帮我审查, 讨论, discuss, battle, 让codex检查, 发给codex, 话题, topic, 代码审查, 架构讨论, 技术决策
Use when adding rules, commands, or skills to dotfiles - decides global vs project-local placement
Use when optimizing MCP token usage, understanding Tool Search thresholds, or deciding MCP vs skills for token efficiency. For plugin MCP bundling, use plugin-dev:mcp-integration.
Use when adding allow/deny rules to Claude Code, granting project permissions, troubleshooting "permission denied" errors, "skill requires approval" prompts, or setting up shared…
AI Agent 成本工程 — 基於 Claude Code 的成本追蹤、prompt cache 最佳化、token 預算控制逆向分析。Use when: 優化 token 消耗、設計成本控制機制、分析 cache 效率、選擇模型配置。
Use when drafting the cover letter (and optional presubmission inquiry) for a Cancer Cell (Cell Press) submission — framing significance, fit, novelty, and suggested/excluded…