আপনার এজেন্টের জন্য উপযুক্ত সক্ষমতা খুঁজে নিন।
Dereplication only - match observed 13C shifts against reference databases to identify known compounds. Use for quick checks if a compound is already known before deciding whether full CASE is needed.
Support clinical trial safety planning using FDA adverse event data. Use when users ask about safety monitoring plans, protocol safety sections, comparator drug safety, or special population considerations for clinical trials.
Remove pattern filters that second-guess RL model predictions. Trigger when: (1) signals show past threshold but status is HOLD, (2) pattern filter blocks model signals, (3) external gates contradict trained model, (4) dashboard shows disconnect between signal strength and action.
Expert guidance for nautical sail (vela) membranes and thin-structure modeling with numerical stabilization. Use for questions about unstable or divergent computations, nonlinear solve failures, time integration instability, conditioning or preconditioning, contact/constraints, or FSI issues in tensioned membrane or thin-shell structures for sails and rigging.
Escalation ladder for hardened/minified/low-signal targets using observation-first instrumentation and baseline/stimulus diffs.
Validates ReadyFrame material takeoffs against all system rules and specifications to catch errors before materials are ordered. Use when validating takeoffs, checking material quantities, reviewing ReadyFrame compliance, verifying plate ratios, checking stud counts, validating opening components, ensuring grade assignments are correct, or when asked to "check this takeoff", "validate materials", "review for errors", or "does this look right". Critical for quality assurance before ordering materials.
Given a research goal, use existing skills, training reports, and references to propose a small, concrete experiment plan.
审计Registry是否与设计artifacts保持一致，生成同步率报告和遗漏清单。当完成设计后、CONSTRAINT验收前使用，避免Registry不一致导致验收失败。
验证一个心理学论文的实验中使用的刺激是否可复现。在开始处理一个心理学论文原始刺激的代码复现工作时，使用这个技能来检验论文是否满足复现要求。
从心理学/认知科学论文原文、论文中的刺激插图(<workspace>/paper/...)、实验数据与参考代码(<workspace>/data/...)中，抽取复现实验所需的全部实现信息，生成严格可追溯、可核验引用的 exp_design.md；输出必须以 stimkit 为唯一刺激实现框架来表述参数、坐标、形状与渲染逻辑，并包含 Evidence Index、Fact Ledger、trial 流程、条件枚举、随机化/反平衡规则、数据字段↔实现参数映射。
Domain knowledge and workflows for pile load testing reports compliant with IS 2911 (Part 4) - 2013. Use when working on test calculations, report generation, PDF templates, pass/fail criteria, or adding new test types (IVPLT, RVPLT, Lateral, Uplift). This skill encodes Indian Standard formulas, acceptance criteria, report structure requirements, and chart specifications for pile foundation testing.
Design rigorous experiments before running them. Use when planning experiments, testing hypotheses, or designing ablation studies.
完了前検証スキル。完了宣言前に検証コマンドを実行し、出力を自分で確認することを必須とする。
Generate standardized CNC setup sheets for MNMUK machine shop. Covers DMG MORI mills/lathes, CITIZEN Swiss, MITSUBISHI EDM, and Haas machines. USE WHEN user says 'setup sheet', 'create setup', 'job setup', 'machine setup', 'tooling list', 'fixture setup', or 'new job' for any CNC operation.
"Is this ACTUALLY verified, or did I just say it is?" - Ralph-wiggum methodology applied to factual accuracy. Use when (1) claims require evidence not assumption, (2) verification must be demonstrable, (3) single-pass investigation insufficient, (4) factual accuracy is critical. Provides the loop logic: iterate until verification thresholds met. Does NOT trigger for: opinions, preferences, how-to instructions, or when user explicitly wants quick answer.
Randomly select items from lists using various algorithms for fair and unbiased selection
Design Science Research Methodology for rigorous artifact development. Use this skill when: (1) Creating new tools, frameworks, or systems that solve real problems (2) Need structured approach to build-evaluate-iterate cycles (3) Want scientific rigor in development process (4) Evaluating artifacts against clear criteria (5) Documenting research contributions systematically Based on Hevner et al. (2004) and Peffers et al. (2007) - foundational DSR papers.
