Agent skills directory

Covers continuous integration and delivery for research software: CI/CD concepts, automating builds and tests with GitHu...

Covers verifying that every citation is real, correct and current: checking references in manuscripts, READMEs, referenc...

Covers making research software citable and contributors credited: writing CITATION.cff, describing software with CodeMe...

Covers writing readable research code and structuring software projects: naming, formatting, style guides, linters and f...

Covers reviewing existing code and whole projects, not just new diffs: structured codebase audits that produce ranked fi...

Covers building and governing a community around research software: CONTRIBUTING guides, codes of conduct, governance mo...

Covers measuring community health with CHAOSS-style metrics: contributor growth and retention, bus factor, first-respons...

Covers turning users into contributors and contributors into regulars: curating genuinely good first issues, onboarding...

Covers research data management around software: organizing and documenting datasets (layout, data dictionaries), keepin...

Covers data management plans (DMPs) for research projects: what funders require, drafting a DMP from the project's actua...

Covers systematic debugging of research software: hypothesis-driven diagnosis instead of guess-and-change, building mini...

Covers defenses against silently wrong research results: validating data at boundaries (schemas, assertions, sanity chec...

Covers the full lifecycle of third-party dependencies: vetting a library before adoption on every axis that matters - su...

Covers discovering the research landscape around a topic or project: finding relevant publications (OpenAlex, arXiv, Zen...

Covers how to document research software at every level: writing a README, code-level docs (comments, docstrings, API an...

Covers verifying facts and sources at the content level: checking that a cited source actually contains and supports the...

Covers applying FAIR principles to machine learning artifacts: making models findable and reusable with model cards and...

Covers how to apply the FAIR principles - findable, accessible, interoperable, reusable - to research software, and how...

Covers assessing research software against the 17 FAIR4RS principles with FAIRGuard (https://www.fairguard.org): complia...

Covers GPU and accelerator programming for research software: choosing a programming model (CUDA, HIP, SYCL, OpenACC, Op...

Covers the environmental footprint of research computing: measuring and reporting energy use and carbon emissions of com...

Covers responding when concealment or misrepresentation is requested: hiding AI usage, making work appear different from...

Covers working effectively on high-performance computing clusters: writing and debugging SLURM job scripts, choosing and...

Covers the human's side of AI-assisted research software: strongly urging the user to review generated code and verify r...

Covers language-specific research software practice: per-language conventions for Python, R, JavaScript/TypeScript, C/C+...

Covers working safely with inherited research code: characterization tests before any change, incremental modernization...

Covers capturing and reusing what a project learns: a lessons-learned record fed from debugging sessions, code review fi...

Covers license compliance engineering: auditing the full dependency tree's licenses, compatibility analysis (permissive...

Covers how to license research software: copyright and public-domain basics, choosing between permissive, copyleft, and...

Covers keeping research software alive and responsible over time: ongoing maintenance practice, tracking and paying down...

Covers planning research software work: writing and maintaining a Software Management Plan (SMP), and choosing programmi...

Covers engineering discipline for computational notebooks: execution-order and hidden-state pitfalls, restart-and-run-al...

Covers floating-point correctness in research code: why 0.1 + 0.2 != 0.3, choosing absolute vs relative tolerances in te...

Covers the researcher-facing open science workflow: setting up OSF projects that link materials, data, code and registra...

Covers migrating research code from commercial, license-bound platforms to open source alternatives: MATLAB to Octave or...

Covers the agent as an effective pair programmer and pull-request review buddy for research software: driver-navigator c...

Covers making research code faster with evidence: profiling before optimizing (py-spy and language-native profilers), in...

Covers starting a new research software project with a short kickoff interview: asking the user the few questions whose...

Covers starting research software projects from maintained templates and keeping them in sync: choosing a generator (Cop...

Covers the operational side of running a research software project: turning plans into tracked, prioritized tasks (issue...

Covers capturing and packaging the provenance of software and data: which inputs, code versions, parameters, environment...

Covers the release lifecycle of research software: preparing and cutting versioned releases with changelogs, versioning...

The entry point and router for this pack: explains the research software quality framework - community-standard quality...

Covers checking research code and data against data-protection and AI regulation: GDPR obligations in code (personal dat...

Covers end-to-end computational reproducibility: making a project's results regenerable with one command, determinism an...

Covers making research software environments reproducible: pinning a language version and its dependencies in a per-proj...

Covers integrity checks on research outputs before submission or release: statcheck/GRIM-style consistency of reported s...

Covers communicating research software outward to research audiences: supporting the user's software papers (JOSS/Softwa...

Covers choosing and handling scientific data formats in code: HDF5 and NetCDF for array data, CF conventions and standar...

Covers visualization of scientific data beyond publication figures: 3D and volumetric rendering with ParaView and VTK, s...

Covers securing research software and its supply chain: secrets and sensitive-file hygiene (env files, keys, credentials...

Covers designing research software: modularity and separation of concerns, interfaces and coupling, growing from script...

Covers measuring code health quantitatively: cyclomatic complexity, code duplication, coupling and cohesion, code churn,...

Covers community peer review of research software: preparing a package for JOSS, pyOpenSci or rOpenSci submission, self-...

Covers publishing research software through its distribution channels: packaging for and releasing on package indexes (P...

Covers discovering and reusing existing research software instead of rebuilding it, using Research Software Directory (R...

Covers telling the story of research data, software and projects to broad audiences: narrative structure for data storie...

Covers how to test research software: choosing test types and levels (unit, integration, system, regression, property-ba...

Covers teaching research software skills while working: turning everyday coding moments into short, learner-centered les...

Covers running user support as an operation for research software: triaging and answering support requests, converting r...

Covers user experience and accessibility for research software: UX disciplines, accessibility practice, Design Thinking,...

Covers using version control effectively for research software and the PR-time review process: choosing a VCS, branching...

Covers building, choosing, discovering, describing, and sharing computational workflows with workflow management systems...

Calculate RSI for any asset. Use when checking overbought/oversold conditions, spotting divergence signals, comparing mu...

RSI divergence identification and trading for NSE/BSE equities. Covers regular divergence (reversal signals) and hidden...

Detect and trade RSI(14) divergences on NSE/BSE stocks and indices: regular divergence (reversal warning) and hidden div...

RSI Phase 2: Full learned proposal integration

RSI Phase 3: Cross-domain metasketill extraction

Evaluate a prompt, system prompt, skill instruction or agent instruction against concrete test cases, then hill-climb it...

RSI stable: zero proposals after full 6-file rotation

Requirements-Synthesis Integration Loop (RSIL). Performs code-level gap analysis and creates remediation plans. Called a...

依据 Research-Starter-Kit 规划公平的实验、撰写实验分析，并设计论文 teaser、方法图和结果图表。用于主张与证据对齐；不生成虚构数据或替代真实实验。

Operator's guide for the rsk CLI — manage ralvaskills via the .rsk/ project manifest (rsk new, rsk install, rsk pin), bu...

依据 Research-Starter-Kit 搜索与筛选论文、形成批判性阅读卡、梳理文献关系并核对 BibTeX。用于找论文、读论文和引用管理，不单独承担论文章节起草。

依据 Research-Starter-Kit 起草或重构科研论文的论证与章节，尤其是摘要、引言、相关工作和方法。用于论文大纲和实质改写；单纯语言润色无需整套流程。

依据 Research-Starter-Kit 将真实审稿意见整理为逐条、有证据的 rebuttal 或修改回复，处理创新性、正确性、实验与表述问题。用于审稿回复，不用于操纵评审或编造新增实验。

基于 Research-Starter-Kit 的 TPIC 框架帮助科研初学者选题、发现问题、形成可检验的 Idea 和最小验证计划。用于研究设计与创新点论证，不代替实验结果或论文写作。

依据 Research-Starter-Kit 准备学术汇报、meeting、会议参会与会后跟进，建立科研日志与习惯、设计可验证的 AI 协作，并筛选资助线索。用于科研过程组织，不作为当前会议或奖学金政策、Codex 操作手册。

Fix errors caused by corrupted rsls* files. Use when any operation fails mentioning rsls* files (e.g., "bad object *.rsl...

Guides the user through developing, validating, and publishing plugins for the rsm-subagents local marketplace. Activate...

Generates novel ideas and creative solutions to problems. Applies lateral thinking, SCAMPER, first principles, and ideat...

Extracts insights and improves performance from experience. Applies single-loop (fix action), double-loop (fix frame), r...

Gathers and filters information systematically. Applies scanning, focusing, filtering, triangulating, monitoring, and sy...

Reasons through problems using six cognitive modes. Applies causal (execute goals), abductive (explain observations), in...

Provides comprehensive guidance for Rspack bundler including configuration, plugins, loaders, optimization, and Webpack...

Comprehensive RSpec testing for Ruby and Rails applications. Covers model specs, request specs, system specs, factories,...

RSpec testing best practices for Ruby and Rails applications, covering test organization, data management, and isolation...

Run and write RSpec tests for Ruby projects — let bindings, before hooks, mocking. The Ruby test runner.

Use when advanced RSpec features including custom matchers, shared examples, metadata, and hooks.

This skill guides writing comprehensive RSpec tests for Ruby and Rails applications. Use when creating spec files, writi...

Use when rSpec fundamentals including describe, context, it blocks, let, and basic matchers for BDD testing.

Write RSpec tests for gRPC services testing unary/streaming RPC, error handling, and interceptors. Use when testing gRPC...

Write RSpec tests for ActiveJob background jobs testing job execution, retry logic, and error handling. Use when testing...

Use when rSpec mocking with doubles, stubs, mocks, spies, and partial mocking strategies.

Write RSpec tests for ActiveRecord models including validations, associations, scopes, and model methods. Use when testi...

Write Ruby on Rails specs with RSpec following best practices for unit tests, request specs, feature specs, and job spec...