All Agent Skills
41,263 results
- RevieweyelockReview code changes systematically: 1. Check for security vulnerabilities (OWASP top 10) 2. Identify performance issues 3. Verify test coverage 4. Assess readability and maintainability
- Reviewzhuga79Локализация РФ. Проверка договора с контрагентом, соглашения о конфиденциальности (NDA) или подписки на ПО (SaaS) против плейбука команды по нормам ГК РФ. Определяет структуру договора по заголовкам, маршрутизирует на нужный скилл (vendor-agreement-review, nda-review, saas-msa-review) и собирает результат в единый меморандум.
- Review ArchitectureMalcolmMcNeelyReview where a ticket's change sits and which way its dependencies point, against this repo's placement rules and boundary checks, and report under an Architecture heading.
- Review ChangesMalcolmMcNeelyReview the changes since a fixed point (commit, branch, tag, or merge-base), or an uncommitted change, along three axes — Standards (does the code follow this repo's documented coding standards?), Spec (does the code match what the originating ticket or spec asked for?) and Architecture (is it in the right module, pointing the right way?).
- Review Circusrhawk117Review a diff, branch, ticket, or whole codebase with the mightymodels persona reviewers. One AskUserQuestion gate sets depth (quick runs its reviewers on sonnet, standard and deep on opus), persona emphasis, and scope; the `review` tool records the run, mightymodels review-metrics and review-signals measure, merge-vader and uncle-bob report, and the tool reads their reports and merges…
- Review Figureshongtongzhou-design综述文献图拼板。当综述初稿按大纲用图计划需要从论文 PDF 裁源图、组 panel，或不能拼时改为引用 Fig.n 时使用。裁切 fail-closed；排版用随包脚本，不改源图数据含义。
- Review Fix Address BotsbiwIntegrate the PR base, run persistent read-only reviewers, fix and re-review findings, validate with repo-native commands, address review bots, and compare model quality.
- Review Frameworkhongtongzhou-design综述框架构造规范。当用户要求设计综述/论文的章节框架，或综述流水线中「综述大纲」一步时使用。先判定综述形态，从精读文献前言与笔记的局限/可引用点提炼带类型标注的研究空白清单，拆解 适量有代表性的综述为五要素范式卡片，以核心问题和证据综合为主线、范式为参考构造框架，产出含覆盖声明、框架推演段与完成自评的 outline.md。
- Review IssuesgwpicardRead every open issue in this repository, group them by theme, and name the best next piece to pick up. For a maintainer deciding what to work on. Reports only; it never edits an issue or applies a label. Load it by its path when you want it.
- Review Portfolio Evidencexinglin-liDate: 2026-09-24 --- name: review-portfolio-evidence description: Challenge one sealed Portfolio book against the Analyst's findings and name the real major negatives in judgment fields, never a route. --- What to name 1. Read the bundle's index (`README.md`) first, then every file it lists under Files, including holdings, findings and coverage. The bundle is complete; there is nothing to fetch.
- Review Public DocsgwpicardReview the shipped prose, site pages and release notes before a release. Load by path.
- Review RepliescodebywaterПишет ответы на отзывы клиентов для Яндекс Карт, 2ГИС, Wildberries, Ozon, Авито, Google Maps и соцсетей. Используй, когда пользователь просит ответить на отзыв, разобрать негатив, обработать пачку отзывов или вставляет текст отзыва клиента.
- Review SpecMalcolmMcNeelyReview a ticket's change against what the ticket asked for, and report the gaps under a Spec heading.
- Review StandardsMalcolmMcNeelyReview a ticket's change against this repo's documented coding standards and its review file, and report under a Standards heading.
- Review Writinghongtongzhou-design英文综述写作规范。当用户要求基于文献笔记与引文库撰写学术综述（大纲、初稿、润色定稿任一阶段）时使用。约束综合而非堆砌（观点先行、引用为证）、扩写只加可回溯证据、禁止凑字数与防御性套话、引用只用 [@bib键]、严禁编造文献、图表占位不虚构数据、无依据论断标 [待核实]、润色只改表达不改观点。
- Reviewing Pull RequestsbbrowningUse when user mentions reviewing PRs, provides GitHub PR URLs/numbers, or discusses code review. Provides structured analysis of code quality, backward compatibility, security issues, test coverage, and unaddressed comments with categorized findings (Critical/High/Medium/Low).
- Reviewing CodebostonaholicReviews a code diff (PR, branch, commit range, working tree, or a diff already in the conversation) in a fresh-context read-only subagent, because a session holding the conversation is a biased reviewer, and returns Conventional Comments findings with an APPROVE, REQUEST CHANGES, or COMMENT verdict.
- Reviewing Design DocsbostonaholicReviews a technical design document or RFC adversarially in a fresh-context read-only subagent (coverage, decisions, edge cases, consistency, risks, citations, scope) and returns findings with a verdict. Use when asked to review a design doc, RFC, or technical design. Not for code diffs; use reviewing-code.
- RhinoalivirgoAutomate Rhino modeling through RhinoCommon, work with Grasshopper data trees, and configure Rhino.Compute workflows.
- RhoststarfieldRun commands and perform explicit file, session, tunnel, or diagnostic operations on SSH-reachable hosts through an installed rhost CLI. Use when work belongs on a remote host and OpenSSH should retain authentication and host-key ownership.
- Ripgrep Over Grep CommandalivirgoSearch code with bounded matches, file filters, and structured search tools when available.
- Roblox Agent Checksm4bwavVerify Roblox Luau code without opening Studio, the way an agent should before saying a change is done: one script (rbx_check.py) runs rojo build, rojo sourcemap, selene, stylua --check, luau-lsp analyze with the Roblox type definitions, and an optional Lune test, and prints one JSON report; plus the verification ladder (static checks, Lune unit tests, place-file assertions with @lune/roblox…
- Roblox Agent Cloudm4bwavUse Roblox Open Cloud from an agent without Studio: run Luau headlessly on a real Roblox server (Luau Execution: create a task, poll it, read results and logs), run engine-level Jest Roblox tests that way in CI, and save or publish a place version from a built .rbxl, through one stdlib script (rbx_cloud.py) that reads the API key from the environment and prints one JSON object.
- Roblox Agent Projectm4bwavPut a Roblox game's code on disk so an AI coding agent can edit it as ordinary files under Git: choose between Studio's Script Sync and Rojo, set up the Rokit toolchain (rojo, StyLua, selene, luau-lsp, lune, wally or pesde) in a rokit.toml, scaffold or convert a project (rojo init, rojo syncback), keep one writer per script so Studio, sync and MCP edits never fight, and set up luau-lsp for…