Browse Skills — Page 249

routing-policy-change

vllm-project/semantic-router

Modifies routing policy after signal extraction, including matched-decision logic, candidate-model selection, and downstream looper behavior. Use when changing decision predicates, thresholds, priorities, model ranking, cost or latency routing, or other post-signal routing policy.

routing-subtour-elimination

elizaOS/eliza

Subtour-elimination methods for TSP, VRP, pickup/dropoff routing, and routing MIPs with binary arc variables. Use when route-continuity constraints may permit disconnected cycles and the model needs MTZ constraints, flow-based connectivity constraints, DFJ subset cuts, or lazy/iterative subtour cuts.

routing-table-updater

notque/vexjoy-agent

Maintain /do routing tables when skills or agents change.

rover

apollographql/skills

>

rowan

K-Dense-AI/scientific-agent-skills

Rowan is a cloud-native molecular modeling and medicinal-chemistry workflow platform with a Python API. Use for pKa and macropKa prediction, conformer and tautomer ensembles, docking and analogue docking, protein-ligand cofolding, MSA generation, molecular dynamics, permeability, descriptor workflows, and related small-molecule or protein modeling tasks. Ideal for programmatic batch screening, multi-step chemistry pipelines, and workflows that would otherwise require maintaining local HPC/GPU infrastructure.

rpi

boshu2/agentops

Run discovery, crank, validation.

rqalpha

lzwme/finance-quant-skills

RQAlpha 米筐开源事件驱动回测框架。支持A股和期货，模块化架构，可自由扩展；当用户需要快速回测A股/期货策略、使用内置数据（download-bundle）、开发Mod插件，或提及 rqalpha、米筐时使用。与 backtrader 相比，rqalpha 内置A股日线数据、安装更简便，适合快速验证；backtrader 更灵活、社区更大。若用户仅需数据获取而无回测需求，引导使用 baostock/akshare/tushare 等数据 Skill。

rrr

Soul-Brews-Studio/arra-oracle-skills-cli

Create session retrospective with AI diary and lessons learned. Use when user says "rrr", "retrospective", "wrap up session", "session summary", or at end of work session.

rrr-lite

Soul-Brews-Studio/arra-oracle-skills-cli

Quick session retrospective — what we did, what we learned. Lite version for minimal profile. Use when user says "rrr", "retrospective", "wrap up". For full version with AI diary and anti-rationalization guard, upgrade to standard (/go standard → /rrr).

rsbuild

TerminalSkills/skills

>-

rsbuild-best-practices

rstackjs/agent-skills

Rsbuild best practices for config, CLI workflow, type checking, bundle optimization, assets, and debugging. Use when writing, reviewing, or troubleshooting Rsbuild projects.

rsbuild-v2-upgrade

rstackjs/agent-skills

Use when upgrading a Rsbuild 1.x project to v2, including dependency and configuration updates.

rsdoctor-analysis

rstackjs/agent-skills

Use when analyzing Rspack/Webpack bundles from local `rsdoctor-data.json` and producing evidence-based optimization recommendations.

rslib-best-practices

rstackjs/agent-skills

Rslib best practices for config, CLI workflow, output, declaration files, dependency handling, build optimization and toolchain integration. Use when writing, reviewing, or troubleshooting Rslib projects.

rspack

partme-ai/full-stack-skills

"Provides comprehensive guidance for Rspack bundler including configuration, plugins, loaders, optimization, and Webpack compatibility. Use when the user asks about Rspack, needs to configure Rspack, optimize build performance, or migrate from Webpack."

rspack-best-practices

rstackjs/agent-skills

Rspack best practices for config, CLI workflow, type checking, CSS, bundle optimization, assets and profiling. Use when writing, reviewing, or troubleshooting Rspack projects.

rspack-debugging

rstackjs/agent-skills

Helps Rspack users and developers debug crashes or deadlocks/hangs in the Rspack build process using LLDB. Use this Skill when users encounter "Segmentation fault" errors during Rspack builds or when the build progress gets stuck.

rspack-split-chunks

rstackjs/agent-skills

>-

rspack-tracing

rstackjs/agent-skills

Comprehensive guide and toolkit for diagnosing Rspack build issues. Quickly identify where crashes/errors occur, or perform detailed performance profiling to resolve bottlenecks. Use when the user encounters build failures, slow builds, or wants to optimize Rspack performance.

rspack-v2-upgrade

rstackjs/agent-skills

Use when upgrading a Rspack 1.x project to v2, including dependency and configuration updates.

rspec-advanced

TheBushidoCollective/han

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

rspec-fundamentals

TheBushidoCollective/han

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

rspec-mocking

TheBushidoCollective/han

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

rspress-custom-theme

rstackjs/agent-skills

Customize Rspress themes using CSS variables, Layout slots, component wrapping, or component ejection. Use when a user wants to change the look and feel of an Rspress site, override theme components, add custom navigation/sidebar/footer content, inject global providers, or modify the default Rspress theme in any way. Also use when a user mentions theme/index.tsx, Layout slots, BEM class overrides, or rspress eject.

rspress-description-generator

rstackjs/agent-skills

Generate and maintain description frontmatter for Rspress documentation files (.md/.mdx). Use when a user wants to add SEO descriptions, improve search engine snippets, generate llms.txt metadata, prepare docs for AI summarization, or batch-update frontmatter across an Rspress doc site. Also use when adding new documentation pages to an Rspress project — every new doc file needs a description.

rspress-v2-upgrade

rstackjs/agent-skills

Migrate Rspress projects from v1 to v2. Use when a user asks to upgrade Rspress, follow the v1-to-v2 guide, update configs/themes, or validate the upgrade.

RSS Digest

aaronjmars/aeon

Fetch, summarize, and deliver RSS feed highlights

RSS Feed Generator

aaronjmars/aeon

Generate an Atom XML feed from articles, validate it, and notify only when it actually changes

rss-automation

aAAaqwq/AGI-Super-Team

RSS feed aggregation and monitoring. Parse RSS/Atom feeds, filter entries,

rss-fetch

vm0-ai/vm0-skills

RSS feed API for fetching news and articles. Use when user mentions "RSS", "feed", "RSS reader", "fetch feed", or asks to get news from RSS sources.

rsshub

uvwt/agentdock

Use the local RSSHub service for status checks, route URL construction, feed fetching, feed parsing, and route probing.

rst-to-myst

ray-project/ray

Convert Ray documentation pages from reStructuredText (.rst) to MyST Markdown (.md). Use when migrating existing files under doc/source/ to MyST, finishing a partial MyST migration of a directory, or when asked to convert/migrate a doc page to markdown. Covers the RST-to-MyST directive mapping, label and cross-reference preservation, sphinx-design tabs/dropdowns/card grids, doctest/testcode handling, the doc/BUILD.bazel doctest exclusions, and the build and doctest verification needed to land a clean docs PR.

rstest-best-practices

rstackjs/agent-skills

Rstest best practices for config, CLI workflow, test writing, mocking, snapshot testing, DOM testing, coverage, multi-project setup, CI integration, performance and debugging. Use when writing, reviewing, or troubleshooting Rstest test projects.

rsync

TerminalSkills/skills

>-

rt-vlm

NVIDIA-AI-Blueprints/video-search-and-summarization

>

ru-text

talkstream/ru-text

>

rubocop-configuration

TheBushidoCollective/han

Use when ruboCop configuration including YAML config, departments, inheritance, and customization.

rubocop-cops

TheBushidoCollective/han

Use when ruboCop cops including built-in cops, configuration, auto-correction, and development.

rubocop-integration

TheBushidoCollective/han

Use when ruboCop CI integration including GitHub Actions, plugins, and performance optimization.

ruby-blocks-procs-lambdas

TheBushidoCollective/han

Use when working with Ruby blocks, procs, lambdas, and functional programming patterns including closures and higher-order functions.

ruby-gems-bundler

TheBushidoCollective/han

Use when working with Ruby gems, Bundler for dependency management, creating gemspecs, and publishing gems to RubyGems.

ruby-mcp-server-generator

github/awesome-copilot

Generate a complete Model Context Protocol server project in Ruby using the official MCP Ruby SDK gem.

ruby-metaprogramming

TheBushidoCollective/han

Use when working with Ruby metaprogramming features including dynamic method definition, method_missing, class_eval, define_method, and reflection.

ruby-oop

TheBushidoCollective/han

Use when working with Ruby's object-oriented programming features including classes, modules, inheritance, mixins, and method visibility.

ruby-patterns

softspark/ai-toolkit

Ruby/Rails: blocks, metaprogramming, ActiveRecord, Sidekiq, RSpec, Sorbet, Hanami. Triggers: Ruby, Rails, ActiveRecord, Sidekiq, RSpec, Gemfile, bundler, Hanami, Sorbet.

ruby-pro

benjaminasterA/antigravity-awesome-skills

Write idiomatic Ruby code with metaprogramming, Rails patterns, and

ruby-pro-v2

diegosouzapw/awesome-omni-skills

ruby-pro workflow skill. Use this skill when the user needs Write idiomatic Ruby code with metaprogramming, Rails patterns, and performance optimization. Specializes in Ruby on Rails, gem development, and testing frameworks and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

ruby-rules

softspark/ai-toolkit

Ruby coding rules: style, patterns, security, testing. Triggers: .rb, Gemfile, .gemspec, Rails, ActiveRecord, Sidekiq, RSpec, Sorbet, rubocop.

ruby-standard-library

TheBushidoCollective/han

Use when working with Ruby's standard library including Enumerable, File I/O, Time/Date, Regular Expressions, and core classes.

rueckausnahme-art-6-abs-3

Klotzkette/claude-fuer-deutsches-recht

Prueft die Rueckausnahme vom Hochrisiko nach Art. 6 Abs. 3 KI-VO: vier Fallgruppen enge Verfahrensaufgabe Verbesserung menschlicher Taetigkeit Mustererkennung ohne Ersetzung vorbereitende Aufgabe. Sicherungsklausel Profiling natuerlicher Personen immer Hochrisiko.

rueckfragebrief-an-anbieter

Klotzkette/claude-fuer-deutsches-recht

Erstelle einen strukturierten Rueckfragebrief an den KI-Anbieter zur Klaerung der berufsrechtlichen und strafrechtlichen Pflichten. Aufbau Anschreiben Kontext drei Fragenbloecke (Verschwiegenheit Subunternehmer TOM und Drittstaat) Fragen zu Zertifizierungen und Versprechungen Frist Unterschrift. Klare praezise Fragen die der Anbieter beantworten kann.

rueckfragen-mandant

Klotzkette/claude-fuer-deutsches-recht

Generiert Rueckfragen an den Mandanten wenn das vorgelegte Material fuer eine sinnvolle Recherche nicht ausreicht oder Abgrenzungsfragen offen sind. Pflichtfragen: Was ist der wesentliche Loesungsbeitrag der Erfindung gegenueber dem Stand der Technik den der Mandant kennt; Welcher Anspruch ist der wichtigste; Welcher Markt und welche Zielstaaten; Gibt es eigene fruehere Veroeffentlichungen Anmeldungen Vortraege Messeauftritte (Eigenstand der Technik); Gibt es Konkurrenten die das Plugin in den Watch nehmen soll; Welcher Recherchezweck. Formuliert die Rueckfragen als Brief oder als Frageliste die in eine Mandantenrueckfrage uebernommen werden kann. Disclaimer keine Rechtsberatung Patentanwaeltin verantwortet die Mandantenkommunikation.

ruegeschriftsatz-erstellen

Klotzkette/claude-fuer-deutsches-recht

Ruegeschriftsatz nach § 160 Abs. 3 GWB als Pflichtvoraussetzung jeder Vergabenachpruefung. Adressat oeffentlicher Auftraggeber. Konkret bezeichneter Vergabeverstoß mit Norm und Sachverhalt. Antrag auf Abhilfe und hilfsweise Aufhebung. Unverzuegliche Einreichung bei Erkennbarkeit. Bei Nichtabhilfe Antragsfrist 15 Kalendertage zur Vergabekammer. Aufbau Sachverhalt, rechtlicher Verstoß, Beweismittel, Antrag. Form Schriftform oder qualifiziert elektronische Signatur. Schwellenwertpruefung nach § 106 GWB obligatorisch. Checkliste Rechtzeitigkeit, Bestimmtheitsgebot, Praeklusionsrisiko und Nachpruefungsstrategie enthalten.

ruff

TerminalSkills/skills

>-

ruff-recursive-fix

github/awesome-copilot

Run Ruff checks with optional scope and rule overrides, apply safe and unsafe autofixes iteratively, review each change, and resolve remaining findings with targeted edits or user decisions.

Rug Scan

aaronjmars/aeon

Assess rug-pull risk for any token on Base — ownership, mint/freeze powers, LP lock, and holder concentration rolled into one risk verdict. Keyless via Etherscan v2 + Base RPC.

rules

code-yeongyu/oh-my-openagent

Use when the user asks about Codex Rules behavior, injected project rules, supported rule file locations, matching, or environment configuration.

rules-distill

affaan-m/ECC

Scan skills to extract cross-cutting principles and distill them into rules — append, revise, or create new rule files

rules-normalize

Fr-e-d/GAAI-framework

Convert implicit or scattered project conventions into governed GAAI rule files, and create or modify rule files with integrity. Activate during Bootstrap, when creating a new rule, or when modifying an existing rule.

run

alirezarezvani/claude-skills

One-shot lifecycle command that chains init → baseline → spawn → eval → merge in a single invocation. Use when the user runs /hub:run or asks to execute a full AgentHub competition end-to-end.

run-acceptance-tests

eric861129/SKILLS_All-in-one

Guide for running acceptance tests for a Terraform provider. Use this when asked to run an acceptance test or to run a test with the prefix `TestAcc`.

run-agent

open-gitagent/opengap

Configures and runs agents with different adapters including Claude, OpenAI, CrewAI, Lyzr, and GitHub Models. Supports local execution, remote git repos, and one-shot prompts. Use when the user wants to run an agent, switch LLM providers, configure adapter settings, or launch agents from git repositories.

run-al-code-analysis

microsoft/AL

Runs CodeCop, PerTenantExtensionCop, UICop, or AppSourceCop against a temporary project through the public prerelease ALTool.

run-al-mcp-tool

microsoft/AL

Invokes one safe AL MCP tooling operation through the workflow-installed prerelease ALTool for independent reproduction of MCP and editor-tooling issues.

run-al-tests

microsoft/AL

Runs a published AL test codeunit against the provisioned BCInsider sandbox through the public prerelease ALTool.

run-apichief

dotnet/efcore

Run ApiChief in the EF Core repo to emit baselines, summaries, deltas, review files, or breaking-change checks. Use when refreshing `*.baseline.json`, preparing API review artifacts, or validating API changes.

run-brand-oem-and-supply-partnerships

Significant-Gravitas/skills-catalog

Use when the portfolio is not resell: sponsorship activations, OEM sell-through, agent ecosystems, and supply-side portfolio optimisation.

run-creator-and-affiliate-partner-programs

Significant-Gravitas/skills-catalog

Use when the portfolio includes creators, affiliates, or publishers: compensation design, brand-safety vetting, yield operations, program health.

run-evals

different-ai/openwork

Run OpenWork UI evals on a Daytona sandbox or local Electron instance. Handles sandbox creation, service startup, and eval execution via CDP browser tools.

run-execute

fabriqaai/specs.md

Execute work items based on their assigned mode (autopilot, confirm, validate). Supports single-item and multi-item (batch/wide) runs.

run-experiment

wanshuiyin/Auto-claude-code-research-in-sleep

Deploy and run ML experiments on local, remote, Vast.ai, or Modal serverless GPU. Use when user says "run experiment", "deploy to server", "跑实验", or needs to launch training jobs.

run-frequency-guard

aaronjmars/aeon

Daily per-skill run-count watchdog — checks if any capped skills exceeded their configured daily limit and alerts on breach

run-full-release

terrylica/cc-skills

Run the current repo's mise release pipeline, or bootstrap one if missing. Use when user wants to release, version bump, publish a package, or.

run-fusion-cloud-recipes

openai/community-plugins

Prepare, submit and reconcile reviewed Fusion Automation jobs with exact sources, scoped authorization and explicit budgets. Not for arbitrary model-generated cloud scripts.

run-global-partner-executive-councils

Significant-Gravitas/skills-catalog

Use when top alliances need a global executive forum: charter the council, run regional-to-global cadence, and drive every decision to an owner.

run-history-skill-builder

dongshuyan/compass-skills

Turn a completed task, browser flow, artifact pipeline, failure-recovery trace, or repeatedly refined workflow into a new reusable skill package or a reviewed skill-design plan. Use when the user asks to make a new skill from real run history, extract a reusable workflow from conversation/logs/files, summarize lessons into a new skill, or produce a plan before writing files. Do not use to upgrade an existing skill or to execute the business workflow itself.

run-history-skill-upgrader

dongshuyan/compass-skills

Use real run evidence, validation failures, source drift, platform drift, and user feedback to plan and, only after explicit approval, apply structural upgrades to an existing skill. Use when the user asks to improve an existing skill from recent runs, recurring failures, outdated sources, excessive bloat, changed platform behavior, or validated workflow feedback. Do not use to create a brand-new skill or to execute the business workflow itself.

run-hyperscaler-marketplace-co-sell

Significant-Gravitas/skills-catalog

Use when a cloud marketplace motion needs partner-side operations: listing and private-offer checks, field-team motion, fund capture, and attribution.

run-judges

closedloop-ai/claude-plugins

Orchestrate parallel judge agent execution, aggregate CaseScore results, write plan-judges.json, code-judges.json, or prd-judges.json, and validate output. Supports evaluating implementation plans (16 judges), code artifacts (11 judges), or PRD artifacts (4 judges) via --artifact-type parameter.

run-kongyo-spec

kongyo2/kongyo-spec

Build, run, and drive the Kongyo Spec Electron desktop app (a markdown spec editor with GFM, Shiki, KaTeX, Mermaid). Use when asked to run, start, launch, build, or screenshot the app, or to interact with its UI — create a spec, edit markdown, preview rendering, or verify shiki/katex/mermaid output.

run-on-slurm

NVIDIA/Megatron-LM

How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-rank failure diagnosis.

run-package

kurtosis-tech/kurtosis

Run Starlark scripts and packages with kurtosis run. Covers all flags including dry-run, args-file, parallel execution, image download modes, verbosity levels, and production mode. Use when executing Kurtosis packages locally or from GitHub.

run-partner-strategy-and-operations

Significant-Gravitas/skills-catalog

Use when the partnerships org needs an operating layer: annual planning, invest/divest calls, revenue and capacity models, objectives, and cadence.

run-plan

fabriqaai/specs.md

Plan the scope of a run by discovering available work items and suggesting groupings. Invoked before run-execute.

run-regulated-partnership-motions

Significant-Gravitas/skills-catalog

Use when a partnership runs inside a regulated frame: payments scheme rules, federal vehicles, tenders, or medical education — frame first.

run-shell

openakita/openakita

Execute shell commands for system operations, directory creation, and script execution. When you need to run system commands, execute scripts, install packages, or manage processes. Note - if commands fail consecutively, try different approaches.

run-skill-script

openakita/openakita

Execute a skill's script file with arguments. When you need to run skill functionality, execute specific operations, or process data with skill.

run-status

fabriqaai/specs.md

Display current run status and progress. Shows work item, mode, duration, and files changed.

run-study

yoheinakajima/distributed-discovery

Run or resume a registered Distributed Discovery study with immutable provenance. Use for executing study configurations, resuming bounded searches, or recording reproducible research runs in this repository.

run-test

mx-space/core

Run tests. Supports running all tests, single file, or pattern-matched tests.

run-test-plan

existential-birds/beagle

Execute YAML test plan, stop on first failure, output rich debug prompt

run-tests

microsoft/testfx

>-

run-the-partner-co-sell-cadence

Significant-Gravitas/skills-catalog

Use for the weekly operating rhythm with an active partner: prep the call, keep deal registration honest, and rescue stuck joint deals.

run-the-partner-marketing-engine

Significant-Gravitas/skills-catalog

Use when co-marketing needs an engine rather than a one-off: the dated calendar, account-based plays, campaign briefs, and the return narrative.

run-without-you

alirezarezvani/claude-skills

Phase 4 of building a Claude Managed Agent — make it run without you. Turn a graded agent into a recurring scheduled deployment (POSIX-cron), an event-driven curl trigger, or confirmed on-demand use, then finalize the versioned roadmap. Use when the user says "run it every morning", "put it on a schedule", "nightly", "weekly", "automate this", "make it recurring", or when the orchestrator routes phase=run-without-you. deployment_builder.py builds the POST /v1/deployments payload (initial_events must include user.message; optionally nests a user.define_outcome so each firing self-grades); cron_validator.py validates the 5-field cron + IANA timezone and prints the wall-clock DST note; next_directions_writer.py writes NEXT-DIRECTIONS.md. No tool makes API calls — the deployment is created via BYOK curl. Distinct from grade-iterate (the in-session loop) and wrap-up (closeout).

runbook

anthropics/knowledge-work-plugins

Create or update an operational runbook for a recurring task or procedure. Use when documenting a task that on-call or ops needs to run repeatably, turning tribal knowledge into exact step-by-step commands, adding troubleshooting and rollback steps to an existing procedure, or writing escalation paths for when things go wrong.

runbook-enterprise-feature

elophanto/EloPhanto

Enterprise feature development runbook — adding major features to existing products with compliance, security, and quality gates. Adapted from msitarzewski/agency-agents.

runbook-gen

EliasOulkadi/shokunin

Generate operations runbooks and post-mortems for incident response — severity matrix, decision trees, escalation paths, war room setup (Slack/Zoom), status page updates, customer comms templates, and blameless post-mortems with action items.

runbook-generator

alirezarezvani/claude-skills

Generate operational runbooks from a service name — deployment, incident response, maintenance, and rollback workflows. Templated structure customizable per environment. Use when documenting on-call procedures for a new service, standardizing incident response across teams, or producing runbooks before launching to production.

runbook-incident-response

elophanto/EloPhanto

Incident response runbook — detection through post-mortem for production issues with severity-based response teams. Adapted from msitarzewski/agency-agents.