Browse Skills — Page 254

sandbox-evasion-implement

wgpsec/AboutSecurity

沙箱逃逸与反分析技术实现。当需要让恶意载荷绕过自动化沙箱分析（AnyRun/Cuckoo/CAPE/Joe/Windows Defender Sandbox）时使用。覆盖环境检测、定时欺骗、用户交互检测、虚拟化检测等主流逃逸技术的实现方法

sandbox-filesystem-access

github/gh-aw-firewall

Configure or diagnose file and directory access, mounts, and host ACLs for AWF sandboxes.

sandbox-framework

SteelMorgan/1c-agent-based-dev-framework

Behavior + permission model for the AI agent inside the sandbox devcontainer. The agent has sudo and may modify its container environment freely to solve tasks, but must never bypass explicit safety restrictions (git hooks/blocks, policy rules) or escalate beyond the sandbox.

sandbox-guard

UseAI-pro/openclaw-skills-security

Generate Docker sandbox configurations for safely running untrusted OpenClaw skills. Isolates filesystem, network,

sandbox-lifecycle-debug

vercel-labs/vercel-openclaw-archived

Sandbox lifecycle debugging for vercel-openclaw: create, resume, stop, snapshotting, reset, stale-running reconciliation, persistent Sandbox v2 behavior, hot spares, and lifecycle locks. Use when sandbox state transitions, status polling, stop/resume, reset, or lifecycle recovery is wrong.

sandbox-migrate-to-next

cloudflare/skills

Migrate Cloudflare Sandbox apps from stable @cloudflare/sandbox to @cloudflare/sandbox@next (SDK 1.0 preview). Use sandbox-next for apps already on the preview.

sandbox-next

cloudflare/skills

Build or maintain Cloudflare Sandbox apps on @cloudflare/sandbox@next (SDK 1.0 preview). Use sandbox-migrate-to-next when porting a stable app.

sandbox-npm-install

github/awesome-copilot

'Install npm packages in a Docker sandbox environment. Use this skill whenever you need to install, reinstall, or update node_modules inside a container where the workspace is mounted via virtiofs. Native binaries (esbuild, lightningcss, rollup) crash on virtiofs, so packages must be installed on the local ext4 filesystem and symlinked back.'

sandbox-sdk

openai/plugins

Build sandboxed applications for secure code execution. Load when building AI code execution, code interpreters, CI/CD systems, interactive dev environments, or executing untrusted code. Covers Sandbox SDK lifecycle, commands, files, code interpreter, and preview URLs. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

sandbox-stable

cloudflare/skills

Build or maintain Cloudflare Sandbox apps on the stable @cloudflare/sandbox package. Use sandbox-next for preview apps and sandbox-migrate-to-next for stable-to-preview migrations.

sandbox-v2-lifecycle

vercel-labs/vercel-openclaw-archived

Vercel Sandbox v2 lifecycle expertise for vercel-openclaw: named persistent OpenClaw sandbox create/resume/stop/delete, persistent auto-save truth, manual snapshot diagnostics, short-lived worker sandboxes, hot spares, and SDK v2 semantics.

sandler-system

guia-matthieu/clawfu-skills

Apply Sandler Selling System principles for consultative sales with pain discovery, budget qualification, and mutual decision frameworks

sanger-chromatogram-qa

aipoch/medical-research-skills

Use sanger chromatogram qa for data analysis workflows that need structured execution, explicit assumptions, and clear output boundaries.

sanierungsbausteine-vorschlagen

Klotzkette/claude-fuer-deutsches-recht

Wenn die Fortbestehensprognose ohne Massnahmen negativ oder knapp positiv ist schlaegt dieser Skill konkrete Sanierungsbausteine vor. Auswahl Patronatserklaerung hart Comfortletter Gesellschafterdarlehen mit Rangruecktritt Stundungsvereinbarungen Forderungsverzichte mit Besserungsschein Eigenkapitalmassnahme StaRUG-Restrukturierungsplan. Empfehlungsmatrix nach Effekt und Umsetzungszeit. Empfiehlt konkret welche Dokumente erzeugt werden sollten (Skills patronatserklaerung-extern-hart-erzeugen gesellschafterdarlehen-rangruecktritt stundungsanfrage-glaeubiger).

sanierungsmoderation-94-starug

Klotzkette/claude-fuer-deutsches-recht

Sanierungsmoderation nach § 94 StaRUG durch gerichtlich bestellten Moderator. Anwendungsbereich vor Restrukturierungs-Antrag bei drohenden Liquiditaets-Engpaessen unstreitigen wirtschaftlich gefaehrdeten Lagen. Aufgaben Moderator vermitteln zwischen Schuldner und Glaeubigern Sanierungs-Konzept ausarbeiten Verhandlungen begleiten. Vertraulichkeit Pflicht § 97 StaRUG. Verfahrens-Dauer drei Monate § 94 Abs. 2 StaRUG. Sanierungsvergleich § 97 StaRUG Bestaetigung § 100 StaRUG durch Restrukturierungs-Gericht. Verzahnung StaRUG-Restrukturierungs-Verfahren bei Erfolg. Bei Misserfolg Verweisung Insolvenz-Antrag. Praeventives Werkzeug Krise-Beratung. Schnittstelle BGH IX ZR 250/15 Anfechtungs-Risiko bei Vergleich Bargeschaeft-Privileg.

sanity

TerminalSkills/skills

>-

sankhya-dashboard-html-jsp-custom-best-pratices

diegosouzapw/awesome-omni-skills

sankhya-dashboard-html-jsp-custom-best-pratices workflow skill. Use this skill when the user needs This skill should be used when the user asks for patterns, best practices, creation, or fixing of Sankhya dashboards using HTML, JSP, Java, and SQL and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

sankhya-dashboard-html-jsp-custom-best-pratices-v2

diegosouzapw/awesome-omni-skills

sankhya-dashboard-html-jsp-custom-best-pratices workflow skill. Use this skill when the user needs This skill should be used when the user asks for patterns, best practices, creation, or fixing of Sankhya dashboards using HTML, JSP, Java, and SQL and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

sanktionen-art-99-bis-101

Klotzkette/claude-fuer-deutsches-recht

Bussgelder nach Art. 99 bis 101 KI-VO: bis 35 Mio EUR oder sieben Prozent Konzernumsatz bei verbotenen Praktiken bis 15 Mio EUR oder drei Prozent bei sonstigen Verstoszen bis 7.5 Mio EUR oder ein Prozent bei falschen Angaben. KMU-Privilegierung.

sanktions-compliance-pruefung

Klotzkette/claude-fuer-deutsches-recht

Sanktions-Compliance: EU-Sanktionen (VO 269/2014 und 833/2014 Russland-Paket 1–14), US-OFAC SDN-Liste, UK-HMT/OFSI, UN-Sicherheitsrat-Resolutionen. Asset-Freeze, sektorale Embargos, Dienstleistungsverbote, Re-Export-Klauseln. AWG §§ 18–19 Strafbarkeit, BAFA-Genehmigungen. Screening-Tools, Dokumentationspflicht 10 Jahre. Sofortmaßnahmen bei Verdacht.

santa-method

affaan-m/ECC

Multi-agent adversarial verification with convergence loop. Two independent review agents must both pass before output ships.

sap

TerminalSkills/skills

>-

sap-extension-creator

heshengtao/super-agent-party

Create Super Agent Party (SAP) extensions. This skill should be used when users want to create, build, or scaffold a new extension for Super Agent Party - including static HTML extensions (pure frontend) and Node.js backend extensions. Triggers on requests like "create a new SAP extension", "build an extension for Super Agent Party", "scaffold a plugin", "make a chat UI extension", or when working with sap extension projects.

sap-successfactors-automation

ComposioHQ/awesome-claude-skills

"Automate SAP SuccessFactors tasks via Rube MCP (Composio). Always search tools first for current schemas."

sapcc-audit

notque/vexjoy-agent

Full-repo SAP CC Go compliance audit against review standards.

sapcc-review

notque/vexjoy-agent

Gold-standard SAP CC Go code review: 10 parallel domain specialists.

sar-analysis

jaechang-hits/SciAgent-Skills

Structure-activity relationship (SAR) analysis guide for drug discovery including molecular descriptor analysis, scaffold analysis, and activity cliff detection.

sarif-parsing

trailofbits/skills

>-

sashimi-plots

swaruplab/operon

Creates sashimi-style plots showing RNA-seq read coverage and splice junction counts using ggsashimi (general-purpose, condition-grouped overlays), rmats2sashimiplot (rMATS-output-aware), MAJIQ-VOILA (LSV posteriors interactive HTML), leafviz (leafcutter clusters Shiny), Jutils (tool-agnostic heatmaps and sashimi for rMATS/leafcutter/SUPPA2/MAJIQ output), or pyGenomeTracks (multi-track publication figures). Tool choice depends on the upstream differential-splicing tool's output format and the publication vs interactive use case. Use when visualizing specific splicing events, validating differential splicing calls, or producing publication-quality figures.

sast

H-mmer/pentest-agents

Source code vulnerability hunting (SAST). Decomposes analysis into specialized passes: map entry points, map dangerous ops, trace flows, find gaps, adversarial validation, exploit. Usage: /sast <repo_path> [--lang c|cpp|rust|java|python|go|php] [--min-score 4] [--max-files 30] [--skip-static] [--best-of N]

sast-configuration

benjaminasterA/antigravity-awesome-skills

Configure Static Application Security Testing (SAST) tools for automated vulnerability detection in application code. Use when setting up security scanning, implementing DevSecOps practices, or aut...

sast-configuration

wshobson/agents

Configure Static Application Security Testing (SAST) tools for automated vulnerability detection in application code. Use when setting up security scanning, implementing DevSecOps practices, or automating code vulnerability detection.

sast-danger-mapper

H-mmer/pentest-agents

Maps dangerous operations in a source file: memory ops, type casts, arithmetic near trust boundaries, free/dealloc patterns. Pattern matching task — list what you see, don't speculate. Use via /sast command.

sast-devils-advocate

H-mmer/pentest-agents

Adversarial validator for SAST findings. Your ONLY job is to DISPROVE the candidate. Find every reason it's not exploitable. If you can't disprove it, it survives. Use via /sast command.

sast-entry-mapper

H-mmer/pentest-agents

Maps entry points where untrusted data enters a source file. Lists every function that receives external input with data type, size constraints, and initial validation. Use via /sast command.

sast-exploit-builder

H-mmer/pentest-agents

Builds working exploits from confirmed SAST findings. Takes a confirmed crash, develops it into a full exploit. Tier 1 (DoS) → Tier 5 (code execution). Use via /sast command after PoC confirmation.

sast-file-ranker

H-mmer/pentest-agents

Source file attack surface ranker. Reads a repository, scores every source file 1-5 by exploitability. Outputs ranked JSON for per-file hunting. Use via /sast command.

sast-flow-tracer

H-mmer/pentest-agents

Traces data flow from entry points to dangerous operations. Cross-file reasoning to determine which entries can reach which dangers, and what validation exists in between. MUST run on Opus for reasoning depth. Use via /sast command.

sast-gap-analyzer

H-mmer/pentest-agents

Analyzes validation gaps in data flows. Takes traced flows and identifies where checks are missing, insufficient, or bypassable. The 'interaction reasoning' step — finds bugs that exist in the gaps between individually correct-looking code. MUST run on Opus. Use via /sast command.

sast-hunter

H-mmer/pentest-agents

Focused PoC builder for SAST candidates. Receives a SPECIFIC candidate vulnerability that survived adversarial validation. Writes a PoC, compiles, runs with ASan, confirms or rejects. Use via /sast command.

satismeter-automation

ComposioHQ/awesome-claude-skills

"Automate Satismeter tasks via Rube MCP (Composio). Always search tools first for current schemas."

satori

diegosouzapw/awesome-omni-skills

Satori workflow skill. Use this skill when the user needs Clinically informed wisdom companion blending psychology and philosophy into a structured thinking partner and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

satori

openai/plugins

Expert guidance for Satori — Vercel's library that converts HTML and CSS to SVG, commonly used to generate dynamic OG images for Next.js and other frameworks.

satori-v2

diegosouzapw/awesome-omni-skills

Satori workflow skill. Use this skill when the user needs Clinically informed wisdom companion blending psychology and philosophy into a structured thinking partner and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

saturation-analysis

yogsoth-ai/de-anthropocentric-research-engine

Track score trajectories, detect saturation/failure points — 15 benchmarks, 50 papers, 60 web searches

saturation-detection

yogsoth-ai/de-anthropocentric-research-engine

Determine when additional searching yields diminishing returns. Analyzes the latest expansion batch against existing corpus to judge continue/near-saturation/saturated. Used by snowball and systematic-survey.

satzungskompetenz-pruefen

Klotzkette/claude-fuer-deutsches-recht

Satzungskompetenz fuer Koerperschaften und Anstalten des oeffentlichen Rechts pruefen. Anwendungsfall Gemeinde Kammer Hochschule oder Sozialversicherungstraeger will Satzung erlassen und Rechtsgrundlage muss geprueft werden. Kommunen Art. 28 Abs. 2 GG Gemeindeordnung Berufsstaendische Kammern BRAO IHK-Gesetz HwO Hochschulen Hochschulgesetz Sozialversicherungstraeger § 33 SGB IV. Vorbehalt des Gesetzes Wesentlichkeitstheorie BVerfGE 33/125 Ermaechtigungsgrundlage Inhalt Zweck Ausmass Genehmigungsvorbehalt Aufsichtsbehoerde Bekanntmachung richtiges Publikationsorgan. Output Empfehlung Satzung auf welcher Grundlage erlassbar.

satzweise-notenmatrix

Klotzkette/claude-fuer-deutsches-recht

Bewertet jeden notenrelevanten Satz eines Arbeitszeugnisses mit einer Schulnote von eins bis fuenf und ordnet ihn einem Themenbereich zu. Ausgabe als geschlossene Matrix mit Satzkurzform, Themenbereich, Note, Steigerungsadverb-Befund und Begruendung — Grundlage fuer Drift-Detektor und Gesamtnoten-Aggregation.

save

AgriciDaniel/claude-obsidian

>

save-knowledge

indranilbanerjee/digital-marketing-pro

Save brand knowledge to memory. Use when: persisting campaign learnings, guidelines, or competitive intel for retrieval.

save-state

tranhieutt/software_development_department

Saves current working context to production/session-state/active.md AND writes an atomic per-task checkpoint to .tasks/checkpoints/[task_id].md. Run before any major context reset, when context usage exceeds 60%, or when ending a work session.

sbiz365-analyst

modu-ai/cowork-plugins

|

sbom-generate

686f6c61/alfred-dev

Usar para generar Software Bill of Materials para cumplimiento del CRA. También: Software Bill of Materials, inventario de componentes, CycloneDX, SPDX, cadena de suministro.

scaffold

SethGammon/Citadel

>-

scaffold-dashboard

ahpxex/open-dashboard

Stand up the dashboard foundation (the platform layer — UI primitives, form system, charts, Repository + adapters, auth seam, theme, routing shell) into a new project as a zero-config runnable app. Run this FIRST when building a dashboard, then compose screens from the add-component catalogue's shapes (add-detail-page, add-kanban, …) and the add-backend operation skill.

scaffold-dotnet-test-project

microsoft/testfx

>-

scaffold-element

remotion-dev/remotion

Scaffold a new Remotion Element for development in the docs Remotion Studio.

scaffold-exercises

mkurman/zorai

Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.

scaffolding

dotnet/efcore

Implementation details for EF Core scaffolding (reverse engineering). Use when changing ef dbcontext scaffold pipeline implementation, database schema reading, CSharpModelGenerator, or related classes.

scaffolding-oracle-to-postgres-migration-test-project

github/awesome-copilot

Scaffolds an xUnit integration test project targeting Oracle in .NET solutions. Creates the test project, transaction-rollback base class, and seed data manager. Use only during Phase 3, before writing Oracle baseline integration tests. Do not invoke during Phase 6 — the PostgreSQL test project is produced by migrating this project, not by running this skill again.

Scala Collections

TheBushidoCollective/han

Use when scala collections including immutable/mutable variants, List, Vector, Set, Map operations, collection transformations, lazy evaluation with views, parallel collections, and custom collection builders for efficient data processing.

Scala Functional Patterns

TheBushidoCollective/han

Use when functional programming patterns in Scala including higher-order functions, immutability, pattern matching, algebraic data types, monads, for-comprehensions, and functional composition for building robust, type-safe applications.

Scala Type System

TheBushidoCollective/han

Use when scala's advanced type system including generics, variance, type bounds, implicit conversions, type classes, higher-kinded types, path-dependent types, and abstract type members for building type-safe, flexible APIs.

scala-pro

benjaminasterA/antigravity-awesome-skills

Master enterprise-grade Scala development with functional

scala-pro-v2

diegosouzapw/awesome-omni-skills

scala-pro workflow skill. Use this skill when the user needs Master enterprise-grade Scala development with functional programming, distributed systems, and big data processing. Expert in Apache Pekko, Akka, Spark, ZIO/Cats Effect, and reactive architectures and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

scalability-advisor

alirezarezvani/claude-cto-team

Guidance for scaling systems from startup to enterprise scale. Use when planning for growth, diagnosing bottlenecks, or designing systems that need to handle 10x-1000x current load.

scalar-ub

yogsoth-ai/de-anthropocentric-research-engine

Scale Game

aAAaqwq/AGI-Super-Team

Test at extremes (1000x bigger/smaller, instant/year-long) to expose fundamental truths hidden at normal scales

Scale Game

obra/superpowers-skills

Test at extremes (1000x bigger/smaller, instant/year-long) to expose fundamental truths hidden at normal scales

scale-the-partner-channel

Significant-Gravitas/skills-catalog

Use when resellers, managed service providers, or distributors need territory-scale activation: funnels with bars, coverage, distributor ops.

scaling-design

yogsoth-ai/de-anthropocentric-research-engine

Design scaling experiments to characterize performance-resource relationships

scaling-frontier

yogsoth-ai/de-anthropocentric-research-engine

Analyze behavior across scales — detect regime changes, identify capacity limits, fit scaling laws within regimes.

scaling-regime-detection

yogsoth-ai/de-anthropocentric-research-engine

Detect regime changes in scaling behavior — breakpoints where behavior qualitatively shifts, mechanisms behind transitions.

scamper-divergence

yogsoth-ai/de-anthropocentric-research-engine

Execute SCAMPER 7 operators on a target solution. Subagent self-selects best 2-3 operators for deepest exploration.

scamper-transformation

yogsoth-ai/de-anthropocentric-research-engine

7 operators (Substitute/Combine/Adapt/Modify/Put/Eliminate/Reverse) for systematic transformation of existing solutions.

scan

cwinvestments/memstack

Use when the user says 'scan project', 'estimate', 'how much to charge', or needs codebase complexity analysis.

scan

wshobson/agents

Scans the codebase to generate project-doc.md and AGENTS.md. Use when bootstrapping a new agent-driven repo, refreshing project documentation after architectural changes, or running a delta scan to detect drift. Runs a full scan on first use and a smart delta scan on subsequent runs. Uses understand-anything + context-mode when available, falls back to native tools otherwise. Only updates AGENTS.md on detected architectural changes with human confirmation.

scan-ingest

obra/scan-to-model

Preserve and inventory scan archives while retaining capture variants, hashes, calibration, and frame provenance.

scan-register

obra/scan-to-model

Fit and independently validate rigid scan alignment from named, source traceable correspondences.

scan-site

microsoft/power-platform-skills

>-

scan-to-model

obra/scan-to-model

Coordinate evidence based reconstruction from scans, photos, plans, and measurements into a reviewable Blender architectural model, with photographic appearance, renders and portable browser delivery when requested.

scanner-bridge

Community-Access/accessibility-agents

Internal helper that bridges GitHub Accessibility Scanner CI data with the agent ecosystem. Fetches scanner-created issues, normalizes findings, deduplicates against local scans, and tracks Copilot fix status.

scanner-bullish

staskh/trading_skills

Scan stocks for bullish trends using technical indicators (SMA, RSI, MACD, ADX). Use when user asks to scan for bullish stocks, find trending stocks, or rank symbols by momentum.

scanner-pmcc

staskh/trading_skills

Scan stocks for Poor Man's Covered Call (PMCC) suitability. Analyzes LEAPS and short call options for delta, liquidity, spread, IV, yield, trend direction, and earnings proximity. Use when user asks about PMCC candidates, diagonal spreads, or LEAPS strategies.

scanning-container-images-with-grype

mukul975/Anthropic-Cybersecurity-Skills

Scan container images for known vulnerabilities using Anchore Grype with SBOM-based matching and configurable severity thresholds.

scanning-containers-with-trivy-in-cicd

mukul975/Anthropic-Cybersecurity-Skills

>

scanning-docker-images-with-trivy

mukul975/Anthropic-Cybersecurity-Skills

Trivy is a comprehensive open-source vulnerability scanner by Aqua Security that detects vulnerabilities in OS packages, language-specific dependencies, misconfigurations, secrets, and license violati

scanning-infrastructure-with-nessus

mukul975/Anthropic-Cybersecurity-Skills

Tenable Nessus is the industry-leading vulnerability scanner used to identify security weaknesses across network infrastructure including servers, workstations, network devices, and operating systems.

scanning-kubernetes-manifests-with-kubesec

mukul975/Anthropic-Cybersecurity-Skills

Perform security risk analysis on Kubernetes resource manifests using Kubesec to identify misconfigurations, privilege escalation risks, and deviations from security best practices.

scanning-market-movers

aAAaqwq/AGI-Super-Team

Real-time detection and analysis of significant price movements and unusual volume patterns across cryptocurrency markets. This skill identifies top g

scanning-network-with-nmap-advanced

mukul975/Anthropic-Cybersecurity-Skills

>

scanning-tools

benjaminasterA/antigravity-awesome-skills

This skill should be used when the user asks to \"perform vulnerability scanning\", \"scan networks for open ports\", \"assess web application security\", \"scan wireless networks\", \"detec...

scanning-tools-v2

diegosouzapw/awesome-omni-skills

Security Scanning Tools workflow skill. Use this skill when the user needs Master essential security scanning tools for network discovery, vulnerability assessment, web application testing, wireless security, and compliance validation. This skill covers tool selection, configuration, and practical usage across different scanning categories and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

scanpy

K-Dense-AI/scientific-agent-skills

Standard single-cell RNA-seq analysis pipeline. Use for QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. Best for exploratory scRNA-seq analysis with established workflows. For deep learning models use scvi-tools; for data format questions use anndata.

scanpy-scrna-seq

jaechang-hits/SciAgent-Skills

scRNA-seq with Scanpy: QC, normalization, HVG selection, PCA, neighborhood graph, UMAP/t-SNE, Leiden clustering, markers, cell annotation, trajectory inference. Standard scRNA-seq exploration.

scanpy-v2

diegosouzapw/awesome-omni-skills

Scanpy: Single-Cell Analysis workflow skill. Use this skill when the user needs Scanpy is a scalable Python toolkit for analyzing single-cell RNA-seq data, built on AnnData. Apply this skill for complete single-cell workflows including quality control, normalization, dimensionality reduction, clustering, marker gene identification, visualization, and trajectory analysis and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

scarcity-urgency-psychologist

diegosouzapw/awesome-omni-skills

scarcity-urgency-psychologist workflow skill. Use this skill when the user needs One sentence - what this skill does and when to invoke it and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

scarcity-urgency-psychologist-v2

diegosouzapw/awesome-omni-skills

scarcity-urgency-psychologist workflow skill. Use this skill when the user needs One sentence - what this skill does and when to invoke it and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

sccm-mecm-attack

wgpsec/AboutSecurity

针对 Microsoft SCCM/MECM (Configuration Manager) 的攻击方法论。当内网发现 SCCM 站点服务器、管理点(MP)、分发点(DP) 时使用。覆盖 NAA 凭证提取、任务序列密码、PXE 启动介质、Client Push 强制认证、站点服务器接管、应用部署横向移动、AdminService API 利用、层级接管(CAS→Primary)。

scenario

boshu2/agentops

Manage holdout scenarios.