DevOps & Infra

concept-git Bundle

Huawei Cloud BSS billing read-only only (not AWS/Azure/other clouds; refuses pricing quotes, real-name review, and any non-billing scope): balance, spend, attribution, reconciliation, coupons, stored-value cards, enterprise/partner billing. One-page briefing via hcloud. Use only when the user explicitly mentions 华为云 / Huawei Cloud / BSS and 余额/账单/对账/资源包/代金券/储值卡/企业或伙伴账务; refuses pay, renew, refund, delete.

concept-git Bundle

Generate Huawei Cloud pre-order price estimates, safely provision allowlisted resources via hcloud, and guide unsubscribe requests to the console only. Use this skill whenever the user mentions 华为云/Huawei Cloud/hcloud with 报价/询价/价格/quote/pricing/budget, 开通/购买/创建/provision/create, or 退订/unsubscribe. Create requires runtime help, --dryrun, fee review, and confirmation. Never run or emit unsubscribe CLI/API. Refuse other clouds, credentials, payment/renewal/delete, and non-allowlisted writes.

concept-git Bundle

Checks Huawei Cloud real-name verification status and guides face-scan verification read-only through hcloud. Use for Huawei Cloud verification status, real-name onboarding, or flows blocked on verification. Accepts no identity documents, bank details, or SMS codes; refuses writes and non-Huawei-Cloud identity workflows.

concept-git Bundle

Checks Huawei Cloud real-name verification (实名认证) status and guides face-scan verification, read-only via hcloud: reads the account's verification state, and when unverified fetches the face-auth QR address, renders it in the terminal to scan by phone, then polls until verified. Use when the user mentions 华为云 / Huawei Cloud plus 实名认证/实名/认证状态/real-name verification, or a Huawei Cloud flow reports verification is required. Face-scan channel only; refuses ID, document, bank-card and SMS-code intake, refuses write operations (enterprise and certificate channels are console-only), and refuses non-Huawei-Cloud identity flows.

guan0123258 Bundle

Design, generate, validate, inspect, and safely apply industrial SCADA/HMI dashboards to FUXA. Assumes device data stays in an upstream cloud platform and FUXA acts as the visualization layer. Supports version and capability probing, explicit-first variable semantics, layout presets, dry-run project patches, and API-to-tag bridging.

samraddhashrivastavatech Skill

UNIVERSAL ORCHESTRATOR — the automatic front door to the entire CATLX skill ecosystem. Activate this once and then just ask in plain English: explain X, fix a problem, deploy/build/configure something, analyze what is wrong, etc. It understands the request, routes to the right CATLX subsystem skill from the skill registry / capability index, then lets that skill auto-delegate recursively and synthesizes the final result. Use proactively for any request that does NOT already name a specific skill, or when the user says 'activate universal orchestrator', 'help me solve', 'why is X failing', 'what is wrong', 'analyze this'.

samraddhashrivastavatech Skill

Handles the CATLX voice-first interface: the 10-stage voice processing pipeline (wake word, audio capture, STT, context injection, NLU/intent, clarification, planning, execution, feedback, memory write), wake word configuration, the continuous conversational context window, and real-time streamed TTS. Use when the user asks about voice commands, wake words, speech-to-text, NLU intents, disambiguation, TTS, or how voice is the primary interface.

samraddhashrivastavatech Skill

Editing, sound and music, shot/asset/file organization, versioning, pipeline, performance optimization, QC, final output, archiving, add-ons, Python/USD/export, render ops, and real-time/game export.

samraddhashrivastavatech Skill

CATLX — Docker Architecture

samraddhashrivastavatech Skill

Performance pipeline from blocking to polish — 12 principles in Blender practice, locomotion (human, animal, invented, multi-leg, flight, swim), acting, fighting, facial animation, lip sync, secondary motion, NLA, Graph Editor mastery.

samraddhashrivastavatech Skill

Handles the CATLX plugin ecosystem: the plugin runtime (worker threads / Docker), signed plugin security with capability grants, the @catlx/plugin-sdk, the Plugin Marketplace, hot reload, and version management with deterministic dependency resolution (PnP-style) and API compatibility shims. Use when the user asks about CATLX plugins, writing/installing a plugin, the Plugin SDK, marketplace, hot reload, plugin signing/security, or plugin dependency resolution.

shadoprizm Bundle

Scan websites, GitHub repositories, and Claw Hub skills for practical security issues using a local quick website scan and CyberLens cloud analysis when connected.

orcaqubits Skill

Set up a Saleor development environment — saleor-platform Docker Compose, CLI, PostgreSQL/Redis prerequisites, manage.py commands, environment variables, project structure. Use when starting a new Saleor project.

orcaqubits Skill

Deploy Medusa v2 to production — build process, server vs worker mode, environment variables, hosting options, Redis caching, database configuration, and production checklist. Use when deploying Medusa applications.

orcaqubits Skill

Build Shopify Functions — serverless WebAssembly extensions for discounts, delivery customization, payment customization, cart validation, cart transforms, and order routing. Use when extending Shopify's backend logic.

ethanxegg Bundle

微信开发者工具「多实例多账号」并行调试：在一台机器上起 N 个互相独立的开发者工具实例， 每个实例登录不同微信号、各挂一个自动化端口，从而同时驱动导生 / 家长 / 导员等多个身份。 也覆盖这一路的坑与处置：多账号调试窗口不可自动化、同一 appid 的 access_token 互相顶掉 （invalid credential）、agent start 只绑第一个窗口、CLI 参数真名（cache --clean session）、 第 3 个实例起不来（minicode server 双端口 bug，附补丁脚本）、 窗口太宽只想留模拟器（lite 窗口）、把调试输出独立成窗口、记住/复原多窗口布局、 lite 窗口被强制置顶（工具写死，附 `untop` 取消）， 以及小程序侧 `module '@babel/runtime/...' is not defined` / `Cloud API isn't enabled` 的鉴别与修复。 当需要多个角色同时在线调试、多窗口并行自动化、开多个开发者工具实例， 或同工程的第二个窗口连不上自动化端口、第 3 个实例开了就卡死、新实例编译报模块缺失时使用。

learningmatter-mit Bundle

Extract continuous X-Y data from experimental spectrum images (Raman, XRD, UV-Vis, IR, etc.) via hybrid VLM + CV pipeline and agent-in-the-loop workflow.

stas2-git Bundle

Use when packaging, testing, deploying, monitoring, or rolling back an ADK agent on Google Agent Runtime with Agents CLI, Terraform, runtime adapters, artifacts, IAM, regions, telemetry, and remote validation.

stas2-git Bundle

Use when a workbook task needs task-specific post-change checks, such as expected sheet names, labels, formulas, tabs, charts, or OCR-visible text that downstream automation can verify.

emanuelegreco29 Bundle

DevOps guidance - CI/CD pipelines, environments and config, containerization, observability and monitoring, incident response and rollback, and deployment platforms. Use when setting up deployment, CI/CD, monitoring, or handling an incident.

alpayc Skill

Writes and changes CI/CD pipeline configuration — job graph, caching, changed-set filtering, matrices, artefacts — validated before pushing. Use it when adding a job, speeding up a pipeline, or fixing a config-class failure.

alpayc Skill

Diagnoses a failing CI run — fetches the logs, finds the first real error rather than the loudest, classifies it as code, flake, infrastructure or config, and fixes what is fixable locally. Use it when a pipeline is red, or a build passes locally and fails in CI.

grzmol Bundle

Salesforce Data Cloud (rebranded Data 360) from a developer's seat - deciding whether a story belongs in Data Cloud at all, modelling data lake objects (DLO) and data model objects (DMO) and the DLO-to-DMO mapping, choosing a primary key and an extract method, ingesting through the Ingestion API in streaming or bulk mode, understanding what identity resolution produces and how to query a unified profile, consuming calculated insights and data graphs, querying with Data 360 SQL through the Query API or with the sfsqlquery Apex namespace and ConnectApi.CdpQuery, the SOQL subset that works against DMOs, surfacing Data Cloud data in LWC through an Apex bridge and in Flow through the cdp invocable actions, source-tracking Data Cloud metadata types (DataStreamDefinition, ObjectSourceTargetMap, DataSrcDataModelFieldMap, MktCalcInsightObjectDef, DataConnectorIngestApi) in an SFDX project, and the ingestion and query limits that bite. Use when a story mentions Data Cloud, Data 360, a data stream, a DLO or DMO, unified

grzmol Bundle

Operating Salesforce CLI v2 (`sf`) as the deterministic execution layer for a Salesforce project — the `sf org`, `sf project`, `sf apex`, `sf data`, `sf package`, `sf schema`, `sf sobject`, `sf config`, `sf alias`, `sf plugins` and `sf code-analyzer` topics, global flags (`--json`, `--target-org`, `--target-dev-hub`, `--api-version`, `--flags-dir`), non-interactive authorization (`sf org login web|jwt|sfdx-url|access-token`, connected app plus JWT for CI), config variables and aliases, `--json` result shapes with jq extraction recipes, `SF_*` environment variables, plugin and JIT-plugin management, retired `sfdx force:*` to `sf` migration, and the failure modes that break CI pipelines. Use this skill whenever a command line is being written or debugged, whenever an org must be authorized from a pipeline, whenever `--json` output must be parsed, whenever the API version or default org resolution looks wrong, or whenever a `sf` command fails with an auth, plugin, or version error.

grzmol Bundle

Record-triggered and autolaunched Flow as a first-class automation layer - the FlowTriggerType and RecordTriggerType matrix, before-save versus after-save placement inside the order of execution, entry conditions and re-entry control, scheduled paths and asynchronous paths, choosing Flow versus Apex trigger and never both on one object, calling Apex from Flow with @InvocableMethod and @InvocableVariable, FlowTest metadata for automated flow tests, flow versioning and the flows/ plus flowDefinitions/ metadata shape, activation on deploy and flow test coverage, and the governor limits flows share with Apex. Use when adding or reviewing a record-triggered flow, deciding between declarative and code automation, writing an invocable Apex action, or when a deploy fails on flow activation or flow coverage.

grzmol Bundle

Covers running fflib Apex Enterprise Patterns in a real delivery pipeline - trigger inventory and one-trigger-per-object dispatch, bypass and kill-switch design with custom permissions and custom metadata, feature flags that swap Application factory bindings, Queueable with Finalizer and Batch runners that call services with per-chunk Unit of Work commits, platform-event publishing and subscriber domains, callout ordering around commitWork, large-data-volume tuning, structured logging and correlation ids, packaging and deployment ordering for fflib-apex-mocks and fflib-apex-common, Code Analyzer rules that misfire on fflib, PR review checklists and the fflib version-upgrade runbook. Use this skill when auditing triggers in an fflib org, adding a bypass switch, running fflib code from Batch or Queueable, packaging or upgrading fflib, tuning Code Analyzer for fflib, or reviewing an fflib pull request.

grzmol Bundle

Structuring a Salesforce DX repository — the full `sfdx-project.json` schema (packageDirectories, default, sourceApiVersion, namespace, sfdcLoginUrl, plugins, packageAliases, replacements, sourceBehaviorOptions, oauthLocalPort, pushPackageDirectoriesSequentially), source-format directory layout for every metadata type (`objects/<Obj>/fields`, `classes`, `triggers`, `lwc`, `aura`, `flows`, `permissionsets`, `layouts`, `flexipages`, `staticresources`, `labels`, `settings`), decomposed metadata types, multiple package directories and modularisation, `.forceignore` semantics and precedence, `package.xml` and `destructiveChangesPre/Post.xml` manifests with `sf project generate manifest`, the source-tracking model (`sf project deploy|retrieve start|preview`, `delete source`, `reset tracking`, `--ignore-conflicts`), source/metadata format conversion, team repo conventions, and the `.vibeforce/` layout. Use this skill when creating or reorganising a DX project, deciding where a metadata file belongs, writing or audit

grzmol Bundle

Covers how Salesforce metadata reaches an org — source deploy versus Metadata API versus change sets versus DevOps Center versus packaging, the full sf project deploy start flag surface, validate plus quick deploy as the production path, test levels and coverage rules, destructive changes, per-metadata-type deployment gotchas (Profiles, Flows, custom settings, record types, picklists, sharing rules, layouts, translations), environment promotion pipelines with git branching, drift and conflict detection, rollback reality, zero-downtime schema and Apex change patterns, CI/CD wiring, and the deployment error catalogue. Use this skill when a task mentions sf project deploy start, deploy validate, deploy quick, --test-level, RunLocalTests, destructiveChanges.xml, package.xml manifests, quick deploy job ids, deployment failures, promoting to production, rollback, or the vf-check deploy-validate / deploy-quick / verify checks.

grzmol Bundle

Building, previewing, testing and shipping Agentforce agents from a source-tracked SFDX project - authoring bundles and Agent Script, the Bot/BotVersion/GenAiPlannerBundle/GenAiPlugin/GenAiFunction metadata graph, custom agent actions written as invocable Apex, autolaunched Flows or prompt templates, action input/output JSON schemas, prompt templates and grounding, the agent user and the permissions it runs under, AiEvaluationDefinition test definitions and the sf agent test commands, agent preview in simulated and live mode, trace analysis, and moving an agent from scratch org to sandbox to production. Use this skill when a story mentions an agent, a copilot, a subagent, a topic, an agent action, an authoring bundle, a .agent file, Agentforce Builder, Testing Center, Prompt Builder, an @InvocableMethod that an agent calls, or when an agent routes to the wrong action, returns data the running user should not see, or fails to activate after a deploy.

grzmol Bundle

Runs Salesforce delivery as a five-wave parallel agent workflow with deterministic gates. Use when a story, bug, or refactor touches more than one metadata type, when several agents must work at once without colliding, when deciding which wave a task belongs to, when a gate fails and the wave must abort, or when wiring the vf-check runner, the vibe-force hooks, and the .vibeforce state files into a pipeline from local edit to verified production deploy.

grzmol Bundle

Post-deploy verification of Salesforce work in a real org - reading deploy results with sf project deploy report and sf project deploy resume, running org Apex tests with sf apex run test and sf apex get test, executing anonymous-Apex smoke probes with sf apex run --file, verifying data with sf data query, verifying configuration (permission set assignments, custom metadata rows, active flow versions, scheduled jobs via CronTrigger, platform event channels, Named Credential reachability), checking org health with sf org list limits and AsyncApexJob failures, and deciding between rollback and forward fix when verification fails. Use this skill in wave 4 after a deploy or quick deploy completes, when a deployment reports Succeeded but behaviour is unproven, when interpreting deploy or Apex test failures, when authoring smoke scripts under scripts/apex/, or when producing the verification report at .vibeforce/reports/smoke-*.json.

samihalawa Skill

Design, implement, publish, deploy, and verify a compact but complete MCP server for a product, codebase, or external service. Use when creating or improving MCP support, exposing broad product capabilities through a token-efficient tool surface, adding remote Streamable HTTP at /mcp and stdio through an npm npx package, publishing a public GitHub MCP repo, optionally registering it in MetaMCP, integrating official or unofficial APIs, providing Anchor Browser identity-backed authentication for browser-only gaps, returning direct application URLs, or exposing tenant-scoped debug logs and full entity lifecycle operations.

grzmol Bundle

Standing security audit of a Salesforce org and its source - who holds ModifyAllData, ViewAllData, AuthorApex and ViewEncryptedData, the object and field matrix behind every permission set, profile sprawl, Apex class and @AuraEnabled exposure, org-wide defaults and without-sharing code, guest user and Experience Cloud surface, Named and External Credentials, secrets in source and in git history, and the Setup-only checks (Health Check, session and password policy, login IP ranges, MFA, Setup Audit Trail) that no CLI command covers. Produces a severity-ranked findings report with evidence and a fix per item. Use when onboarding an org, preparing a security review or audit response, or periodically. Not for reviewing a diff - that is the sf-security-reviewer agent - and not for writing secure Apex, which is skill sf-security-model.

stas2-git Bundle

Use when a user has a workbook goal and the workflow needs a constrained implementation plan that maps the request to likely sheets, VBA modules, validation checks, and risk points before any code is generated.

stas2-git Bundle

Use when a workflow is about to change one or more Excel workbooks and needs timestamped backups, working copies, or other reversible safety rails before VBA injection or rebuild steps.

codegobrrrr9 Bundle

Pre-ship safety for vibe-coded apps. Stops the agent from putting secrets in client code or git, shipping database tables without row-level security, leaving API routes without auth, opening CORS to everyone, or exposing admin keys in the browser. Use whenever writing app code that touches secrets, databases, auth, payments, or deployment, and when the user says ship, deploy, launch, publish, go live, is this safe, or /seatbelt.