В каталоге 183 730 навыков в 14 категориях.
Active incident response — restore service first, identify root cause second, file the incident report third. For AICP t...
Structured workflow for production incident management following SRE best practices.Covers incident declaration, triage,...
Guides incident response from detection through postmortem. Use when designing on-call runbooks, triaging production inc...
Internal — for Boundless team members only. Query the Boundless Indexer REST API for on-chain market data, staking, PoVW...
AIOps-style CloudBase inspection skill (v3). Use when users need health checks, log diagnosis, alarm interpretation (CPU...
Add any SaaS API as a first-class integration. Provide the service name — ops-integrate discovers auth patterns, tests c...
Investigate incidents and analyze logs - query CloudWatch logs with filters,correlate events across services, identify e...
Linear command center. Shows current sprint, creates/updates issues, manages priorities, syncs with GSD phases.
Local LLM health checks and cache management. Probe Ollama/vLLM/SGLang endpoints, clean model caches.
Internal — for Boundless team members only. Query AWS CloudWatch logs for Boundless services (provers, slasher, distribu...
Routine non-incident upkeep — security audit Python deps (`pip-audit`), refresh model GGUF inventory, prune Docker dangl...
Ops Manager. Use for SOPs and operating processes in Phase 8. Real titles: Ops Manager.
Guidance for writing OpenStack operations manual procedures following NASA document standards. Use when authoring per-se...
Marketing command center. Email campaigns (Klaviyo), paid ads (Meta/Google), analytics (GA4), SEO, and social media metr...
Autonomous PR merge pipeline. Scans all repos for open PRs, dispatches subagents to fix CI, resolve conflicts, address r...
Structured workflow for infrastructure migration planning including cloud migrations,technology upgrades, and data cente...
Investigate and triage operational signals — alarms, pages, monitors, and ops issues — using the Ops Mission Control inc...
Unified APM and monitoring surface. Polls Datadog, New Relic, and OpenTelemetry backends for active alerts, error traces...
Monitor deployed infrastructure health and performance - check resource status,query CloudWatch metrics (CPU, memory, re...
Monitor Sentry for unresolved errors in frontend and backend projects. Supports filtering by project, environment, and t...
Business-level "what should I do next". Priority stack — fires > unread comms > ready-to-merge PRs > Linear sprint > rev...
Designs and troubleshoots NUKE-based CI/CD pipelines for .NET services. Use when refactoring target graphs, splitting te...
Provides NZBGeek API search and SABnzbd API download operations for ANY content type (movies, TV, music, apps, books, et...
Set up on-call for a service — the rotation, primary and secondary, the handoff checklist, severity levels, incident rol...
Autonomous multi-project orchestration engine. Audits all registered projects, structures work into dependency-wired tas...
Parallel operational readiness validation using G-3 OPERATIONS. Deploy 6 probes to validate workflow readiness before ex...
Performance analysis for Expo + serverless backend projects. Runs Lighthouse audits, bundle size analysis, and k6 load t...
Compile, profile, diagnose, optimize, and compare Ascend NPU operators across CANN versions and A2/A3/A5 for Ascend C, C...
Internal — for Boundless team members only. Monitor Boundless deployment pipelines (AWS CodePipeline + CodeBuild) on the...
Structured workflow for onboarding new services to the internal platformincluding infrastructure provisioning, observabi...
算子精度标准。描述 Ascend C 算子各种 dtype 输出对应的精度比对标准(混合容差 atol/rtol)。当需要(1)评估算子精度是否达标,(2)编写 ST 测试验证精度,(3)处理 FP16/FP32/BF16 等不同数据类型精...
NPU 性能采集与分析,支持 msprof application 标准可比较计时(每例 10 组 warmup→target 取中位数)、msprof 深度指标采集与算子级瓶颈定位、kernel-level 对比测试(--compare/...
Portfolio dashboard for all GSD-tracked projects. Scans ~/Projects and ~/gsd-workspaces for .planning/ directories, show...
Publish local .claude skills/loops to Ametyst — verbatim, flattened, no brain rewrite; optional retire-local (MOVE origi...
Internal — for Boundless team members only. Cross-reference Boundless indexer API data, broker telemetry, and service lo...
AUTO-INVOKE when user mentions ops, runbook, inventory, audit trail, ops repo, sysops, devops, itops, infrastructure ope...
Clean and rebuild the solution to ensure a fresh state. Use this when the user faces transient build errors or stale art...
Cut an emisar product release end to end — changelog, version, license date, gate, commit, signed tag, push, and GitHub...
Respond to incidents and apply remediations - restart services, scale resources,clear caches, update configurations, rol...
Revenue and costs tracker. AWS spend via aws ce, credits tracker, project revenue stages. Shows burn rate, runway estima...
Revert AICP/fleet to a recorded last-known-good state — uses the rollback contract that `ops-deploy` Operation 4 records...
Manage the local development environment for Expo + serverless backend projects. Supports start, stop, restart, and stat...
Write an operational runbook any qualified operator can execute under pressure, with verification, failure paths, and es...
Use when running ops automation workflows for ops-runbook-demo.
Write runbooks for a service — one per paging alert plus the common incident types — each a checklist of is-this-real ch...
Provision, manage, and terminate RunPod GPU instances for LLM training. Use when user says "spin up GPU", "create RunPod...
当用户执行系统级命令(sysctl、iptables、systemctl、Docker 配置、数据库 DDL)或进行服务器运维操作时触发。提供运维安全规范。
Query SAM.gov for federal contracts, entity registrations, exclusions, and opportunities. Uses official GSA APIs for gov...
Runtime scaling — adjust replicas, resources, autoscaling
Structured workflow for infrastructure security audits including compliancevalidation, vulnerability assessment, and sec...
Post-setup credential manager. Shows current integration status (configured/missing/expired) and lets you update individ...
Guide user through support platform setup. Use when user says "set up", "configure", "I'm on step X", or provides API ke...
Ship local changes to origin/dev with hard-enforced git safety policy, integrator-shell lock/guard flow, validate-change...
NPU 仿真器技能。提供 CANN Simulator 的使用指导,包括精度仿真、性能仿真、流水线分析。当需要在无 NPU 硬件环境下验证算子功能、分析性能瓶颈、定位精度问题时使用。也用于分析已有的 npusim 性能报告(summary....
Define SLOs for a service — an SLI per critical user journey as good events over valid events, a target and window, the...
生成或校验算子 spec.yaml(算子的 L0 数学约束唯一真值)。当用户提及:生成 spec.yaml、新算子 spec 骨架、scaffold spec、validate spec.yaml、spec schema 校验、算子规格校验...
Cross-platform, hardware-adaptive system optimizer. Auto-detects macOS / Linux / WSL / Windows (MINGW/Cygwin/MSYS2) and...
Lightweight green/red status panel for every configured integration. No gather, no actions.
Generate a recurring status snapshot of a folder-based workspace (clients, pipeline files, recent activity, command heal...
Stream Deck control skill for agents. Provides ability to restart streamdeck daemons, execute button tasks, query status...
The primary supply-chain analyst role for Northwind Logistics. Owns carrier on-time-delivery (OTD), lane cost benchmarks...
Turn messy campaign requests into actionable programmatic operations tickets with required fields, severity, SLA, owner,...
Cross-platform issue triage. Pulls from Sentry (MCP), Linear (MCP), GitHub Issues (gh). Cross-references against code to...
Operations and infrastructure utilities for vm0 project
Health check all services across environments. Checks frontend URLs, backend GraphQL endpoints, and reports response tim...
Voice operations — make phone calls (Bland AI), text-to-speech (ElevenLabs), transcribe audio (Whisper/Groq). Replace Op...
WhatsApp Business Cloud API — send approved template messages at scale, manage templates with approval tracking, and int...
Workstation diagnostics, health monitoring, and maintenance. Knows this machine and can help troubleshoot, clean up, and...
YOLO mode. Spawns 4 parallel C-suite agents (CEO, CTO, CFO, COO). Each analyzes the business from their perspective usin...
Use when about to take any outward or offensive action (request, payload, persistence, lateral movement, exfil, or feedi...
Builds red-team OPSEC plans that connect an authorized objective to observable artifacts, detection risk, countermeasure...
Install or set up from the source-backed instructions:
Use when a prompt contains systematic or IUPAC-like chemical names that need deterministic name-to-structure parsing thr...
Detect proxy requirements and route fetches through secure proxies with auth handling and offline fallbacks. Use when da...
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work...
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after...
Archive multiple completed changes at once. Use when user wants to archive several changes in one operation.
Archive multiple completed changes at once. Use when archiving several parallel changes.
Continue implementing tasks from an OpenSpec change. Use when user wants to resume work on an existing change.
Continue working on an OpenSpec change by creating the next artifact. Use when the user wants to progress their change,...
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use wh...
Fast-forward through OpenSpec artifact creation. Use when the user wants to quickly create all artifacts needed for impl...
Triggers when the user says「opsx 批量修复」「批量 opsx-jira-fix」「opsx-jira-fix-queue」「opsx-jira-fix-batch」「批量 OpenSpec Jira 修复」/...
OpenSpec-flavored end-to-end Jira bug-fix workflow that persists root cause, behavior change, fix plan, verification, an...
Create a new OpenSpec change directory. Use when user wants to start a new change by creating just the directory scaffol...
Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, f...
Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.
Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they wan...
Eight-stage PDCA problem-solving workflow that persists analysis, proposal, design review, plan, execution, and verifica...
Sync delta specs from a change to main specs. Use when user wants to apply delta specs from a change to the main specs d...
Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spe...
Verify an OpenSpec change is complete and ready. Use when user wants to check if a change is ready for archive or implem...
Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, cor...
Shared OpenSpec workspace gate for OPSX workflows: locate project root, verify openspec/, and require exact native OPSX...
Comprehensive guide to opt. Master the concepts, implementation, best practices, and real-world applications of opt in p...
Optional retrospective for projects with local or self-hosted AI models (Ollama, LM Studio, llama.cpp, vLLM, an embeddin...
Drafts opt-out forms and notices of exclusion for class actions, settlements, arbitration clauses, and privacy programs....
Guide for porting code from optaic-v0 to optaic-trading. Use when migrating DataAPI, pipelines, stores, accessors, opera...
Route Optax tasks across optimizer construction, loss and schedule workflows, and advanced utilities or contrib topics.
Discover and deliver repository optimization work end to end: identify performance/reliability/maintainability/security/...