SkillAtlasSkill 详情

castai-prod-checklist

A model-agnostic agent-skills platform.

审核状态：已审核Quality 72Security 70

复制安装命令

用 Codex 或 Claude 安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它先审查 Skill 页面再帮你安装。

复制前请先查看来源、License 和安全提示。

项目 README

来源文件：README.md

抓取于 2026年8月27日

Tons of Skills

A model-agnostic agent-skills platform. The canonical layer is harness-free by construction; Claude Code is currently the verified-native harness. Other harnesses remain engineering candidates until their native-path integration is verified; source research alone is never presented as public support.

Release CLI Plugins Skills GitHub Stars skills.sh Sponsor: Kobiton Buy me a monster

ko-fi

Version semantics: the release badge is this marketplace's display version. npm packages, including the ccpi CLI and publishable plugins, retain their own package versions; they are intentionally not expected to equal the display version. The version-surface checker governs the display surfaces without rewriting package semver.

Install

Inside Claude Code, one command installs the whole marketplace:

/plugin marketplace add jeremylongshore/claude-code-plugins

Or use the CLI:

pnpm add -g @intentsolutionsio/ccpi
ccpi install devops-automation-pack

Browse the marketplace · Explore plugins · Download bundles

Killer Skill of the Week — no-ai-slop by Peter Yang

Strip AI slop from any draft — named-pattern edits that keep the writer's real voice

no-ai-slop does two jobs and refuses to fake a third. In Edit mode it makes the minimum effective edit — cutting throat-clearing, weak verbs, and abstract nouns while deliberately preserving the writer's cadence, bluntness, humor, and honest admissions, so a rough draft still sounds like the same person afterward. In Detect mode it names each AI-slop pattern it finds, quotes the offending line, and gives the fix in a few words — and pointedly does NOT score the draft or guess whether an AI wrote it. That restraint is the whole point: AI detectors guess; named patterns are evidence the reader can check. MIT-licensed, single focused skill, actively maintained by Peter Yang.

"AI detectors guess. Named patterns are evidence the user can check." — Peter Yang

Grade: A | Week of July 22, 2026 (W30) | View on GitHub

Previous picks: tonone, mnemos, databricks-pack, kobiton-automate, skyvern, code-cleanup, web-analytics, token-optimizer, executive-assistant-skills, skill-creator, cursor-pack, crypto-portfolio-tracker. See all at tonsofskills.com.

Scale, labeled

Every number below names the cohort it counts and the command that reproduces it — an unlabeled count is how a corpus ends up with five contradictory answers to "how many skills."

CountCohortReproduce with
442catalog plugins (catalog-entry cohort)node scripts/generate-readme-toc.mjs over marketplace.extended.json
3,067marketplace-visible skills (distinct)node -e "import('./scripts/corpus-resolver.mjs').then(m=>console.log(m.resolveCorpus('marketplace-visible').length))"
347agent definitions in pluginsgit ls-files 'plugins/**' | grep '/agents/.*\.md'
19plugin categoriesls -d plugins/*/

📦 Live npm Downloads

Across 396 published packages in the claude-code-plugins namespace. Updated daily by GitHub Actions.

WindowAll packagesEstablished (>30d)
Last 24 hours962962
Last 7 days2,9202,916
Last 30 days12,86812,779

"Established" excludes packages first published within the last 30 days, so a bulk-publish event doesn't dominate the headline.

Top 10 by last 30 days:

#PackageLast 30d
1@intentsolutionsio/openrouter-pack556
2@intentsolutionsio/groq-pack496
3@intentsolutionsio/databricks-pack274
4@intentsolutionsio/clickhouse-pack273
5@intentsolutionsio/wallet-security-auditor263
6@intentsolutionsio/notion-pack258
7@intentsolutionsio/elevenlabs-pack244
8@intentsolutionsio/freshie-inventory-manager214
9@intentsolutionsio/supabase-pack210
10@intentsolutionsio/agency-os204

Last refreshed 2026-08-19T03:03:05.709Z.

Ways in

Five real questions, five doors — each resolves to a live, generated surface, never a hand-maintained list:

Browse by category

The 19 categories below link into the live marketplace. Plugin counts are the catalog-entry cohort — regenerated from marketplace.extended.json by this generator; the catalog itself lives on tonsofskills.com, never in this file (§ 6A of the platform blueprint).

CategoryPlugins
🤖AI & Machine Learning36
🎭AI Agents & Agency10
🔌API Development26
💼Business Tools6
👥Community21
₿Crypto & Web327
💾Database26
🎨Design2
🔧DevOps & Infrastructure36
📚Examples & Templates5
🧩MCP Servers16
📦Packages5
⚡Performance25
✅Productivity30
🎁SaaS Skill Packs106
🔐Security27
✨Skill Enhancers9
🧪Testing28
📁Analytics1

What the classes mean

Four artifact classes live in this repository, distinguished on sight and never blurred — provenance is a truth requirement here, not a UX nicety:

ClassWhat it isHow the reader can tell
Canonical skillFirst-party, harness-free, the source of truthNo .source.json in its plugin directory
Generated adapterA thin, machine-produced harness projectionLives under a generated path with a "generated — do not edit" header
First-party packageAn Intent Solutions distribution (npm, cowork zip)@intentsolutionsio scope, IS-authored license
Upstream mirrorSomebody else's work, hosted mirror-by-default.source.json present — upstream author, license, and pinned commit recorded

Certification

Not yet certified. The certification program (tiers T0–T4 with retained, hash-matched evidence) is a later epic of the platform blueprint; until its report exists, no artifact on this surface claims a tier. This line is rendered from the absence of certification-report.json — honestly, not cosmetically.

Contribute

Start with the contribution guide, then the intake and review standards every submission passes through:

Governance

Provenance

External plugins are hosted mirror-by-default: the contributor's repository stays the source of truth, every mirrored source is pinned in a content lockfile, and upstream credit — author, license, resolved commit — is recorded in the mirror itself. Improvements flow by upstreaming to the author's repository, never by silently editing the mirror. The full decision record is the external-sync model.

License

MIT for the repository scaffolding and first-party tooling; each plugin carries its own license in its manifest, and mirrored plugins keep their upstream license verbatim.

其他

中风险

  • 来源需自行核对维护者身份。
  • 包含脚本或命令调用，安装前请复核。
  • 可能需要外部 token、网络权限或第三方服务。
  • 未检测到高风险命令。
  • 扫描发现：3 条。

Codex — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库：git clone https://github.com/jeremylongshore/tons-of-skills-marketplace.git
  3. 将 "skills/.curated/castai-prod-checklist" 文件夹复制到 Codex 的 skills 目录中。
  4. 重启 Codex 让新的 skill 生效。

Codex — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Codex 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Codex 让新的 skill 生效。

Claude Code — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库：git clone https://github.com/jeremylongshore/tons-of-skills-marketplace.git
  3. 将 "skills/.curated/castai-prod-checklist" 文件夹复制到 Claude Code 的 skills 目录中。
  4. 重启 Claude Code 让新的 skill 生效。

Claude Code — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Claude Code 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Claude Code 让新的 skill 生效。

Cursor — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库：git clone https://github.com/jeremylongshore/tons-of-skills-marketplace.git
  3. 将 "skills/.curated/castai-prod-checklist" 文件夹复制到 Cursor 的 skills 目录中。
  4. 重启 Cursor 让新的 skill 生效。

Cursor — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Cursor 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Cursor 让新的 skill 生效。

GitHub Copilot — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库：git clone https://github.com/jeremylongshore/tons-of-skills-marketplace.git
  3. 将 "skills/.curated/castai-prod-checklist" 文件夹复制到 GitHub Copilot 的 skills 目录中。
  4. 重启 GitHub Copilot 让新的 skill 生效。

GitHub Copilot — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 GitHub Copilot 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 GitHub Copilot 让新的 skill 生效。

Windsurf — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库：git clone https://github.com/jeremylongshore/tons-of-skills-marketplace.git
  3. 将 "skills/.curated/castai-prod-checklist" 文件夹复制到 Windsurf 的 skills 目录中。
  4. 重启 Windsurf 让新的 skill 生效。

Windsurf — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Windsurf 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Windsurf 让新的 skill 生效。
查看 SKILL.md 原文
name: castai-prod-checklist
description: 'Production readiness checklist for CAST AI cluster onboarding.

  Use when going live with CAST AI autoscaling, validating Phase 2 setup,

  or preparing for production cost optimization.

  Trigger with phrases like "cast ai production", "cast ai go-live",

  "cast ai checklist", "cast ai launch".

  '
allowed-tools: Read, Bash(kubectl:*), Bash(curl:*), Bash(helm:*), Grep
version: 1.4.0
license: MIT
author: Jeremy Longshore <jeremy@intentsolutions.io>
tags:
- saas
- kubernetes
- cost-optimization
- castai
compatibility: Designed for Claude Code

CAST AI Production Checklist

Overview

Complete checklist for enabling CAST AI cost optimization on a production Kubernetes cluster. Covers Phase 1 (monitoring) through Phase 2 (full automation) with validation steps at each stage.

Prerequisites

  • CAST AI tested on a staging cluster first
  • Production API key (Full Access)
  • Change management approval for node lifecycle changes

Instructions

Complete the phases in order and preserve evidence for every checked item. Start in monitoring-only mode, verify the production cluster identity and baseline metrics, then request the approved change window before enabling automation. Use a two-person review for capacity limits, disruption budgets, and the emergency-disable procedure; do not copy staging keys, policies, or test evidence into the production record without revalidation.

Phase 1: Monitoring Only

  • Agent installed with read-only key
  • Agent pod healthy: kubectl get pods -n castai-agent
  • Console shows cluster as "Connected"
  • Savings report generating (wait 24h for full data)
  • Review savings estimate before enabling automation

Phase 2: Autoscaling Enabled

  • Full Access API key provisioned and stored in secrets manager
  • Cluster controller installed
  • Evictor installed with conservative settings (non-aggressive)
  • Spot handler installed for graceful interruption handling
  • Autoscaler policies configured with appropriate limits:
    • clusterLimits.cpu.maxCores set to safe ceiling
    • unschedulablePods.headroom configured (10-15%)
    • nodeDownscaler.emptyNodes.delaySeconds >= 300 for production
    • spotInstances.spotDiversityEnabled = true
  • Node templates created for workload-specific needs (GPU, high-memory)
  • PodDisruptionBudgets set on all critical workloads

Workload Autoscaler

  • Workload autoscaler installed
  • Critical deployments annotated with min/max resource bounds
  • Anti-shrink cooldown set (300s minimum)
  • Memory headroom >= 20% for production workloads

Security

  • API key in secrets manager (not Helm values files)
  • Kvisor security agent installed
  • Network policies applied to castai-agent namespace
  • RBAC reviewed and minimized
  • Key rotation scheduled (90-day interval)

Monitoring and Alerting

  • Alert on agent pod restarts: kube_pod_container_status_restarts_total{namespace="castai-agent"}
  • Alert on API errors in agent logs
  • CAST AI console email notifications enabled
  • Savings report reviewed weekly
  • Dashboard tracking spot vs on-demand node ratio

Rollback Procedure

# Disable autoscaling immediately (keeps agent monitoring)
curl -X PUT -H "X-API-Key: ${CASTAI_API_KEY}" \
  -H "Content-Type: application/json" \
  "https://api.cast.ai/v1/kubernetes/clusters/${CASTAI_CLUSTER_ID}/policies" \
  -d '{"enabled": false}'

# Or remove all CAST AI components
helm uninstall castai-evictor -n castai-agent
helm uninstall cluster-controller -n castai-agent
# Keep the agent for monitoring if desired

Error Handling

ConditionResponse
Agent offline or API authentication failsKeep automation disabled; verify secret reference, RBAC, and egress before retrying.
Policy response differs from the approved limitsStop rollout, restore the prior policy, and reopen change review.
Eviction or latency alert firesDisable autoscaling using the tested path and engage the workload owner.
Rollback command cannot be exercised safelyDo not proceed to go-live; repair the runbook and test it in staging.

Validation Commands

# Final pre-go-live verification
echo "=== CAST AI Production Validation ==="

# Agent healthy
kubectl get pods -n castai-agent -o wide

# All components running
helm list -n castai-agent

# Policies correct
curl -s -H "X-API-Key: ${CASTAI_API_KEY}" \
  "https://api.cast.ai/v1/kubernetes/clusters/${CASTAI_CLUSTER_ID}/policies" \
  | jq '{enabled, unschedulablePods: .unschedulablePods.enabled, downscaler: .nodeDownscaler.enabled, spot: .spotInstances.enabled}'

# Savings estimate
curl -s -H "X-API-Key: ${CASTAI_API_KEY}" \
  "https://api.cast.ai/v1/kubernetes/clusters/${CASTAI_CLUSTER_ID}/savings" \
  | jq '{monthly: .monthlySavings, percent: .savingsPercentage}'

Output

Create a production-readiness record that ties each checklist item to its evidence, accountable owner, approval, validation timestamp, and tested rollback. A healthy agent alone does not authorize go-live: policy limits, disruption controls, monitoring, and the emergency-disable path must all be confirmed against the intended production cluster.

Examples

For a production launch, capture a redacted policy response, current Helm release state, agent health, alert test, and savings-baseline review in the change record. If an approval or rollback test is missing, leave autoscaling disabled and resolve that gap before enabling it for production workloads.

Resources

Next Steps

For version upgrades, see castai-upgrade-migration.

发现问题？提交给管理员复核

评分：

评论 (0)

暂无评论，成为第一个评论者吧！