New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Fastllm Operate

by azrtydxb in azrtydxb/Fastllm-proxy

Operate and diagnose the FastLLM deployment on the kw Kubernetes cluster — check whether it is running, bring it back after a shutdown, deploy manifest changes, and work out why the gateway is…

Apache-2.0Auto-check passedDevOps & Cloud

Install Fastllm Operate

skills CLI
$ npx skills add azrtydxb/Fastllm-proxy --skill fastllm-operate -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install azrtydxb/Fastllm-proxy fastllm-operate --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/azrtydxb/Fastllm-proxy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/fastllm-operate .claude/skills/fastllm-operate && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
fastllm-operate
GitHub stars
108
Token cost
~932 tokens
SKILL.md length
433 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
Apache-2.0

At a glance

Operate and diagnose the FastLLM deployment on the kw Kubernetes cluster — check whether it is running, bring it back after a shutdown, deploy manifest changes, and work out why the gateway is…

  • Works in 7 steps: Nodes schedulable — kubectl get nodes.… → Workloads not scaled to zero — a clean… → Registry up — the image lives… → …
  • Pods not starting
  • SKILL.md covers Topology, Diagnose in dependency order, Verify, do not assume and Do not
  • Calls kubectl

What it does

Fastllm Operate is an agent skill from azrtydxb/Fastllm-proxy. Operate and diagnose the FastLLM deployment on the kw Kubernetes cluster — check whether it is running, bring it back after a shutdown, deploy manifest changes, and work out why the gateway is unreachable, returning 503, or serving stale policy. Use for "is fastllm up", pods not starting, ImagePullBackOff, empty service endpoints, a missing Postgres pod, or backends out of rotation. Not for API calls against a healthy instance (fastllm-routing, fastllm-gateway and friends).

Its SKILL.md is about 930 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in DevOps & Cloud, covering Container orchestration and Deployment. It works with Kubernetes and PostgreSQL. The repository describes itself as: The lowest-overhead LLM router. Production-ready, highly available, one OpenAI-compatible endpoint in front of 80 providers and your own vLLM/SGLang — 0.76 µs per request, no I/O… The licence is Apache-2.0.

When your agent uses it

  • Pods not starting
  • ImagePullBackOff
  • Empty service endpoints
  • A missing Postgres pod

Example prompts

  • “is fastllm up”
  • “/fastllm-operate”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Nodes schedulable — kubectl get nodes. Ready,SchedulingDisabled means
  2. Workloads not scaled to zero — a clean shutdown scales deployments and
  3. Registry up — the image lives in-cluster. If nexus/nexus is scaled to
  4. Postgres present — a CNPG cluster can report Cluster in healthy state
  5. Image matches the schema — `migration N was previously applied but is
  6. Service endpoints non-empty — kubectl -n fastllm get endpoints. A stale
  7. Backends in rotation — the proxy logs backend healthy, back in rotation

What it can do on your machine

Read from SKILL.md and the folder at commit 5d53db8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • kubectl

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use kubectl, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Fastllm Operate loads about 932 tokens when it runs. Until then it costs about 124 tokens; SKILL.md has 433 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~124
When it runs · the whole SKILL.md, loaded when a task matches
~932

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from azrtydxb/Fastllm-proxy at commit 5d53db8, republished under its Apache-2.0 licence (© azrtydxb). 433 words, ~932 tokens.

Download SKILL.mdSave it as .claude/skills/fastllm-operate/SKILL.md (or your agent's skills folder).
name
fastllm-operate
description
Operate and diagnose the FastLLM deployment on the kw Kubernetes cluster — check whether it is running, bring it back after a shutdown, deploy manifest changes, and work out why the gateway is unreachable, returning 503, or serving stale policy. Use for "is fastllm up", pods not starting, ImagePullBackOff, empty service endpoints, a missing Postgres pod, or backends out of rotation. Not for API calls against a healthy instance (fastllm-routing, fastllm-gateway and friends).

Operating FastLLM on kw

Topology

Namespacefastllm (control plane, proxy, CNPG Postgres)
Operatorfastllm-system
Gateway VIP192.168.10.125, alt 192.168.10.126
Admin VIP192.168.10.129:4001 (HTTPS, self-signed — use -k)
Postgres dev VIP192.168.10.127:5432
Registry192.168.10.131 (Nexus, in the nexus namespace)
Manifestsdeploy/ — applied continuously, so they are the source of truth

Diagnose in dependency order

Work down. Each step is worthless until the one above it passes.

  1. Nodes schedulable — kubectl get nodes. Ready,SchedulingDisabled means cordoned: existing pods keep running while nothing new can start. A blanket cordon across every node is a deliberate shutdown, not a fault, and it causes unrelated-looking failures downstream (Longhorn's driver-deployer crash-loops because its helper pod cannot schedule).
  2. Workloads not scaled to zero — a clean shutdown scales deployments and statefulsets to 0. Recover the intended count from kubectl.kubernetes.io/last-applied-configuration rather than assuming 1.
  3. Registry up — the image lives in-cluster. If nexus/nexus is scaled to 0, everything else is ImagePullBackOff for a reason that has nothing to do with the workload.
  4. Postgres present — a CNPG cluster can report Cluster in healthy state with no pods at all when hibernated. Check kubectl -n fastllm get cluster fastllm-pg -o jsonpath='{.metadata.annotations}' for cnpg.io/hibernation: on; clear it with kubectl -n fastllm annotate cluster fastllm-pg cnpg.io/hibernation=off --overwrite. Nothing in describe or the operator log points at this.
  5. Image matches the schema — migration N was previously applied but is missing in the resolved migrations means the deployed image is older than the database. Compare the manifest's tag against migrations/.
  6. Service endpoints non-empty — kubectl -n fastllm get endpoints. A stale selector (for example a Helm-era four-label selector against single-label pods) leaves a Service with <none> and the proxy reporting No route to host at the control plane.
  7. Backends in rotation — the proxy logs backend healthy, back in rotation and backend failed N consecutive probes, out of rotation by URL.
Show full SKILL.md (125 more words)Show less

Verify, do not assume

  • Gateway 401 = healthy and rejecting an unauthenticated request. That is a successful smoke test.
  • Gateway /health 503 = running but has no usable snapshot.
  • curl 000 = nothing listening; that is the real failure.
  • A Deployment's spec.selector is immutable. Changing labels means deleting and recreating it, and the Service selector must be updated to match or endpoints go empty.

Do not

  • Do not undo a blanket cordon or scale-up stateful workloads without asking — a full shutdown is usually deliberate, and databases starting cold at once is not free.
  • Do not edit an applied migration. sqlx checksums them and refuses to start.
  • Do not write to Postgres to make a config change when an admin session is available; SQL writes bypass the audit trail.

© azrtydxb, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/fastllm-operate of azrtydxb/Fastllm-proxy.

Open the folder on GitHubat commit 5d53db8

Compare with similar skills

Fastllm Operate next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Fastllm Operate compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Fastllm Operate this skillazrtydxb/Fastllm-proxy108—~932Automated safety check: PassApache-2.0
Platform Engineeringmagnus919/agent-skills115—~2.4kAutomated safety check: PassMIT
Mirrord Operatormetalbear-co/mirrord5.4k1 repos~4.6kAutomated safety check: PassMIT
LangBot Deployment Guidelangbot-app/LangBot18k—~1.5kAutomated safety check: NotesApache-2.0
Openbkn Deployopenbkn-ai/bkn-foundry661—~1.9kAutomated safety check: NotesCustom licence
KubeShark for KubernetesLukasNiessen/kubernetes-skill446—~1.2kAutomated safety check: PassMIT

Similar skills

  • Platform Engineering

    magnus919/agent-skills

    A skill your agent uses when building or operating internal developer platforms: infrastructure as code, CI/CD, container orchestration, service networking, secrets, and observability, or when…

    115 GitHub stars~2.4k tokensUpdated yesterday
    DevOps & CloudAuto-check passed

  • Mirrord Operator

    metalbear-co/mirrord

    Help users install and configure the mirrord Operator for team/enterprise environments.

    5.4k GitHub starsUsed in 1 repo~4.6k tokens
    DevOps & CloudAuto-check passed

  • LangBot Deployment Guide

    langbot-app/LangBot

    Deploys and configures a LangBot instance with Docker Compose or Kubernetes, covering config.yaml, the Box sandbox runtime, the plugin runtime and the global API key.

    18k GitHub stars~1.5k tokensUpdated today
    DevOps & CloudAuto-check: notes

  • Openbkn Deploy

    openbkn-ai/bkn-foundry

    Deploy or upgrade OpenBKN on a customer-authorized Linux server through the repository's deploy scripts, with preflight checks, explicit confirmation, secret handling, and post-deployment…

    661 GitHub stars~1.9k tokensUpdated today
    DevOps & CloudAuto-check: notes

  • KubeShark for Kubernetes

    LukasNiessen/kubernetes-skill

    Keeps Kubernetes manifests, Helm charts and policies grounded by diagnosing six failure modes, such as insecure defaults and API drift, and loading only matching references.

    446 GitHub stars~1.2k tokensUpdated 28 days ago
    DevOps & CloudAuto-check passed

  • GitOps with ArgoCD and Flux

    wshobson/agents

    Sets up GitOps continuous delivery for Kubernetes with ArgoCD or Flux, covering installation, repository layout, sync policies, progressive delivery and secrets.

    40k GitHub starsUsed in 12 repos~1.5k tokens
    DevOps & CloudAuto-check passed

More from azrtydxb/Fastllm-proxy

All 14 skills in this repo

  • Fastllm Agents

    azrtydxb/Fastllm-proxy

    Manage and invoke A2A agents behind FastLLM — register, patch, delete and list agents on the control plane, list them through the gateway, fetch an agent card, and invoke an agent by name.

    108 GitHub stars~512 tokensUpdated today
    Auto-check passed

  • Fastllm Backends

    azrtydxb/Fastllm-proxy

    Run and troubleshoot the inference backends on the DGX Spark pair that FastLLM proxies to — starting or stopping models with vLLM, SGLang or sparkrun, choosing memory and speculative-decoding…

    108 GitHub stars~980 tokensUpdated today
    Auto-check passed

  • Fastllm Classifier

    azrtydxb/Fastllm-proxy

    Manage FastLLM prompt classes for semantic routing — create classes and their example prompts, list or delete them, and evaluate how a given prompt would be classified.

    108 GitHub stars~499 tokensUpdated today
    Auto-check passed

  • Fastllm Deployment

    azrtydxb/Fastllm-proxy

    Inspect and control the running FastLLM deployment — read effective configuration and deployment settings, force a snapshot rebuild, fetch the snapshot the proxies consume, and check liveness and…

    108 GitHub stars~727 tokensUpdated today
    Auto-check passed

  • Fastllm Gateway

    azrtydxb/Fastllm-proxy

    Send inference requests through the FastLLM OpenAI-compatible gateway — chat completions, completions, embeddings, rerank, score, responses, moderations, audio speech and transcription, image…

    108 GitHub stars~926 tokensUpdated today
    Auto-check passed

  • Fastllm MCP

    azrtydxb/Fastllm-proxy

    Manage and use MCP servers behind FastLLM — register, patch, delete and list MCP servers on the control plane, and list or call their tools through the gateway.

    108 GitHub stars~515 tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Fastllm Operate

What does Fastllm Operate do?

Operate and diagnose the FastLLM deployment on the kw Kubernetes cluster — check whether it is running, bring it back after a shutdown, deploy manifest changes, and work out why the gateway is…. Fastllm Operate is an agent skill from azrtydxb/Fastllm-proxy. Operate and diagnose the FastLLM deployment on the kw Kubernetes cluster — check whether it is running, bring it back after a shutdown, deploy manifest changes, and work out why the gateway is unreachable, returning 503, or serving stale policy.

When should I use Fastllm Operate?

Fastllm Operate fits situations like: pods not starting; imagePullBackOff; empty service endpoints; A missing Postgres pod.

How do I install Fastllm Operate in Claude Code?

Run `npx skills add azrtydxb/Fastllm-proxy --skill fastllm-operate -a claude-code`. Or copy the skill folder (.claude/skills/fastllm-operate in azrtydxb/Fastllm-proxy) into .claude/skills/fastllm-operate in your project. Claude Code loads it when a task matches its description.

How do I install Fastllm Operate in Codex?

Run `npx skills add azrtydxb/Fastllm-proxy --skill fastllm-operate -a codex`. Or copy the skill folder (.claude/skills/fastllm-operate in azrtydxb/Fastllm-proxy) into .agents/skills/fastllm-operate in your project. Codex loads it when a task matches its description.

Can I use Fastllm Operate in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add azrtydxb/Fastllm-proxy --skill fastllm-operate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fastllm-operate, .gemini/skills/fastllm-operate, .github/skills/fastllm-operate and .opencode/skills/fastllm-operate in your project.

What does Fastllm Operate need to run?

Going by SKILL.md and its folder, Fastllm Operate needs the command-line tools its instructions call (kubectl).

Does Fastllm Operate access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Fastllm Operate safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Fastllm Operate use?

Fastllm Operate is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Fastllm Operate use?

About 932 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Fastllm Operate?

Skills that share tags, products or a category with Fastllm Operate: Platform Engineering (magnus919/agent-skills, 115 stars), Mirrord Operator (metalbear-co/mirrord, 5.4k stars), LangBot Deployment Guide (langbot-app/LangBot, 18k stars) and Openbkn Deploy (openbkn-ai/bkn-foundry, 661 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Fastllm Operate?

azrtydxb (a GitHub organization) maintains it in azrtydxb/Fastllm-proxy, which has 108 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 5, 2026.

Source: azrtydxb/Fastllm-proxy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.