Inference Autopilot
rednote-machine-learning/Inference-autopilot
Analyze, benchmark, diagnose, and optimize large-model inference deployments from hardware inventory, model details, workload traces, and latency or throughput SLOs.
Agent skill
Castai Performance Tuning
by jeremylongshore in jeremylongshore/tons-of-skills-marketplace
Tune CAST AI node and workload autoscaling against application SLOs, scheduling constraints, and recommendation confidence.
Install Castai Performance Tuning
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill castai-performance-tuning -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jeremylongshore/tons-of-skills-marketplace castai-performance-tuning --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/.curated/castai-performance-tuning .claude/skills/castai-performance-tuning && rm -rf skills-srcUse ~/.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/
Install the "castai-performance-tuning" agent skill from https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/main/skills/.curated/castai-performance-tuning into .claude/skills/castai-performance-tuning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "castai-performance-tuning", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/main/skills/.curated/castai-performance-tuningType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill castai-performance-tuning -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jeremylongshore/tons-of-skills-marketplace castai-performance-tuning --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/.curated/castai-performance-tuning .agents/skills/castai-performance-tuning && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "castai-performance-tuning" agent skill from https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/main/skills/.curated/castai-performance-tuning into .agents/skills/castai-performance-tuning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "castai-performance-tuning", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill castai-performance-tuning -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jeremylongshore/tons-of-skills-marketplace castai-performance-tuning --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/.curated/castai-performance-tuning .cursor/skills/castai-performance-tuning && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "castai-performance-tuning" agent skill from https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/main/skills/.curated/castai-performance-tuning into .cursor/skills/castai-performance-tuning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "castai-performance-tuning", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/jeremylongshore/tons-of-skills-marketplace.git --path skills/.curated/castai-performance-tuning--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill castai-performance-tuning -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jeremylongshore/tons-of-skills-marketplace castai-performance-tuning --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/.curated/castai-performance-tuning .gemini/skills/castai-performance-tuning && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "castai-performance-tuning" agent skill from https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/main/skills/.curated/castai-performance-tuning into .gemini/skills/castai-performance-tuning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "castai-performance-tuning", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install jeremylongshore/tons-of-skills-marketplace castai-performance-tuningInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill castai-performance-tuning -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/.curated/castai-performance-tuning .github/skills/castai-performance-tuning && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "castai-performance-tuning" agent skill from https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/main/skills/.curated/castai-performance-tuning into .github/skills/castai-performance-tuning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "castai-performance-tuning", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill castai-performance-tuning -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jeremylongshore/tons-of-skills-marketplace castai-performance-tuning --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/.curated/castai-performance-tuning .opencode/skills/castai-performance-tuning && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "castai-performance-tuning" agent skill from https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/main/skills/.curated/castai-performance-tuning into .opencode/skills/castai-performance-tuning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "castai-performance-tuning", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
castai-performance-tuning- GitHub stars
- 2.8k
- Token cost
- ~1.2k tokens
- SKILL.md length
- 442 words
- Files
- 2 (incl. references)
- Skills in repo
- 3,342
- Repo updated
- First seen
- Licence
- MIT
At a glance
Tune CAST AI node and workload autoscaling against application SLOs, scheduling constraints, and recommendation confidence.
- Works in 6 steps: Build the timeline → Inspect effective workload policy → Choose application mode → …
- Optimization causes latency
- SKILL.md covers Overview, Prerequisites, Instructions and Tool Discipline, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Castai Performance Tuning is an agent skill from jeremylongshore/tons-of-skills-marketplace. Tune CAST AI node and workload autoscaling against application SLOs, scheduling constraints, and recommendation confidence. Use when optimization causes latency, disruption, slow provisioning, or unstable replica and resource behavior. Trigger with: "tune CAST AI performance", "stabilize CAST AI autoscaling", "fix CAST AI scaling latency".
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/official-docs.md`). Compatibility notes: Requires workload telemetry, SLOs, and read access to effective CAST AI and Kubernetes scaling configuration
It sits in DevOps & Cloud, covering Site reliability engineering. The repository describes itself as: Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com. The licence is MIT.
When your agent uses it
- Optimization causes latency
- Slow provisioning
- Unstable replica and resource behavior
- With: tune CAST AI performance
Example prompts
- “tune CAST AI performance”
- “stabilize CAST AI autoscaling”
- “fix CAST AI scaling latency”
- “/castai-performance-tuning”
Requirements
- Compatibility (from SKILL.md): Requires workload telemetry, SLOs, and read access to effective CAST AI and Kubernetes scaling configuration
- Pre-approved tools (allowed-tools): Read, Grep, Write, Edit, Bash(kubectl:*)
Workflow steps
6 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
ReadGrepWriteEditBash(kubectl:*)
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
docs.cast.ai
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.
Compatibility
Requires workload telemetry, SLOs, and read access to effective CAST AI and Kubernetes scaling configuration
From compatibility in the SKILL.md frontmatter.
Context cost
Castai Performance Tuning loads about 1.2k tokens when it runs, and up to ~1.4k if it reads all its reference files. Until then it costs about 92 tokens; SKILL.md has 442 words of instructions outside code blocks.
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 jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 442 words, ~1,155 tokens.
Download SKILL.mdSave it as
.claude/skills/castai-performance-tuning/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- castai-performance-tuning
- description
- Tune CAST AI node and workload autoscaling against application SLOs, scheduling constraints, and recommendation confidence. Use when optimization causes latency, disruption, slow provisioning, or unstable replica and resource behavior. Trigger with: "tune CAST AI performance", "stabilize CAST AI autoscaling", "fix CAST AI scaling latency".
- allowed-tools
- Read, Grep, Write, Edit, Bash(kubectl:*)
- compatibility
- Requires workload telemetry, SLOs, and read access to effective CAST AI and Kubernetes scaling configuration
- version
- 2.0.0
- argument-hint
- [cluster-and-workload]
- model
- inherit
- effort
- high
- license
- MIT
- author
- Jeremy Longshore <jeremy@intentsolutions.io>
- tags
- saas, kubernetes, cast-ai, performance, autoscaling
CAST AI Performance Guardrail Tuning
Overview
Tune from evidence across workload demand, requests, replicas, scheduling, and nodes. Keep vertical, horizontal, and node changes separate so a lower bill never hides degraded service.
Prerequisites
- Workload SLOs, error budget, traffic profile, and representative observation window
- Effective scaling policy, annotations, HPA, PDB, node templates, and cluster limits
- Metrics-server and healthy CAST AI components
Instructions
Step 1: Build the timeline
Use Read and Grep to align request rate, latency, errors, pod requests, replicas, pending time, evictions, node provisioning, and policy changes. Identify whether the symptom precedes or follows CAST AI action.
Step 2: Inspect effective workload policy
Check policy assignment, recommendation percentile, overhead, optimization threshold, minimum and maximum resources, confidence, and automation state. Invalid annotation YAML is ignored; an invalid policy name can fall back to a system policy, so verify effective state rather than intended text.
Step 3: Choose application mode
Use Immediate mode only when evictions are acceptable and PDB behavior is proven. Use Deferred mode when recommendations should apply at natural recreation. Account for recommendation confidence and gradual behavior on newly onboarded clusters.
Step 4: Reconcile horizontal scaling
Inspect the native autoscaling/v2 HPA, metric targets, replica bounds, stabilization, and ownership. Avoid competing HPA controllers. When CAST AI takes ownership, treat that as a configuration migration with explicit rollback.
Step 5: Reconcile node capacity
Use Bash(kubectl:*) to examine pending reasons, affinities, topology, taints, resource shape, and scheduling events. Review node templates and maximum CPU limits. More permissive capacity is not automatically safer or cheaper.
Show full SKILL.md (190 more words)Show less
Step 6: Change one variable
Use Write or Edit to record one hypothesis, one configuration change, performance and cost guardrails, observation window, and rollback. Compare the same traffic class and retain SLO evidence before expanding.
Tool Discipline
Use Read and Grep for metrics, policy, and configuration evidence. Use Write and Edit for the tuning experiment and decision. Use Bash(kubectl:*) for bounded, non-secret inspection of workloads, HPAs, PDBs, events, and nodes.
Output
- Joined performance and scaling timeline
- Effective vertical, horizontal, and node control map
- One-variable experiment with SLO and cost guardrails
- Expand, hold, or rollback decision
Examples
A workload oscillates because replica stabilization and vertical requests changed together. The team freezes vertical automation, tunes the managed HPA in a canary, and restores rightsizing only after replica behavior is stable.
Error Handling
| Failure | Response |
|---|---|
| Metrics are missing or misaligned | Stop tuning and repair observability |
| Effective policy differs from annotation | Correct YAML or policy assignment before experimentation |
| PDB blocks needed replacement | Prefer Deferred mode or review disruption with the owner |
| SLO regresses | Roll back immediately even if cost improves |
Resources
© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file (references) in skills/.curated/castai-performance-tuning of jeremylongshore/tons-of-skills-marketplace.
- SKILL.md
- references/official-docs.md
Open the folder on GitHubat commit cfae287
Compare with similar skills
Castai Performance Tuning 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Castai Performance Tuning this skilljeremylongshore/tons-of-skills-marketplace | 2.8k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Inference Autopilotrednote-machine-learning/Inference-autopilot | 144 | — | ~4.5k | Automated safety check: Pass | Apache-2.0 | |
| Executing Distributed System Testsshenli/distributed-system-testing | 231 | — | ~5.1k | Automated safety check: Notes | MIT | |
| Alerting Irmgrafana/skills | 282 | 1 repos | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| Slo Implementationwshobson/agents | 40k | 11 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Agentforce D360 Analyzeforcedotcom/sf-skills | 1.1k | — | ~3.4k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Executing Distributed System Tests
shenli/distributed-system-testing
A skill your agent uses when running a previously designed distributed-systems test plan against a real or simulated cluster — driving fault injection, workload, chaos scenarios, linearizability /…
- Official
Alerting Irm
grafana/skills
Configure Grafana Alerting, Incident Response Management (IRM), and SLOs end-to-end — provisions Grafana-managed and data-source-managed alert rules, contact points (Slack/PagerDuty/email/webhook)…
Slo Implementation
wshobson/agents
Define and implement Service Level Indicators (SLIs) and Service Level Objectives (SLOs) with error budgets and alerting.
Agentforce D360 Analyze
forcedotcom/sf-skills
Data Cloud 360° view of a single Agentforce session. An agent skill from forcedotcom/sf-skills.
- Official
Promql
grafana/skills
Write, validate, and optimize PromQL for Prometheus / Grafana Mimir / Grafana Cloud Metrics.
More from jeremylongshore/tons-of-skills-marketplace
All 3,342 skills in this repoPerforming Security Code Review
jeremylongshore/tons-of-skills-marketplace
Execute this skill enables AI assistant to conduct a security-focused code review using the security-agent plugin.
Adapting Transfer Learning Models
jeremylongshore/tons-of-skills-marketplace
Build this skill automates the adaptation of pre-trained machine learning models using transfer learning techniques.
Agent Context Loader
jeremylongshore/tons-of-skills-marketplace
Execute proactive auto-loading: automatically detects and loads agents.md files.
Aggregating Performance Metrics
jeremylongshore/tons-of-skills-marketplace
Aggregate and centralize performance metrics from applications, systems, databases, caches, and services.
Analyzing Capacity Planning
jeremylongshore/tons-of-skills-marketplace
Execute this skill enables AI assistant to analyze capacity requirements and plan for future growth.
Analyzing Database Indexes
jeremylongshore/tons-of-skills-marketplace
Process use when you need to work with database indexing. An agent skill from jeremylongshore/tons-of-skills-marketplace.
Related
Categories
Questions about Castai Performance Tuning
What does Castai Performance Tuning do?
Tune CAST AI node and workload autoscaling against application SLOs, scheduling constraints, and recommendation confidence. Castai Performance Tuning is an agent skill from jeremylongshore/tons-of-skills-marketplace. Tune CAST AI node and workload autoscaling against application SLOs, scheduling constraints, and recommendation confidence.
When should I use Castai Performance Tuning?
Castai Performance Tuning fits situations like: optimization causes latency; slow provisioning; unstable replica and resource behavior; with: tune CAST AI performance.
How do I install Castai Performance Tuning in Claude Code?
Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill castai-performance-tuning -a claude-code`. Or copy the skill folder (skills/.curated/castai-performance-tuning in jeremylongshore/tons-of-skills-marketplace) into .claude/skills/castai-performance-tuning in your project. Claude Code loads it when a task matches its description.
How do I install Castai Performance Tuning in Codex?
Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill castai-performance-tuning -a codex`. Or copy the skill folder (skills/.curated/castai-performance-tuning in jeremylongshore/tons-of-skills-marketplace) into .agents/skills/castai-performance-tuning in your project. Codex loads it when a task matches its description.
Can I use Castai Performance Tuning 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 jeremylongshore/tons-of-skills-marketplace --skill castai-performance-tuning -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/castai-performance-tuning, .gemini/skills/castai-performance-tuning, .github/skills/castai-performance-tuning and .opencode/skills/castai-performance-tuning in your project.
What does Castai Performance Tuning need to run?
SKILL.md names no scripts, command-line tools or credentials: Castai Performance Tuning is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Grep, Write, Edit, Bash(kubectl:*). Compatibility (from SKILL.md): Requires workload telemetry, SLOs, and read access to effective CAST AI and Kubernetes scaling configuration.
Does Castai Performance Tuning access the network?
SKILL.md names 1 domain. As links in the text: docs.cast.ai. This is read from the text; nothing was executed.
Is Castai Performance Tuning 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 Castai Performance Tuning use?
Castai Performance Tuning is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Castai Performance Tuning use?
About 1.2k tokens (SKILL.md is roughly 4.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 262 tokens, read only when the agent opens those files.
What are the alternatives to Castai Performance Tuning?
Skills that share tags, products or a category with Castai Performance Tuning: Inference Autopilot (rednote-machine-learning/Inference-autopilot, 144 stars), Executing Distributed System Tests (shenli/distributed-system-testing, 231 stars), Alerting Irm (grafana/skills, 282 stars) and Slo Implementation (wshobson/agents, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Castai Performance Tuning?
jeremylongshore (a GitHub user) maintains it in jeremylongshore/tons-of-skills-marketplace, which has 2,827 GitHub stars. The repository holds 3,342 skills in this directory. The repository was last updated on October 10, 2026.
Source: jeremylongshore/tons-of-skills-marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.