okdev

DevOps Community

Repo stars 0
Author repo skills-registry

Interpretation is structured for decision-making; original keeps the upstream SKILL.md unchanged.

Decide Fit First

Core job: Use when helping someone use okdev to initialize, start, inspect, connect to, sync with, troubleshoot, or tear down Kubernetes d…
Best fit: Use it when the task has reusable inputs, steps, and validation criteria rather than a one-off answer.
Avoid forcing it: If the source lacks commands, platform support, or external-service evidence, keep those fields unknown instead of guessing.

Design Intent

Structure: The skill is organized around “Overview”, “When to Use”, “Working Style”, “Quick Heuristics”, showing how the author expects the agent to judge fit, collect context, and produce verifiable output.
Trigger evidence: Prioritize the author’s wording around when to use it, what context to collect, and what output shape to produce.
Evidence boundary: Author text states facts, repository files prove commands and paths, and Fluxly only adds fit, limits, and usage judgment.

How To Use It

Inputs: Provide target material, scope, expected result, forbidden changes, and validation method.
Invocation: Name okdev directly; if the source includes slash commands, start with the command and then add task context.
Validation: Start small and check whether the result follows “Overview / When to Use / Working Style” before expanding.

Boundaries And Review

Dependencies: It usually needs no extra API key, so start with a small validation task.
Permissions: Declared permissions include read / shell-exec; ask the agent to state file, command, and rollback boundaries before acting.
Quality bar: A useful result names the deliverable, evidence, and next action. Generic prose means the task needs tighter context.

okdev

Overview

Use this skill for end-user questions about the okdev CLI. Prefer okdev-native workflows over generic Kubernetes or SSH advice, and anchor answers in the repo docs before giving detailed guidance.

Primary docs:

docs/quickstart.md
docs/command-reference.md
docs/config-manifest.md
docs/troubleshooting.md

When to Use

Use this skill when the request involves:

okdev init, up, status, ssh, exec, cp, sync, ports, down, prune
config discovery or .okdev.yaml / .okdev/okdev.yaml
sync behavior, session reuse, port forwards, or SSH access
manifest-backed workloads such as job, generic, or pytorchjob
attachable pod behavior, multi-pod sessions, or inter-pod SSH

Do not use this skill for:

editing the okdev source code itself
generic cluster administration unrelated to okdev
generic SSH or tmux advice that does not depend on okdev

Working Style

Identify the workload shape first: simple pod vs manifest-backed workload.
Prefer okdev commands and documented config fields over low-level kubectl workarounds.
For troubleshooting, ask for the smallest okdev output that exposes state, usually okdev status --details.
Escalate to kubectl checks only when okdev output is not enough.
When the question is about multi-pod behavior, read references/multipod.md.
When the question is about symptoms or failures, read references/troubleshooting.md.
When the question is about normal usage flow, read references/workflows.md.

Quick Heuristics

Config discovery order is: explicit --config, .okdev/okdev.yaml, .okdev.yaml, okdev.yaml.
okdev up reuses an existing session workload by default.
Use okdev up --reconcile when workload-shaping config changed and the user wants those changes applied.
Use okdev sync --reset when local/background sync state is stale but the workload itself is still the intended one.
okdev ssh is the okdev-managed interactive path; ssh okdev-<session> is the plain SSH host alias path.
For sync, SSH, and port-forward issues, okdev status --details is usually the first useful diagnostic.

Source: acmore/okdev — distributed by TomeVault.

Fluxly profile Author and license come from source; runtime, permissions, and network are Fluxly detections or estimates

Fluxly category: DevOps
Author-declared agents: No explicit declaration found; this is not inferred or tested compatibility
Static check: 88 / 100 · heuristic scan, not runtime safety proof
Author / version / license: @tomevault-io · no license declared
Fluxly token estimate: Lean
Fluxly setup estimate: Guided setup
External API key: No requirement detected
Detected OS requirements: Unspecified
Runtime requirements: Unspecified
Detected file/system behavior: Read-only
Shell exec
Detected network behavior: Local-only
Install commands: None (reference only)

Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.

Heads up: 未限定 allowed-tools，默认拥有全部工具权限。

Output preview okdev.preview

The current SKILL.md does not define a fixed output example.

SKILL.md SKILL.md

# okdev

## Overview

Use this skill for end-user questions about the `okdev` CLI. Prefer `okdev`-native workflows over generic Kubernetes or SSH advice, and anchor answers in the repo docs before giving detailed guidance.

Primary docs:

- `docs/quickstart.md`
- `docs/command-reference.md`
- `docs/config-manifest.md`
- `docs/troubleshooting.md`

## When to Use

Use this skill when the request involves:

- `okdev init`, `up`, `status`, `ssh`, `exec`, `cp`, `sync`, `ports`, `down`, `prune`
- config discovery or `.okdev.yaml` / `.okdev/okdev.yaml`
- sync behavior, session reuse, port forwards, or SSH access
- manifest-backed workloads such as `job`, `generic`, or `pytorchjob`
- attachable pod behavior, multi-pod sessions, or inter-pod SSH

Do not use this skill for:

- editing the `okdev` source code itself
- generic cluster administration unrelated to `okdev`
- generic SSH or tmux advice that does not depend on `okdev`

## Working Style

1. Identify the workload shape first: simple pod vs manifest-backed workload.
2. Prefer `okdev` commands and documented config fields over low-level `kubectl` workarounds.
3. For troubleshooting, ask for the smallest `okdev` output that exposes state, usually `okdev status --details`.
4. Escalate to `kubectl` checks only when `okdev` output is not enough.
5. When the question is about multi-pod behavior, read `references/multipod.md`.
6. When the question is about symptoms or failures, read `references/troubleshooting.md`.
7. When the question is about normal usage flow, read `references/workflows.md`.

## Quick Heuristics

- Config discovery order is: explicit `--config`, `.okdev/okdev.yaml`, `.okdev.yaml`, `okdev.yaml`.
- `okdev up` reuses an existing session workload by default.

…

Evidence boundary and execution chain

Author text anchors workflow facts; Fluxly only indexes current sections, terms, files, and commands.

sections -> Overview → When to Use → Working Style → Quick Heuristics
terms    -> Use this skill for end-user questions about the okdev CLI. · 1. Identify the workload shape first: simple pod vs manifest-backed workload. · - Config discovery order is: explicit --config, .okdev/okdev.yaml, .okdev.yaml, okdev.yaml. · --- > Source: [acmore/okdev](https://github.com/acmore/okdev) — distributed by [TomeVault](https://tomevault.io).
files/cmd -> okdev · docs/quickstart.md · docs/command-reference.md · docs/config-manifest.md · docs/troubleshooting.md · okdev init · status · ssh
body sha256 -> 059bbd5fe500

Decide Fit First

Design Intent

How To Use It

Boundaries And Review

okdev

Overview

When to Use

Working Style

Quick Heuristics

Discussion