runpod/runpod-plugins-official

write-guide

Write or change a skill, reference doc or golden path in this repo so it agrees with the concept graph and is linked to it.

Quelltext ansehen
Originales Skill-Dokument

Aus dem Quell-Repository gerendert; Überschriften, Beispiele, Code, Tabellen, Links und Bilder bleiben erhalten.

Write a guide against the concept graph

This repo has two kinds of content that must agree:

  • Concepts (plugins/runpod/skills/runpod-usage/concepts/*.yaml) hold exact facts as

rules, each citing a public source. They are the source of truth for what is true.

  • Guides (every SKILL.md, reference/*.md and golden path) explain, teach and

demonstrate. They are the source of truth for how to do it.

A guide states facts that the concept rules support, and links to the concepts it covers. A concept is covered by at least one guide. pnpm check:guides enforces both links.

Writing or changing a guide

  1. Find the concepts it touches before writing (run these in ontology/tools/):
bash
   pnpm build:sqlite
   pnpm query tree "<concept>"      # the concept, its children and the guides that cover them
   pnpm query search "<question>"   # the rules that answer a question
   pnpm query concept "<name>"      # every rule on one concept, with evidence
  1. Write from the rules. Every factual claim (a limit, a default, a state, what an action

does, what exists) must match a rule. Explain it in your own words and add the how: the commands, order, pitfalls and verification.

  • If the guide needs a fact that no rule has, add the rule first with the

add-concept skill, citing the spec, the public docs or a live probe. Then write the guide.

  • If a rule is wrong or out of date, fix the rule (and its evidence) in the same change.
  • Never let a guide and a rule say different things. If you find a disagreement, the

public source decides which one changes.

  1. Declare the links.
GuideWhereExample
SKILL.mdmetadata.concepts in the frontmatterconcepts: [pod, network-volume]
Reference doca concepts: line in frontmatter at the top---<br>concepts: [runpod-secret]<br>---
Golden pathlanes, mcp and concepts in frontmattersee plugins/runpod/skills/runpod/golden-paths/README.md

List the concepts the guide actually explains or uses, not every word it mentions. pnpm build:bundle --suggest lists the concepts each golden path names, as candidates. A reference doc that a rule already cites as evidence is linked automatically, but list its concepts anyway when it covers more than the citing rules.

  1. Point to the rules when a doc is the main explanation of a concept. End it with a short

"Exact rules" section with a Markdown link to each concept file (from a reference doc the target is ../concepts/<id>.yaml).

  1. Route it. A new reference doc gets a row in its skill's SKILL.md table. A new golden

path gets rows in the router's table and golden-paths/README.md.

After adding or changing a concept

  1. pnpm check:guides fails if the new concept has no guide. Extend an existing doc or write

a new one, following the steps above.

  1. Find the guides that already cover it and check they still agree with the rules:
bash
   pnpm query tree "<concept>"                    # guides linked to it
   grep -rln "<name or alias>" ../../plugins/     # guides that mention it without a link
  1. When a rule cites a skill file as evidence and you change that file, re-read the rule:

grep -rn "<path>" ../../plugins/runpod/skills/runpod-usage/concepts/.

Style

Follow plugins/runpod/skills/runpod-usage/concepts/README.md → "Writing style" and the repo conventions in AGENTS.md: plain present tense, "Runpod", code identifiers in backticks, no "currently" or "not yet", and positive claims over claims that something is missing (a missing capability needs the spec or docs as evidence, and CLI absence claims are checked by hooks/check_cli_absence_claims.py).

Check

bash
cd ontology/tools
pnpm format && pnpm validate --strict && pnpm check:guides && pnpm test
cd ../.. && python3 hooks/check_links.py && python3 hooks/check_runpod_branding.py

check:guides must report no errors, and the build line "concepts with a guide" must stay at every concept.

aus demselben Repository

Weitere Skills

Alle Skills
runpod
Community

cost-audit

'Read-only Runpod spend audit: find idle spend, explain serverless billing when nothing seems to run, break spend down by resource type and by resource, and give a whole-account snapshot. Every figure comes from the MCP billing and list reads; it recommends actions and never stops or changes anything. Use when the user asks about their bill, what is costing money, what is running on the account, or tells you to stop or delete idle resources it did not name by id: the audit with ids and the user'

Installationen
5
GitHub Stars
46
Aktualisiert
9. Okt.
runpod
Community

discovery

'Answer what is available, what fits and the price against Runpod''s catalogs: GPU and CPU types with price, live stock per data center and per product, the CUDA versions that have capacity, the Hub worker marketplace, the public template catalog, and the pay-per-use Public Endpoints. Read-only: it filters to the user''s real constraint, sizes a model''s VRAM need against real stock, quotes price and stock from the reads, and says "none found" rather than inventing an entry. Use when the user as

Installationen
5
GitHub Stars
46
Aktualisiert
9. Okt.
runpod
Community

endpoint-ops

'Operate a Serverless endpoint that already exists: diagnose queued jobs and dying workers, tune scaling, idle timeout and FlashBoot safely, pin the GPU selection, and manage the queue (cancel a job, purge). Read-only by default; changes only the exact setting the user authorized, with a read before and after. Use when the user has an endpoint and asks why it is slow, stuck or failing, or wants one of its settings changed through the Runpod MCP tools.'

Installationen
5
GitHub Stars
46
Aktualisiert
9. Okt.
runpod
Community

pod-deploy

Provision a Runpod Pod for interactive, development or training use and tell the user exactly how to connect to it. Reads stock before creating, picks the image and GPU class from the catalog reads, exposes only the ports the workload needs, hands back the working proxy URL or SSH address, and for training co-locates a network volume so checkpoints outlive the Pod. Also covers creating a Pod and stopping it immediately, so that only its disk bills until the user comes back. Use when the user wan

Installationen
5
GitHub Stars
46
Aktualisiert
9. Okt.