|
| 1 | +name: Skill proposal |
| 2 | +description: Propose a new skill for the AMD Skills catalog. |
| 3 | +title: "[Skill proposal] <short outcome or skill name>" |
| 4 | +labels: |
| 5 | + - skill-proposal |
| 6 | +body: |
| 7 | + - type: markdown |
| 8 | + attributes: |
| 9 | + value: | |
| 10 | + Thanks for proposing a skill! Skills earn their keep on **repeated, opinionated AMD workflows**. |
| 11 | + Before filing, please skim `CONTRIBUTING.md` (especially *"Is this task a good fit for a skill?"* and the two contribution paths) so we can route this proposal quickly. |
| 12 | +
|
| 13 | + Fill out the short fields below, then describe the skill in detail at the end. |
| 14 | +
|
| 15 | + - type: input |
| 16 | + id: name |
| 17 | + attributes: |
| 18 | + label: Proposed skill name |
| 19 | + description: Use `lowercase-with-hyphens`, max 64 characters, action- or outcome-oriented (e.g. `porting-cuda-to-hip`, `tuning-mi300x`, `picking-rocm-container`). Avoid generic names like `helper` or `gpu-stuff`. |
| 20 | + placeholder: e.g. tuning-mi300x-inference |
| 21 | + validations: |
| 22 | + required: true |
| 23 | + |
| 24 | + - type: dropdown |
| 25 | + id: prior_art |
| 26 | + attributes: |
| 27 | + label: Does something like this already exist? |
| 28 | + description: Help us avoid duplicating effort. If you pick a "Yes" option, link the prior art in the description below. |
| 29 | + options: |
| 30 | + - "No — new idea" |
| 31 | + - "Yes — as documentation, a runbook, or internal guide" |
| 32 | + - "Yes — as a similar skill in another catalog or repo" |
| 33 | + - "Not sure — happy to discuss" |
| 34 | + validations: |
| 35 | + required: true |
| 36 | + |
| 37 | + - type: dropdown |
| 38 | + id: home |
| 39 | + attributes: |
| 40 | + label: Where should this skill live? |
| 41 | + description: See the two contribution paths in `CONTRIBUTING.md`. Path A skills are authored under `skills/` in this repo; Path B skills live in a product repo and are registered here via `catalog/`. |
| 42 | + options: |
| 43 | + - "Path A: incubated in this repo (may move to a product repo and continbue to be registered here)" |
| 44 | + - "Path B: authored in a product repo (HIP, ROCm, Ryzen AI, Lemonade, ...) and registered here" |
| 45 | + - "Not sure yet — needs discussion" |
| 46 | + validations: |
| 47 | + required: true |
| 48 | + |
| 49 | + - type: dropdown |
| 50 | + id: focus_area |
| 51 | + attributes: |
| 52 | + label: Catalog focus area |
| 53 | + description: Which focus area in the catalog best fits this skill? |
| 54 | + options: |
| 55 | + - "Application integration" |
| 56 | + - "Hardware-native" |
| 57 | + - "Cross-stack porting" |
| 58 | + - "Profiling and delivery" |
| 59 | + - "Other / not sure" |
| 60 | + validations: |
| 61 | + required: true |
| 62 | + |
| 63 | + - type: textarea |
| 64 | + id: description |
| 65 | + attributes: |
| 66 | + label: Skill description |
| 67 | + description: | |
| 68 | + Describe the skill in as much detail as you can. Useful things to cover: |
| 69 | + - **User goal**: what is the user trying to achieve when this skill should fire? |
| 70 | + - **Trigger surface**: words, phrases, file extensions, error messages, product names that should route to this skill. |
| 71 | + - **Platform Scope**: Is this for client? server? Both? |
| 72 | + - **Inputs and outputs**: what does the agent receive, and what does it produce? |
| 73 | + validations: |
| 74 | + required: true |
0 commit comments