GitHub organization
Agent skills by AMD-AGI
- skills
- 13
- repositories
- 2
Repositories by AMD-AGI
Skills by AMD-AGI, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Critic layer for the inference optimizer. An agent skill from AMD-AGI/Hyperloom. | AMD-AGI/ | 216 | — | ~3.5k | Automated safety check: Pass | Unknown | today |
| 2 | Inspect the current Spur (AMD SLURM-compatible) cluster node-allocation state and produce a Markdown report (optionally rendered to a standalone HTML page) covering the caller's account/QoS… | AMD-AGI/ | 130 | — | ~2.7k | Automated safety check: Pass | Unknown | today |
| 3 | Review a Hyperloom pull request. An agent skill from AMD-AGI/Hyperloom. | AMD-AGI/ | 216 | — | ~4.8k | Automated safety check: Pass | Unknown | today |
| 4 | Compare a Primus backend against an upstream repository or reference, verify git state, dependencies, directory changes, and integration coupling, then generate comparison reports, dashboard… | AMD-AGI/ | 130 | — | ~3.4k | Automated safety check: Pass | Unknown | today |
| 5 | Deploys or restarts the shared global Experience KB that Hyperloom workspaces push their Experiences to and pull others' from, validates authenticated health, and tells each workspace which .env… | AMD-AGI/ | 216 | — | ~1.1k | Automated safety check: Notes | Unknown | today |
| 6 | Inventory and explain the patch (monkey-patch) optimizations Primus layers over upstream training backends such as Megatron-LM, TorchTitan, and MaxText, including their version compatibility… | AMD-AGI/ | 130 | — | ~3.5k | Automated safety check: Pass | Unknown | today |
| 7 | Update the Primus documentation for a monthly training-image release — bump version references, realign the bare-metal install scripts with the release Dockerfiles, record the published image stacks… | AMD-AGI/ | 130 | — | ~2.9k | Automated safety check: Pass | Unknown | today |
| 8 | Run a 4-hour multi-node Hyperloom Qwen3-30B-A3B optimization (Infera PD-disaggregated or RayJob aggregated) with --nodes 2 and sglang MoE tuning on MI325X. | AMD-AGI/ | 216 | — | ~1.8k | Automated safety check: Pass | Unknown | today |
| 9 | Validate SLURM cluster nodes by running actual training jobs in groups. | AMD-AGI/ | 130 | — | ~3.7k | Automated safety check: Pass | Unknown | today |
| 10 | Generate a validation plan and test scaffolding to check a Primus optimization that has been ported into a user's own training framework, across correctness (numerical accuracy vs a reference)… | AMD-AGI/ | 130 | — | ~1.5k | Automated safety check: Pass | Unknown | today |
| 11 | Check available idle nodes in a SLURM cluster. An agent skill from AMD-AGI/Primus. | AMD-AGI/ | 130 | — | ~3k | Automated safety check: Warn | Unknown | today |
| 12 | Opinionated guide for using Primus Projection to choose parallelism (TP/PP/EP/CP/DP) and pipeline schedules, validate memory fit on target nodes, reason about communication collectives, and explore… | AMD-AGI/ | 130 | — | ~5.3k | Automated safety check: Pass | Unknown | today |
| 13 | Configures Hyperloom after pip install --target . An agent skill from AMD-AGI/Hyperloom. | AMD-AGI/ | 216 | — | ~7.2k | Automated safety check: Notes | Unknown | today |
Questions, answered from the data.
What is the best skill by AMD-AGI?
Critic Agent from AMD-AGI/Hyperloom ranks first of the 13 skills by AMD-AGI listed here, with the highest score: its repository has 216 GitHub stars, its SKILL.md loads about 3.5k tokens and it passes the automated safety check with no findings. Next come Spur Cluster Status and Review PR.
Are AMD-AGI's skills official?
None yet. All 13 skills by AMD-AGI listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.