GitHub user
Agent skills by sorryhyun
- skills
- 12
- repository
- 1
Repositories by sorryhyun
Skills by sorryhyun, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | The model catalog (library/downloads.py) — one Asset row per weight (repo, files, destination, installed probe), packs, resolve() name order, and the rule that loaders import their default paths… | sorryhyun/ | 125 | — | ~502 | Automated safety check: Pass | MIT | today |
| 2 | 2.Qwen21 Qwen-Image-2.1 LoRA line (NOT Anima) — running cache/train through the daemon, make gui-qwen, the CacheRequest/TrainRequest flag surface and how to add a field, model-dir resolution, cache layout… | sorryhyun/ | 125 | — | ~1.9k | Automated safety check: Notes | MIT | today |
| 3 | The trainer ↔ animetools boundary — what the curation split moved out, the typed request/stage API the make targets build, the git-pin dev loop and its stale-venv trap, and the tests that guard the… | sorryhyun/ | 125 | — | ~1.5k | Automated safety check: Pass | MIT | today |
| 4 | Free-fit native-shape bucketing — the token bands per edge tier, tier choice at preprocess time, the compiledynamicseq coupling and per-tier graph budget, and why training never needs --targetres. | sorryhyun/ | 125 | — | ~932 | Automated safety check: Pass | MIT | today |
| 5 | 5.Captions Caption pipeline — position-clause grammar (never hand-split a caption), make caption-autotag modes, make caption-position (v2 rewrite rules and gates), and the preprocess-stage wiring for both. | sorryhyun/ | 125 | — | ~1.3k | Automated safety check: Pass | MIT | today |
| 6 | The ComfyUI node map — which node lives in which standalone repo vs in-tree under customnodes/, where each is symlinked, and the vendor-sync rule for the vendor/ subsets. | sorryhyun/ | 125 | — | ~470 | Automated safety check: Pass | MIT | today |
| 7 | 7.Daemon Submit, monitor, and manage GPU jobs through the anima daemon (make daemon-, make gen, make run-status, MCP bridge, discovery). | sorryhyun/ | 125 | — | ~2.1k | Automated safety check: Pass | MIT | today |
| 8 | The animalora programmatic façade for embedders — namespaces and lazy re-exports, the request-driven GenerationRequest inference path, adapter family from checkpoint metadata, and ANIMAHOME path… | sorryhyun/ | 125 | — | ~544 | Automated safety check: Pass | MIT | today |
| 9 | The LoRA-family three-axis routing surface (usemoestyle / routeperlayer / routersource) — the variant matrix, per-variant module details (LoRA/T-LoRA/Hydra), and GlobalRouter mechanics. | sorryhyun/ | 125 | — | ~1.3k | Automated safety check: Pass | MIT | today |
| 10 | 10.Sigma Lowres σ-demoted training (--sigmalowres) — routing rules and their validation, span schedules, the shipped combolate recipe vs combo, and the sibling-latent precache requirement. | sorryhyun/ | 125 | — | ~581 | Automated safety check: Pass | MIT | today |
| 11 | 11.Soup Run or modify the uncond-init soup pipeline (make soup, scripts/soup/, configs/soup/soup.toml) — selection globs, uncond-init reuse and naming, env knobs, sigmalowres interaction, and constraints. | sorryhyun/ | 125 | — | ~728 | Automated safety check: Pass | MIT | today |
| 12 | 12.Gui Changes Recipes for common changes to the PySide6 GUI — adding a training field, variant, or language; changing job submission; composing a new job-submitting tab; and the action-button/theming rules. | sorryhyun/ | 125 | — | ~590 | Automated safety check: Pass | MIT | today |
Questions, answered from the data.
What is the best skill by sorryhyun?
Model Catalog from sorryhyun/anima_lora ranks first of the 12 skills by sorryhyun listed here, with the highest score: its repository has 125 GitHub stars, its SKILL.md loads about 502 tokens and it passes the automated safety check with no findings. Next come Qwen21 and Anime Tools.
Are sorryhyun's skills official?
None yet. All 12 skills by sorryhyun 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.