LLM Torch Profiler Analysis
sgl-project/sglang
Unified LLM torch-profiler triage skill for sglang, vllm, TensorRT-LLM, and TokenSpeed.
σ-demoted training (--sigmalowres) — routing rules and their validation, span schedules, the shipped combolate recipe vs combo, and the sibling-latent precache requirement.
Install Sigma Lowres
$ npx skills add sorryhyun/anima_lora --skill sigma-lowres -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install sorryhyun/anima_lora sigma-lowres --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/sorryhyun/anima_lora.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/sigma-lowres .claude/skills/sigma-lowres && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "sigma-lowres" agent skill from https://github.com/sorryhyun/anima_lora/tree/main/.claude/skills/sigma-lowres into .claude/skills/sigma-lowres/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sigma-lowres", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/sorryhyun/anima_lora/tree/main/.claude/skills/sigma-lowresType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add sorryhyun/anima_lora --skill sigma-lowres -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install sorryhyun/anima_lora sigma-lowres --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sorryhyun/anima_lora.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/sigma-lowres .agents/skills/sigma-lowres && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "sigma-lowres" agent skill from https://github.com/sorryhyun/anima_lora/tree/main/.claude/skills/sigma-lowres into .agents/skills/sigma-lowres/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sigma-lowres", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add sorryhyun/anima_lora --skill sigma-lowres -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install sorryhyun/anima_lora sigma-lowres --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sorryhyun/anima_lora.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/sigma-lowres .cursor/skills/sigma-lowres && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "sigma-lowres" agent skill from https://github.com/sorryhyun/anima_lora/tree/main/.claude/skills/sigma-lowres into .cursor/skills/sigma-lowres/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sigma-lowres", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/sorryhyun/anima_lora.git --path .claude/skills/sigma-lowres--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add sorryhyun/anima_lora --skill sigma-lowres -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install sorryhyun/anima_lora sigma-lowres --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sorryhyun/anima_lora.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/sigma-lowres .gemini/skills/sigma-lowres && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "sigma-lowres" agent skill from https://github.com/sorryhyun/anima_lora/tree/main/.claude/skills/sigma-lowres into .gemini/skills/sigma-lowres/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sigma-lowres", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install sorryhyun/anima_lora sigma-lowresInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add sorryhyun/anima_lora --skill sigma-lowres -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/sorryhyun/anima_lora.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/sigma-lowres .github/skills/sigma-lowres && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "sigma-lowres" agent skill from https://github.com/sorryhyun/anima_lora/tree/main/.claude/skills/sigma-lowres into .github/skills/sigma-lowres/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sigma-lowres", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add sorryhyun/anima_lora --skill sigma-lowres -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install sorryhyun/anima_lora sigma-lowres --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sorryhyun/anima_lora.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/sigma-lowres .opencode/skills/sigma-lowres && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "sigma-lowres" agent skill from https://github.com/sorryhyun/anima_lora/tree/main/.claude/skills/sigma-lowres into .opencode/skills/sigma-lowres/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sigma-lowres", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
sigma-lowres- GitHub stars
- 125
- Token cost
- ~581 tokens
- SKILL.md length
- 259 words
- Files
- 1
- Skills in repo
- 12
- Repo updated
- First seen
- Licence
- MIT
At a glance
σ-demoted training (--sigmalowres) — routing rules and their validation, span schedules, the shipped combolate recipe vs combo, and the sibling-latent precache requirement.
- Development work in your project
- SKILL.md covers Routing rules, Spans and Requirements & interactions
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Sigma Lowres is an agent skill from sorryhyun/anima_lora. σ-demoted training (--sigmalowres) — routing rules and their validation, span schedules, the shipped combolate recipe vs combo, and the sibling-latent precache requirement. Load before enabling, tuning, or debugging sigmalowres flags or configs/preprocess.toml's sigmademote.
Its SKILL.md is about 580 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development. The repository describes itself as: optimized anima lora training script. The licence is MIT.
When your agent uses it
- Development work in your project
Example prompts
- “/sigma-lowres”
What it can do on your machine
Read from SKILL.md and the folder at commit d16b651. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Sigma Lowres loads about 581 tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 259 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from sorryhyun/anima_lora at commit d16b651, republished under its MIT licence (© sorryhyun). 259 words, ~581 tokens.
Download SKILL.mdSave it as
.claude/skills/sigma-lowres/SKILL.md (or your agent's skills folder).- name
- sigma-lowres
- description
- σ-demoted training (--sigma_lowres) — routing rules and their validation, span schedules, the shipped combolate recipe vs combo, and the sibling-latent precache requirement. Load before enabling, tuning, or debugging sigma_lowres flags or configs/preprocess.toml's sigma_demote.
σ-demoted training (--sigma_lowres)
Opt-in: routes each train step's latent grid by noise level — high-σ steps train on a
lower-res sibling latent of the same image. Full contract + measured arm table:
docs/optimizations/sigma_lowres.md.
Routing rules
Certified per-step routes: 1024→896 on σ>0.5 (half-line), 1024→768 on the σ∈(0.65,0.95) window — non-nesting, hence the stacked router.
--sigma_lowres_route2 takes priority over the primary rule and therefore
requires an explicit σ window (_threshold2 + _threshold2_max): an unbounded rule 2
shadows rule 1 everywhere and silently disables yarnsig. That, and malformed
spans/routes, are setup-time errors — the surface validates before the model loads.
--sigma_lowres_yarnsig rides along by default and applies to the primary rule only
(off to drop it).
Spans
--sigma_lowres_span early|late|spread[:FRAC] gates by training progress (bias placed
during subspace selection is amplified). _span2 is the same for rule 2.
- combolate — the shipped recipe, what
configs/base.tomlsets: the stacked router withlate:0.75spans on both rules. ~−14% wall, ΔW ~0.75 (endpoint weights close to native). - combo — both spans cleared (
sigma_lowres_span = ""/_span2 = ""): the unscheduled arm E16 measured best at render level (−18%, inside the seed lottery on both corpora) but far from native in weight space (ΔW ~0.37).
Requirements & interactions
- Needs sibling latents precached:
sigma_demote = "1024:896,1024:768"inconfigs/preprocess.tomlchains one emit per route onto every VAE pass;make preprocess-demoteemits them. Siblings are keys inside the native VAE npz (demoted_{H}x{W}, one per route, outside the latents namespace) — not separate files. - Validation stays native; output is an ordinary LoRA.
- In the soup pipeline,
--sigma_lowres*is a whole-pipeline knob replayed onto the uncond run and folded into its name — see thesoupskill.
© sorryhyun, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .claude/skills/sigma-lowres of sorryhyun/anima_lora.
Open the folder on GitHubat commit d16b651
Compare with similar skills
Sigma Lowres next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Sigma Lowres this skillsorryhyun/anima_lora | 125 | — | ~581 | Automated safety check: Pass | MIT | |
| LLM Torch Profiler Analysissgl-project/sglang | 37k | 2 repos | ~6.4k | Automated safety check: Pass | Apache-2.0 | |
| Aoti Debugpytorch/pytorch | 104k | 1 repos | ~1.7k | Automated safety check: Pass | Custom licence | |
| Get API Docs with chubandrewyng/context-hub | 14k | 1 repos | ~775 | Automated safety check: Pass | MIT | |
| Debug Distributed Hangsgl-project/sglang | 37k | 2 repos | ~2.4k | Automated safety check: Pass | Apache-2.0 | |
| Adk Sample Creatorgoogle/adk-python | 22k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Aoti Debug
pytorch/pytorch
Debug AOTInductor (AOTI) errors and crashes. An agent skill from pytorch/pytorch.
Get API Docs with chub
andrewyng/context-hub
Fetches current documentation for third-party APIs and SDKs with the chub CLI before the agent writes code against them, instead of relying on remembered API shapes.
Debug Distributed Hang
sgl-project/sglang
Debug hanging issues in SGLang distributed inference (TP/PP/DP/EP).
- Official
Adk Sample Creator
google/adk-python
Creates a new sample agent in the ADK Python repository — the sample directory, its agent.py, and its README.md — following the conventions the existing samples already use.
- Official
CUTLASS FMHA Incremental Rebuild
microsoft/onnxruntime
Explains why editing CUTLASS fused-MHA headers in ONNX Runtime can leave stale CUDA kernels after an incremental build, and how to force and verify a real rebuild.
More from sorryhyun/anima_lora
All 12 skills in this repoModel Catalog
sorryhyun/anima_lora
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…
Qwen21
sorryhyun/anima_lora
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…
Anime Tools
sorryhyun/anima_lora
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…
Bucketing
sorryhyun/anima_lora
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.
Captions
sorryhyun/anima_lora
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.
Custom Nodes
sorryhyun/anima_lora
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.
Related
Categories
Questions about Sigma Lowres
What does Sigma Lowres do?
σ-demoted training (--sigmalowres) — routing rules and their validation, span schedules, the shipped combolate recipe vs combo, and the sibling-latent precache requirement. Sigma Lowres is an agent skill from sorryhyun/anima_lora. σ-demoted training (--sigmalowres) — routing rules and their validation, span schedules, the shipped combolate recipe vs combo, and the sibling-latent precache requirement.
When should I use Sigma Lowres?
Sigma Lowres fits situations like: development work in your project.
How do I install Sigma Lowres in Claude Code?
Run `npx skills add sorryhyun/anima_lora --skill sigma-lowres -a claude-code`. Or copy the skill folder (.claude/skills/sigma-lowres in sorryhyun/anima_lora) into .claude/skills/sigma-lowres in your project. Claude Code loads it when a task matches its description.
How do I install Sigma Lowres in Codex?
Run `npx skills add sorryhyun/anima_lora --skill sigma-lowres -a codex`. Or copy the skill folder (.claude/skills/sigma-lowres in sorryhyun/anima_lora) into .agents/skills/sigma-lowres in your project. Codex loads it when a task matches its description.
Can I use Sigma Lowres in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add sorryhyun/anima_lora --skill sigma-lowres -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sigma-lowres, .gemini/skills/sigma-lowres, .github/skills/sigma-lowres and .opencode/skills/sigma-lowres in your project.
What does Sigma Lowres need to run?
SKILL.md names no scripts, command-line tools or credentials: Sigma Lowres is instructions for the agent only.
Does Sigma Lowres access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Sigma Lowres safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Sigma Lowres use?
Sigma Lowres is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Sigma Lowres use?
About 581 tokens (SKILL.md is roughly 2.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Sigma Lowres?
Skills that share tags, products or a category with Sigma Lowres: LLM Torch Profiler Analysis (sgl-project/sglang, 37k stars), Aoti Debug (pytorch/pytorch, 104k stars), Get API Docs with chub (andrewyng/context-hub, 14k stars) and Debug Distributed Hang (sgl-project/sglang, 37k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Sigma Lowres?
sorryhyun (a GitHub user) maintains it in sorryhyun/anima_lora, which has 125 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 10, 2026.
Source: sorryhyun/anima_lora on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.