Esmfold2
JimLiu/science-skills
Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al.
Use FP16/BF16 mixed precision to accelerate training and reduce memory.
Install Mixed Precision
$ npx skills add aiming-lab/AutoResearchClaw --skill mixed-precision -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install aiming-lab/AutoResearchClaw mixed-precision --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/aiming-lab/AutoResearchClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/researchclaw/skills/builtin/tooling/mixed-precision .claude/skills/mixed-precision && 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 "mixed-precision" agent skill from https://github.com/aiming-lab/AutoResearchClaw/tree/main/researchclaw/skills/builtin/tooling/mixed-precision into .claude/skills/mixed-precision/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mixed-precision", 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/aiming-lab/AutoResearchClaw/tree/main/researchclaw/skills/builtin/tooling/mixed-precisionType 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 aiming-lab/AutoResearchClaw --skill mixed-precision -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install aiming-lab/AutoResearchClaw mixed-precision --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aiming-lab/AutoResearchClaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/researchclaw/skills/builtin/tooling/mixed-precision .agents/skills/mixed-precision && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "mixed-precision" agent skill from https://github.com/aiming-lab/AutoResearchClaw/tree/main/researchclaw/skills/builtin/tooling/mixed-precision into .agents/skills/mixed-precision/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mixed-precision", 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 aiming-lab/AutoResearchClaw --skill mixed-precision -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install aiming-lab/AutoResearchClaw mixed-precision --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aiming-lab/AutoResearchClaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/researchclaw/skills/builtin/tooling/mixed-precision .cursor/skills/mixed-precision && 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 "mixed-precision" agent skill from https://github.com/aiming-lab/AutoResearchClaw/tree/main/researchclaw/skills/builtin/tooling/mixed-precision into .cursor/skills/mixed-precision/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mixed-precision", 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/aiming-lab/AutoResearchClaw.git --path researchclaw/skills/builtin/tooling/mixed-precision--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 aiming-lab/AutoResearchClaw --skill mixed-precision -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install aiming-lab/AutoResearchClaw mixed-precision --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aiming-lab/AutoResearchClaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/researchclaw/skills/builtin/tooling/mixed-precision .gemini/skills/mixed-precision && 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 "mixed-precision" agent skill from https://github.com/aiming-lab/AutoResearchClaw/tree/main/researchclaw/skills/builtin/tooling/mixed-precision into .gemini/skills/mixed-precision/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mixed-precision", 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 aiming-lab/AutoResearchClaw mixed-precisionInstalls 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 aiming-lab/AutoResearchClaw --skill mixed-precision -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/aiming-lab/AutoResearchClaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/researchclaw/skills/builtin/tooling/mixed-precision .github/skills/mixed-precision && 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 "mixed-precision" agent skill from https://github.com/aiming-lab/AutoResearchClaw/tree/main/researchclaw/skills/builtin/tooling/mixed-precision into .github/skills/mixed-precision/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mixed-precision", 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 aiming-lab/AutoResearchClaw --skill mixed-precision -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install aiming-lab/AutoResearchClaw mixed-precision --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aiming-lab/AutoResearchClaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/researchclaw/skills/builtin/tooling/mixed-precision .opencode/skills/mixed-precision && 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 "mixed-precision" agent skill from https://github.com/aiming-lab/AutoResearchClaw/tree/main/researchclaw/skills/builtin/tooling/mixed-precision into .opencode/skills/mixed-precision/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mixed-precision", 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
mixed-precision- GitHub stars
- 15k
- Token cost
- ~275 tokens
- SKILL.md length
- 52 words
- Files
- 1
- Skills in repo
- 34
- Repo updated
- First seen
- Licence
- MIT
At a glance
Use FP16/BF16 mixed precision to accelerate training and reduce memory.
- Optimizing GPU performance
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Mixed Precision is an agent skill from aiming-lab/AutoResearchClaw. Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.
Its SKILL.md is about 280 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 AI & LLM Engineering. It works with CUDA. The repository describes itself as: Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞. The licence is MIT.
When your agent uses it
- Optimizing GPU performance
Example prompts
- “/mixed-precision”
What it can do on your machine
Read from SKILL.md and the folder at commit be4ba47. 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
Mixed Precision loads about 275 tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 52 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 aiming-lab/AutoResearchClaw at commit be4ba47, republished under its MIT licence (© aiming-lab). 52 words, ~275 tokens.
Download SKILL.mdSave it as
.claude/skills/mixed-precision/SKILL.md (or your agent's skills folder).- name
- mixed-precision
- description
- Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.
- metadata.category
- tooling
- metadata.trigger-keywords
- training,gpu,memory,speed,precision,fp16,bf16
- metadata.applicable-stages
- 10,12
- metadata.priority
- 5
- metadata.version
- 1.0
- metadata.author
- researchclaw
- metadata.references
- Micikevicius et al., Mixed Precision Training, ICLR 2018
- metadata.code-template
- scaler = torch.cuda.amp.GradScaler() for batch in dataloader: optimizer.zero_grad() with torch.cuda.amp.autocast(): output = model(batch) loss =…
Mixed Precision Training Best Practice
Use torch.cuda.amp for automatic mixed precision:
- Wrap forward pass in torch.cuda.amp.autocast()
- Use GradScaler for loss scaling
- BF16 preferred over FP16 on Ampere+ GPUs (RTX 3xxx, A100, RTX 4xxx)
- Watch for NaN gradients — reduce learning rate if needed
- Do NOT use amp with custom CUDA kernels unless tested
© aiming-lab, 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 researchclaw/skills/builtin/tooling/mixed-precision of aiming-lab/AutoResearchClaw.
Open the folder on GitHubat commit be4ba47
Compare with similar skills
Mixed Precision 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 |
|---|---|---|---|---|---|---|
| Mixed Precision this skillaiming-lab/AutoResearchClaw | 15k | — | ~275 | Automated safety check: Pass | MIT | |
| Esmfold2JimLiu/science-skills | 227 | 4 repos | ~2.5k | Automated safety check: Pass | Apache-2.0 | |
| MUSA GPU Training Optimizeropen-infra-skills/infra-skills | 141 | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| Benchmark TuneMesh-LLM/mesh-llm | 3.5k | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Cuda Kernel OptimizerKernelFlow-ops/cuda-optimized-skill | 212 | — | ~4.3k | Automated safety check: Pass | MIT | |
| DGX Spark Training Gotchaswshobson/agents | 40k | 1 repos | ~2k | Automated safety check: Pass | MIT |
Similar skills
MUSA GPU Training Optimizer
open-infra-skills/infra-skills
Profiles, benchmarks and tunes AI training workloads on Moore Threads MUSA GPUs with a measurement-first process that keeps model behavior unchanged.
Benchmark Tune
Mesh-LLM/mesh-llm
A skill your agent uses when running, debugging, interpreting, or documenting mesh-llm benchmark tune model-serving throughput trials, including choosing…
Cuda Kernel Optimizer
KernelFlow-ops/cuda-optimized-skill
Iteratively optimize a CUDA/CUTLASS/Triton kernel only when strict on-device compilation, correctness, timing, and NCU evidence gates pass.
DGX Spark Training Gotchas
wshobson/agents
Preflight checks and diagnosis for ten known failure modes of ML training on NVIDIA DGX Spark's GB10, spanning launch errors, memory, thermals, bandwidth and precision.
Areno Develop Kernel
inclusionAI/AReno
Develop, optimize, debug, and validate an AReno CUDA, Triton, fused, attention, convolution, routing, or MoE operator.
More from aiming-lab/AutoResearchClaw
All 34 skills in this repoA-Evolve Agent Improvement
aiming-lab/AutoResearchClaw
Diagnoses where an agent failed across runs and turns the findings into new skills, system prompt patches and knowledge entries, using the A-Evolve loop.
Metabolic Study Planner
aiming-lab/AutoResearchClaw
Turns a broad metabolic modelling topic into a concrete, paper-shaped plan with organism, model, perturbations, metrics and figures before any FBA code is written.
MFA Pipeline Orchestrator
aiming-lab/AutoResearchClaw
Runs a metabolic flux analysis from model loading to phenotype prediction and figures by handing work to four sub-agents in sequence.
Qiskit 2.x Quantum ML Reference
aiming-lab/AutoResearchClaw
Reference patterns for writing qiskit 2.x code for variational quantum machine learning: feature maps, VQC training, VQE for chemistry, MPS circuits and noise models.
Genome-Scale Metabolic Model Builder
aiming-lab/AutoResearchClaw
Builds or loads a genome-scale metabolic model in COBRApy, sets its growth medium and objective, and exports it as a validated JSON file for flux analysis.
Biopython Bioinformatics
aiming-lab/AutoResearchClaw
Quick reference for Biopython work: sequence operations, SeqIO file parsing, BLAST searches, Entrez queries, phylogenetic trees and PDB structure analysis.
Related
Works with
Categories
Questions about Mixed Precision
What does Mixed Precision do?
Use FP16/BF16 mixed precision to accelerate training and reduce memory. Mixed Precision is an agent skill from aiming-lab/AutoResearchClaw. Use FP16/BF16 mixed precision to accelerate training and reduce memory.
When should I use Mixed Precision?
Mixed Precision fits situations like: optimizing GPU performance.
How do I install Mixed Precision in Claude Code?
Run `npx skills add aiming-lab/AutoResearchClaw --skill mixed-precision -a claude-code`. Or copy the skill folder (researchclaw/skills/builtin/tooling/mixed-precision in aiming-lab/AutoResearchClaw) into .claude/skills/mixed-precision in your project. Claude Code loads it when a task matches its description.
How do I install Mixed Precision in Codex?
Run `npx skills add aiming-lab/AutoResearchClaw --skill mixed-precision -a codex`. Or copy the skill folder (researchclaw/skills/builtin/tooling/mixed-precision in aiming-lab/AutoResearchClaw) into .agents/skills/mixed-precision in your project. Codex loads it when a task matches its description.
Can I use Mixed Precision 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 aiming-lab/AutoResearchClaw --skill mixed-precision -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mixed-precision, .gemini/skills/mixed-precision, .github/skills/mixed-precision and .opencode/skills/mixed-precision in your project.
What does Mixed Precision need to run?
SKILL.md names no scripts, command-line tools or credentials: Mixed Precision is instructions for the agent only.
Does Mixed Precision 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 Mixed Precision 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 Mixed Precision use?
Mixed Precision 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 Mixed Precision use?
About 275 tokens (SKILL.md is roughly 1.1k 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 Mixed Precision?
Skills that share tags, products or a category with Mixed Precision: Esmfold2 (JimLiu/science-skills, 227 stars), MUSA GPU Training Optimizer (open-infra-skills/infra-skills, 141 stars), Benchmark Tune (Mesh-LLM/mesh-llm, 3.5k stars) and Cuda Kernel Optimizer (KernelFlow-ops/cuda-optimized-skill, 212 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Mixed Precision?
aiming-lab (a GitHub organization) maintains it in aiming-lab/AutoResearchClaw, which has 14,595 GitHub stars. The repository holds 34 skills in this directory. The repository was last updated on August 19, 2026.
Source: aiming-lab/AutoResearchClaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.