Agent skill

Protein Mutation Enhancement

by PKU-YuanGroup in PKU-YuanGroup/OpenAI4S

Deterministic protein gain-of-function mutation workflow: build single, double, and higher-order mutant libraries; merge ESM sequence-effect scores, structure metrics from ESMFold-class models…

MITAuto-check passed

Install Protein Mutation Enhancement

skills CLI

$ npx skills add PKU-YuanGroup/OpenAI4S --skill protein-mutation-enhancement -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install PKU-YuanGroup/OpenAI4S protein-mutation-enhancement --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/PKU-YuanGroup/OpenAI4S.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/protein-mutation-enhancement .claude/skills/protein-mutation-enhancement && rm -rf skills-src

Use ~/.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/

Paste into Claude Code

Install the "protein-mutation-enhancement" agent skill from https://github.com/PKU-YuanGroup/OpenAI4S/tree/main/skills/protein-mutation-enhancement into .claude/skills/protein-mutation-enhancement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "protein-mutation-enhancement", 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

$skill-installer install https://github.com/PKU-YuanGroup/OpenAI4S/tree/main/skills/protein-mutation-enhancement

Type 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.

skills CLI

$ npx skills add PKU-YuanGroup/OpenAI4S --skill protein-mutation-enhancement -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install PKU-YuanGroup/OpenAI4S protein-mutation-enhancement --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/PKU-YuanGroup/OpenAI4S.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/protein-mutation-enhancement .agents/skills/protein-mutation-enhancement && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "protein-mutation-enhancement" agent skill from https://github.com/PKU-YuanGroup/OpenAI4S/tree/main/skills/protein-mutation-enhancement into .agents/skills/protein-mutation-enhancement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "protein-mutation-enhancement", 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.

skills CLI

$ npx skills add PKU-YuanGroup/OpenAI4S --skill protein-mutation-enhancement -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install PKU-YuanGroup/OpenAI4S protein-mutation-enhancement --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/PKU-YuanGroup/OpenAI4S.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/protein-mutation-enhancement .cursor/skills/protein-mutation-enhancement && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "protein-mutation-enhancement" agent skill from https://github.com/PKU-YuanGroup/OpenAI4S/tree/main/skills/protein-mutation-enhancement into .cursor/skills/protein-mutation-enhancement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "protein-mutation-enhancement", 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

$ gemini skills install https://github.com/PKU-YuanGroup/OpenAI4S.git --path skills/protein-mutation-enhancement

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add PKU-YuanGroup/OpenAI4S --skill protein-mutation-enhancement -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install PKU-YuanGroup/OpenAI4S protein-mutation-enhancement --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/PKU-YuanGroup/OpenAI4S.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/protein-mutation-enhancement .gemini/skills/protein-mutation-enhancement && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "protein-mutation-enhancement" agent skill from https://github.com/PKU-YuanGroup/OpenAI4S/tree/main/skills/protein-mutation-enhancement into .gemini/skills/protein-mutation-enhancement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "protein-mutation-enhancement", 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.

GitHub CLI

$ gh skill install PKU-YuanGroup/OpenAI4S protein-mutation-enhancement

Installs 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).

skills CLI

$ npx skills add PKU-YuanGroup/OpenAI4S --skill protein-mutation-enhancement -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/PKU-YuanGroup/OpenAI4S.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/protein-mutation-enhancement .github/skills/protein-mutation-enhancement && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "protein-mutation-enhancement" agent skill from https://github.com/PKU-YuanGroup/OpenAI4S/tree/main/skills/protein-mutation-enhancement into .github/skills/protein-mutation-enhancement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "protein-mutation-enhancement", 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.

skills CLI

$ npx skills add PKU-YuanGroup/OpenAI4S --skill protein-mutation-enhancement -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install PKU-YuanGroup/OpenAI4S protein-mutation-enhancement --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/PKU-YuanGroup/OpenAI4S.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/protein-mutation-enhancement .opencode/skills/protein-mutation-enhancement && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "protein-mutation-enhancement" agent skill from https://github.com/PKU-YuanGroup/OpenAI4S/tree/main/skills/protein-mutation-enhancement into .opencode/skills/protein-mutation-enhancement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "protein-mutation-enhancement", 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: protein-mutation-enhancement
GitHub stars: 622
Token cost: ~1.5k tokens
SKILL.md length: 419 words
Files: 4
Skills in repo: 17
Repo updated: Oct 9, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Deterministic protein gain-of-function mutation workflow: build single, double, and higher-order mutant libraries; merge ESM sequence-effect scores, structure metrics from ESMFold-class models…

Works in 7 steps: Validate the wild-type protein sequence… → Build a deterministic mutant library → Score sequence effect with an ESM… → …
SKILL.md covers Workflow Contract, Import, Build a Mutation Library and Merge Scores and Rank, plus 3 more sections
Runs Python scripts from its folder

What it does

Protein Mutation Enhancement is an agent skill from PKU-YuanGroup/OpenAI4S. Deterministic protein gain-of-function mutation workflow: build single, double, and higher-order mutant libraries; merge ESM sequence-effect scores, structure metrics from ESMFold-class models, property/function scores; rank candidates; and decide whether to stop or start the next design round.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `README.md`, `README_zh.md` and `kernel.py`).

The repository describes itself as: Open-source AI agent for scientific research. Analyze data in Python/R with Claude, GPT, Gemini, and more. The licence is MIT.

Example prompts

“/protein-mutation-enhancement”

Requirements

Python 3

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

Validate the wild-type protein sequence and define mutable positions.
Build a deterministic mutant library
Score sequence effect with an ESM masked-LM model
Predict structures for promising mutants
Merge sequence, structure, property, and functional assay/proxy metrics.
Rank by weighted normalized score and apply acceptance thresholds.
If any candidate passes thresholds, call host.submit_output(...). If none

What it can do on your machine

Read from SKILL.md and the folder at commit 4a72e87. 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
Ships script files (Python), which the agent can run.
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

Protein Mutation Enhancement loads about 1.5k tokens when it runs. Until then it costs about 81 tokens; SKILL.md has 419 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~81
When it runs · the whole SKILL.md, loaded when a task matches: ~1.5k

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 PKU-YuanGroup/OpenAI4S at commit 4a72e87, republished under its MIT licence (© PKU-YuanGroup). 419 words, ~1,461 tokens.

Download SKILL.mdSave it as .claude/skills/protein-mutation-enhancement/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.

name: protein-mutation-enhancement
description: Deterministic protein gain-of-function mutation workflow: build single, double, and higher-order mutant libraries; merge ESM sequence-effect scores, structure metrics from ESMFold-class models, property/function scores; rank candidates; and decide whether to stop or start the next design round.
origin: openai4s
category: workflow
requirements: gpu

Protein Mutation Enhancement Workflow

Use this skill when the task is to improve a target protein by iterative mutation design. It is an orchestration layer: deterministic library construction, score merging, ranking, and loop-control run locally with stdlib-only helpers; heavyweight model calls run through existing model skills such as fair-esm2 and esmfold2.

Workflow Contract

Validate the wild-type protein sequence and define mutable positions.
Build a deterministic mutant library:
- round 1 usually uses single mutants over selected positions;
- later rounds expand top candidates to doubles or higher-order combinations;
- every variant has a stable ID such as A12V+G47D.
Score sequence effect with an ESM masked-LM model:
- retrieve fair-esm2 or esmfold2 for concrete GPU recipes;
- produce a table keyed by id, commonly with esm_delta where higher is better.
Predict structures for promising mutants:
- retrieve esmfold2 for ESMFold2 / ESMFold2-Fast recipes;
- produce structure metrics keyed by id, commonly plddt, ptm, pae, rmsd_to_wt, or task-specific interface metrics.
Merge sequence, structure, property, and functional assay/proxy metrics.
Rank by weighted normalized score and apply acceptance thresholds.
If any candidate passes thresholds, call host.submit_output(...). If none pass, use the top ranked variants to seed the next loop and expand the library.

Import

The directory name contains hyphens, so import via importlib:

python

import importlib

pm = importlib.import_module("protein-mutation-enhancement.kernel")

Build a Mutation Library

python

wt = "MKTAYIAKQRQISFVKSHFSRQ"

library = pm.enumerate_mutants(
    wt,
    positions=[3, 5, 8, 12],
    substitutions={3: ["A", "L", "F"], 5: ["V", "L"], 8: ["R", "K"]},
    max_order=2,
    limit=500,
)

pm.write_fasta(library, "round1_mutants.fasta")

positions are 1-indexed. If substitutions omits a position, all 20 natural amino acids except the wild-type residue are used. Candidate IDs are stable and sorted by position, so downstream score tables can safely join on id.

Show full SKILL.md (171 more words)Show less

Merge Scores and Rank

After running ESM and structure jobs, load or construct score tables keyed by variant ID:

python

esm_scores = {
    "T3L": {"esm_delta": 1.8},
    "Y5V": {"esm_delta": 0.3},
    "T3L+Y5V": {"esm_delta": 2.1},
}
structure_scores = {
    "T3L": {"plddt": 86.0, "rmsd_to_wt": 0.8},
    "Y5V": {"plddt": 71.0, "rmsd_to_wt": 2.4},
    "T3L+Y5V": {"plddt": 82.0, "rmsd_to_wt": 1.1},
}

round_result = pm.run_selection_round(
    library,
    score_tables=[esm_scores, structure_scores],
    weights={
        "esm_delta": 0.45,
        "plddt": 0.25,
        "rmsd_to_wt": 0.15,
        "property_score": 0.15,
    },
    directions={"rmsd_to_wt": "low"},
    acceptance_thresholds={
        "composite_score": 0.72,
        "esm_delta": 1.0,
        "plddt": 75.0,
    },
    top_k=20,
)

best = round_result["ranked"][0]
print(best["id"], best["composite_score"], round_result["should_continue"])

property_score is computed locally from conservative amino-acid-class, hydropathy, charge, and size-change heuristics unless an external table provides it. External assay or task-proxy metrics can be added as extra columns and weights.

Loop Pattern

python

current_library = pm.enumerate_mutants(wt, positions=active_positions, max_order=1)

for round_idx in range(1, 6):
    # 1. Score `current_library` using fair-esm2 / ESMC.
    # 2. Fold the promising subset using esmfold2 / ESMFold2-Fast.
    # 3. Merge the resulting tables.
    result = pm.run_selection_round(
        current_library,
        score_tables=[esm_scores, structure_scores, function_scores],
        weights=weights,
        directions=directions,
        acceptance_thresholds=thresholds,
        top_k=50,
    )
    if not result["should_continue"]:
        host.submit_output({"accepted": result["accepted"], "round": round_idx})
        break

    active_positions = pm.suggest_next_positions(result["ranked"], max_positions=10)
    current_library = pm.enumerate_mutants(
        wt,
        positions=active_positions,
        max_order=min(round_idx + 1, 4),
        seeds=result["next_round_seeds"],
        limit=2000,
    )
else:
    host.submit_output({"accepted": [], "ranked": result["ranked"][:20]})

Practical Defaults

Start with curated active-site, binding-site, stability, or conservation positions instead of all positions when possible.
Use max_order=1 for the first pass, then expand top single mutants into doubles/combinations with seeds=....
Keep the model jobs separate from ranking artifacts:
- mutants.fasta
- esm_scores.csv
- structure_scores.csv
- ranked_candidates.json
Prefer hard acceptance thresholds for safety-critical metrics such as minimum pLDDT or maximum RMSD, and use weighted composite score only after those gates pass.

Notes

This skill does not claim a mutation is biologically validated. It ranks candidates for follow-up validation using deterministic, inspectable rules.
Core helpers are pure stdlib and safe for the default offline test suite.
GPU model installation, weights, and remote execution remain in the model skills (fair-esm2, esmfold2) and compute skills.

Files

SKILL.md and 3 other files in skills/protein-mutation-enhancement of PKU-YuanGroup/OpenAI4S.

SKILL.md
README.md
README_zh.md
kernel.py

Open the folder on GitHubat commit 4a72e87

Compare with similar skills

Protein Mutation Enhancement 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.

Protein Mutation Enhancement compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Protein Mutation Enhancement this skillPKU-YuanGroup/OpenAI4S	622	—	~1.5k	Automated safety check: Pass	MIT	yesterday
Image Enhancernexu-io/open-design	100k	—	~332	Automated safety check: Pass	Apache-2.0	yesterday
Protein Sequence FunctionVectorSpaceLab/AREX-Skill	331	—	~921	Automated safety check: Pass	Custom licence	1 mo ago
Azure Functionsdavila7/claude-code-templates	33k	2 repos	~344	Automated safety check: Pass	MIT	yesterday
Frontend Query Mutationlangflow-ai/langflow	155k	—	~979	Automated safety check: Pass	MIT	yesterday
Neon Functionssickn33/agentic-awesome-skills	47k	1 repos	~8.6k	Automated safety check: Notes	Apache-2.0	2 days ago

Similar skills

Image Enhancer
nexu-io/open-design
Improve image and screenshot quality by enhancing resolution, sharpness, and clarity for professional presentations and documentation.
100k GitHub stars~332 tokensUpdated yesterday
Media & CreativeAuto-check passed
Protein Sequence Function
VectorSpaceLab/AREX-Skill
A skill your agent uses for PaddleHelix protein sequence pretraining, prediction, protein function workflows, tokenizer/model guidance, and safe protein input validation.
331 GitHub stars~921 tokensUpdated 1 mo ago
Research & ScienceAuto-check passed
Azure Functions
davila7/claude-code-templates
Expert patterns for Azure Functions development including isolated worker model, Durable Functions orchestration, cold start optimization, and production patterns.
33k GitHub starsUsed in 2 repos~344 tokens
Backend & APIsAuto-check passed
Frontend Query Mutation
langflow-ai/langflow
Guide for implementing Langflow frontend query and mutation patterns with Axios and TanStack React Query v5.
155k GitHub stars~979 tokensUpdated yesterday
Frontend & DesignAuto-check passed
Neon Functions
sickn33/agentic-awesome-skills
Long-running, serverless Node.js HTTP functions deployed onto your Neon branch, with DATABASEURL injected automatically and compute that runs next to your data.
47k GitHub starsUsed in 1 repo~8.6k tokens
Backend & APIsAuto-check: notes
Deterministic Design
sickn33/agentic-awesome-skills
Render the UI and prove it's balanced + usable: a deterministic layout audit (centroid / optical-center / pixel-oracle balance via explicit math + annotated screenshot) plus a vision-judged Nielsen…
47k GitHub starsUsed in 1 repo~736 tokens
Frontend & DesignAuto-check passed

More from PKU-YuanGroup/OpenAI4S

All 17 skills in this repo

Single Cell Rna Analysis
PKU-YuanGroup/OpenAI4S
Reproducible Scanpy workflow for human or mouse 10x scRNA-seq and snRNA-seq count matrices: single-sample descriptive QC, clustering and annotation, or comparative donor-aware pseudobulk DE and Milo…
622 GitHub stars~1.3k tokensUpdated yesterday
Auto-check passed
Bioprobench
PKU-YuanGroup/OpenAI4S
Score an LLM's biological-protocol reasoning on the BioProBench benchmark: protocol QA, step ordering, error detection, protocol generation, and LLM-judged error reasoning; or generate the responses.
622 GitHub stars~2.3k tokensUpdated yesterday
Auto-check passed
Reaction Atom Mapping
PKU-YuanGroup/OpenAI4S
Map atoms and changed bonds for a complete reaction with RXNMapper.
622 GitHub stars~1.2k tokensUpdated yesterday
Auto-check passed
Reaction Forward Prediction
PKU-YuanGroup/OpenAI4S
Predict ranked products from reactants and reagents with ReactionT5v2-forward; use for outcome prediction or round-trip recovery.
622 GitHub stars~2k tokensUpdated yesterday
Auto-check passed
Reaction Yield Estimation
PKU-YuanGroup/OpenAI4S
Estimate yield for a fully specified reactant/reagent/product record with ReactionT5v2-yield.
622 GitHub stars~2.3k tokensUpdated yesterday
Auto-check passed
Rfdiffusion
PKU-YuanGroup/OpenAI4S
Generate de novo protein backbones with RFdiffusion for protein-target binders, hotspot-conditioned interfaces, motif scaffolding, partial diffusion, or symmetric assemblies.
622 GitHub stars~2.2k tokensUpdated yesterday
Auto-check passed

Questions about Protein Mutation Enhancement

What does Protein Mutation Enhancement do?

Deterministic protein gain-of-function mutation workflow: build single, double, and higher-order mutant libraries; merge ESM sequence-effect scores, structure metrics from ESMFold-class models…. Protein Mutation Enhancement is an agent skill from PKU-YuanGroup/OpenAI4S. Deterministic protein gain-of-function mutation workflow: build single, double, and higher-order mutant libraries; merge ESM sequence-effect scores, structure metrics from ESMFold-class models, property/function scores; rank candidates; and decide whether to stop or start the next design round.

How do I install Protein Mutation Enhancement in Claude Code?

Run `npx skills add PKU-YuanGroup/OpenAI4S --skill protein-mutation-enhancement -a claude-code`. Or copy the skill folder (skills/protein-mutation-enhancement in PKU-YuanGroup/OpenAI4S) into .claude/skills/protein-mutation-enhancement in your project. Claude Code loads it when a task matches its description.

How do I install Protein Mutation Enhancement in Codex?

Run `npx skills add PKU-YuanGroup/OpenAI4S --skill protein-mutation-enhancement -a codex`. Or copy the skill folder (skills/protein-mutation-enhancement in PKU-YuanGroup/OpenAI4S) into .agents/skills/protein-mutation-enhancement in your project. Codex loads it when a task matches its description.

Can I use Protein Mutation Enhancement 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 PKU-YuanGroup/OpenAI4S --skill protein-mutation-enhancement -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/protein-mutation-enhancement, .gemini/skills/protein-mutation-enhancement, .github/skills/protein-mutation-enhancement and .opencode/skills/protein-mutation-enhancement in your project.

What does Protein Mutation Enhancement need to run?

Going by SKILL.md and its folder, Protein Mutation Enhancement needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Protein Mutation Enhancement 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 Protein Mutation Enhancement 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 Protein Mutation Enhancement use?

Protein Mutation Enhancement 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 Protein Mutation Enhancement use?

About 1.5k tokens (SKILL.md is roughly 5.8k 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 Protein Mutation Enhancement?

Skills that share tags, products or a category with Protein Mutation Enhancement: Image Enhancer (nexu-io/open-design, 100k stars), Protein Sequence Function (VectorSpaceLab/AREX-Skill, 331 stars), Azure Functions (davila7/claude-code-templates, 33k stars) and Frontend Query Mutation (langflow-ai/langflow, 155k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Protein Mutation Enhancement?

PKU-YuanGroup (a GitHub organization) maintains it in PKU-YuanGroup/OpenAI4S, which has 622 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 9, 2026.

Source: PKU-YuanGroup/OpenAI4S on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Protein Mutation Enhancement

Facts

At a glance

What it does

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Protein Mutation Enhancement Workflow

Workflow Contract

Import

Build a Mutation Library

Merge Scores and Rank

Loop Pattern

Practical Defaults

Notes

Files

Compare with similar skills

Similar skills

More from PKU-YuanGroup/OpenAI4S

Questions about Protein Mutation Enhancement