Agent skill

Sciagent Skill Creator

by jaechang-hits in jaechang-hits/SciAgent-Skills

Scaffold a new SciAgent-Skills entry. An agent skill from jaechang-hits/SciAgent-Skills.

Custom licenceAuto-check passedAgent Workflows

Install Sciagent Skill Creator

skills CLI
$ npx skills add jaechang-hits/SciAgent-Skills --skill sciagent-skill-creator -a claude-code

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

GitHub CLI
$ gh skill install jaechang-hits/SciAgent-Skills sciagent-skill-creator --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/jaechang-hits/SciAgent-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/sciagent-skill-creator .claude/skills/sciagent-skill-creator && 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/

Facts

Skill name
sciagent-skill-creator
GitHub stars
371
Token cost
~2.3k tokens
SKILL.md length
1,069 words
Files
3 (incl. scripts)
Skills in repo
169
Repo updated
First seen
Licence
Custom licence

At a glance

Scaffold a new SciAgent-Skills entry. An agent skill from jaechang-hits/SciAgent-Skills.

  • Works in 7 steps: Topic — concrete tool/library/concept… → Sub-type — pipeline | toolkit | database… → Category — primary category directory.… → …
  • User says (any language): add a SciAgent skill
  • SKILL.md covers When to invoke this skill, What you need to collect from…, Duplicate check before… and How to run the scaffolder, plus 5 more sections
  • Runs Python scripts from its folder; calls python

What it does

Sciagent Skill Creator is an agent skill from jaechang-hits/SciAgent-Skills. Scaffold a new SciAgent-Skills entry. Picks pipeline/toolkit/database/guide template, creates skills/{category}/{name}/SKILL.md with valid frontmatter, appends the registry.yaml entry, runs validation. Enforces name uniqueness, kebab-case, description keyword rules, schema rules from AGENTS.md. TRIGGER when user says (any language): "add a SciAgent skill", "add a skill for <X", "create new skill", "create a SKILL.md for <X", "scaffold a skill", "new skill entry", "register a skill", "신규 skill 추가", "스킬 만들어줘", "스킬…

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts (for example `scripts/scaffold.py` and `scripts/validate_description.py`).

It sits in Agent Workflows, covering Skill authoring, Agent instruction files and Project scaffolding. The repository describes itself as: 197 bioinformatics & life science skills for Claude Code and AI agents — BixBench 92.0% accuracy. RNA-seq, single-cell, drug discovery, proteomics, and more. Powers OmicsHorizon.

When your agent uses it

  • User says (any language): add a SciAgent skill
  • Add a skill for <X
  • Create new skill
  • Create a SKILL.md for <X

Example prompts

  • “add a SciAgent skill”
  • “add a skill for <X”
  • “create new skill”
  • “/sciagent-skill-creator”

Requirements

  • Python 3

Workflow steps

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

  1. Topic — concrete tool/library/concept name. Reject vague topics ("ML stuff") with a clarifying question.
  2. Sub-type — pipeline | toolkit | database | guide. Use the decision rule from AGENTS.md Step 1b. If unsure, ask the user.
  3. Category — primary category directory. List the table from AGENTS.md Step 2 if the user is unsure.
  4. Entry name — kebab-case slug. Convention: {tool-name}-{purpose} (e.g., pydeseq2-differential-expression). Confirm with the user.
  5. License — underlying tool's license. Default to CC-BY-4.0 for original prose-only content.
  6. Description — 1-2 sentences, max 1024 chars. Lead with tool/domain keyword in the first 120 chars. Anti-patterns are in AGENTS.md Step 5…
  7. Tags (optional) — only if the entry meaningfully spans multiple categories (e.g., literature DB stored under scientific-writing, tag with…

What it can do on your machine

Read from SKILL.md and the folder at commit 82c862c. 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 2 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    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

Sciagent Skill Creator loads about 2.3k tokens when it runs. Until then it costs about 229 tokens; SKILL.md has 1,069 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~229
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

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); the scripts in this folder are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,069 words (~2,292 tokens).

“Repo-local scaffolder for skills/ entries. Mechanizes the boilerplate from AGENTS.md Steps 1, 2, 4, 5, 6 so authoring effort stays on content (When to Use, Workflow, Recipes, References) and not on field plumbing.”

— opening of SKILL.md by jaechang-hits, Custom licence
name
sciagent-skill-creator

Read the full SKILL.md on GitHub

Files

SKILL.md and 2 other files (scripts) in .claude/skills/sciagent-skill-creator of jaechang-hits/SciAgent-Skills.

  • SKILL.md
  • scripts/scaffold.py
  • scripts/validate_description.py

Open the folder on GitHubat commit 82c862c

Compare with similar skills

Sciagent Skill Creator 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.

Sciagent Skill Creator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sciagent Skill Creator this skilljaechang-hits/SciAgent-Skills371—~2.3kAutomated safety check: PassCustom licence
Claude Code Plugin Structureanthropics/claude-plugins-official38k10 repos~3.4kAutomated safety check: PassApache-2.0
Harness Agent Team Designerrevfactory/harness9.1k—~4.5kAutomated safety check: PassApache-2.0
Harness Evolution Feedback Looprevfactory/harness9.1k—~855Automated safety check: PassApache-2.0
Skill Creatorccusage/ccusage19k—~1.1kAutomated safety check: PassCustom licence
Intent Layercrafter-station/skills1121 repos~633Automated safety check: PassMIT

Similar skills

  • Claude Code Plugin Structure

    anthropics/claude-plugins-official

    Official

    Explains the directory layout, plugin.json manifest and component organization of a Claude Code plugin, including auto-discovery and portable paths.

    38k GitHub starsUsed in 10 repos~3.4k tokens
    Agent WorkflowsAuto-check passed
  • Harness Agent Team Designer

    revfactory/harness

    Designs a project-specific agent harness: defines specialist agents, writes the skills they follow, picks an execution mode and model for each, and keeps the setup maintained.

    9.1k GitHub stars~4.5k tokensUpdated 11 days ago
    Agent WorkflowsAuto-check passed
  • Collects feedback on how an agent harness performed, generalizes it, and updates the harness agents, skills and orchestrator along with a change-history table.

    9.1k GitHub stars~855 tokensUpdated 11 days ago
    Agent WorkflowsAuto-check passed
  • Skill Creator

    ccusage/ccusage

    Guides repo-local skill creation and updates. An agent skill from ccusage/ccusage.

    19k GitHub stars~1.1k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Intent Layer

    crafter-station/skills

    Set up hierarchical Intent Layer (AGENTS.md files) for codebases.

    112 GitHub starsUsed in 1 repo~633 tokens
    Agent WorkflowsAuto-check passed
  • Skill Creator

    luongnv89/asm

    Create a skill or bring an existing one up to the same standard (validate + asm eval fix loop); run evals, tune triggering.

    954 GitHub stars~5.3k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

More from jaechang-hits/SciAgent-Skills

All 169 skills in this repo
  • Neb Irc Activation Energy

    jaechang-hits/SciAgent-Skills

    NEB-IRC activation energy pipeline for reaction barriers using GFN2-xTB and pysisyphus.

    371 GitHub stars~4k tokensUpdated 10 days ago
    Auto-check passed
  • Molecular Visualization 3dmol

    jaechang-hits/SciAgent-Skills

    3Dmol.js WebGL molecular visualization emitted as self-contained HTML.

    371 GitHub stars~3.2k tokensUpdated 10 days ago
    Auto-check passed
  • Cobrapy Metabolic Modeling

    jaechang-hits/SciAgent-Skills

    Constraint-based (COBRA) analysis of genome-scale metabolic models: FBA, FVA, knockouts, flux sampling, production envelopes, gapfilling, media optimization.

    371 GitHub starsUsed in 1 repo~4.9k tokens
    Auto-check passed
  • Rdkit Chemdraw Cdxml

    jaechang-hits/SciAgent-Skills

    Read, write, and edit ChemDraw CDX/CDXML files with RDKit's rdkit.Chem.rdChemDraw plus direct XML editing, always paired with a rendered PNG.

    371 GitHub stars~6.9k tokensUpdated 10 days ago
    Auto-check passed
  • Pubmed Database

    jaechang-hits/SciAgent-Skills

    Programmatic PubMed access via NCBI E-utilities REST API. An agent skill from jaechang-hits/SciAgent-Skills.

    371 GitHub starsUsed in 1 repo~4.4k tokens
    Auto-check passed
  • Shap Model Explainability

    jaechang-hits/SciAgent-Skills

    Model interpretability via SHAP (Shapley values from game theory).

    371 GitHub starsUsed in 1 repo~3.7k tokens
    Auto-check passed

Categories

Questions about Sciagent Skill Creator

What does Sciagent Skill Creator do?

Scaffold a new SciAgent-Skills entry. An agent skill from jaechang-hits/SciAgent-Skills. Sciagent Skill Creator is an agent skill from jaechang-hits/SciAgent-Skills. Scaffold a new SciAgent-Skills entry.

When should I use Sciagent Skill Creator?

Sciagent Skill Creator fits situations like: user says (any language): add a SciAgent skill; add a skill for <X; create new skill; create a SKILL.md for <X.

How do I install Sciagent Skill Creator in Claude Code?

Run `npx skills add jaechang-hits/SciAgent-Skills --skill sciagent-skill-creator -a claude-code`. Or copy the skill folder (.claude/skills/sciagent-skill-creator in jaechang-hits/SciAgent-Skills) into .claude/skills/sciagent-skill-creator in your project. Claude Code loads it when a task matches its description.

How do I install Sciagent Skill Creator in Codex?

Run `npx skills add jaechang-hits/SciAgent-Skills --skill sciagent-skill-creator -a codex`. Or copy the skill folder (.claude/skills/sciagent-skill-creator in jaechang-hits/SciAgent-Skills) into .agents/skills/sciagent-skill-creator in your project. Codex loads it when a task matches its description.

Can I use Sciagent Skill Creator 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 jaechang-hits/SciAgent-Skills --skill sciagent-skill-creator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sciagent-skill-creator, .gemini/skills/sciagent-skill-creator, .github/skills/sciagent-skill-creator and .opencode/skills/sciagent-skill-creator in your project.

What does Sciagent Skill Creator need to run?

Going by SKILL.md and its folder, Sciagent Skill Creator needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Sciagent Skill Creator 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 Sciagent Skill Creator 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Sciagent Skill Creator use?

Sciagent Skill Creator has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Sciagent Skill Creator use?

About 2.3k tokens (SKILL.md is roughly 9.2k 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 Sciagent Skill Creator?

Skills that share tags, products or a category with Sciagent Skill Creator: Claude Code Plugin Structure (anthropics/claude-plugins-official, 38k stars), Harness Agent Team Designer (revfactory/harness, 9.1k stars), Harness Evolution Feedback Loop (revfactory/harness, 9.1k stars) and Skill Creator (ccusage/ccusage, 19k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sciagent Skill Creator?

jaechang-hits (a GitHub user) maintains it in jaechang-hits/SciAgent-Skills, which has 371 GitHub stars. The repository holds 169 skills in this directory. The repository was last updated on September 29, 2026.

Source: jaechang-hits/SciAgent-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.