Agent skill

Project Initializer

by Drchronx in Drchronx/ai-agent-research-starter-kit

Initialize a structured academic research project workspace.

Custom licenceAuto-check passedData & Analytics

Install Project Initializer

skills CLI
$ npx skills add Drchronx/ai-agent-research-starter-kit --skill project-initializer -a claude-code

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

GitHub CLI
$ gh skill install Drchronx/ai-agent-research-starter-kit project-initializer --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/Drchronx/ai-agent-research-starter-kit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/'本地Skills功能分类库/16_科研项目管理与版本控制Skills/project-initializer' .claude/skills/project-initializer && 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
project-initializer
GitHub stars
134
Token cost
~406 tokens
SKILL.md length
151 words
Files
3 (incl. scripts)
Skills in repo
53
Repo updated
First seen
Licence
Custom licence

At a glance

Initialize a structured academic research project workspace.

  • Works in 5 steps: Create or propose a stable project… → Generate AGENTS.md with project-specific… → Generate… → …
  • Creating doctoral project folders
  • SKILL.md covers Inputs, Workflow, Hard Constraints and Script, plus 1 more section
  • Runs Python scripts from its folder

What it does

Project Initializer is an agent skill from Drchronx/ai-agent-research-starter-kit. Initialize a structured academic research project workspace. Use for creating doctoral project folders, AGENTS.md, project dashboard, literature/data/analysis/manuscript/submission/log directories, research project templates, and reproducible project scaffolds for papers, experiments, EEG/BCI projects, or dissertations.

Its SKILL.md is about 410 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `agents/openai.yaml` and `scripts/create_project_skeleton.py`).

It sits in Data & Analytics, covering Project scaffolding, Essays and academic help and Data analysis. The repository describes itself as: AI Agent 科研全流程教学包,能教学生从零部署 Codex、Claude Code、OpenClaw、Hermes 等 Agent,学会使用 Skills、飞书、AMiner、AI4Scholar、Zotero、Obsidian…

When your agent uses it

  • Creating doctoral project folders
  • Project dashboard
  • Literature/data/analysis/manuscript/submission/log directories
  • Research project templates

Example prompts

  • “/project-initializer”

Requirements

  • Python 3

Workflow steps

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

  1. Create or propose a stable project folder structure.
  2. Generate AGENTS.md with project-specific rules.
  3. Generate 00_project_dashboard/project_status.md.
  4. Generate starter files for weekly plan, research log, data lineage, manuscript versions, and submission tracker.
  5. Explain where raw data, processed data, literature, scripts, outputs, and manuscript files should go.

What it can do on your machine

Read from SKILL.md and the folder at commit aab1133. 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 1 file in scripts/ (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

Project Initializer loads about 406 tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 151 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~85
When it runs · the whole SKILL.md, loaded when a task matches
~406

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 151 words (~406 tokens).

“Use this skill when starting a new research project or converting a messy folder into a structured workspace.”

— opening of SKILL.md by Drchronx, Custom licence
name
project-initializer

Read the full SKILL.md on GitHub

Files

SKILL.md and 2 other files (scripts) in 本地Skills功能分类库/16_科研项目管理与版本控制Skills/project-initializer of Drchronx/ai-agent-research-starter-kit.

  • SKILL.md
  • agents/openai.yaml
  • scripts/create_project_skeleton.py

Open the folder on GitHubat commit aab1133

Compare with similar skills

Project Initializer 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.

Project Initializer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Project Initializer this skillDrchronx/ai-agent-research-starter-kit134—~406Automated safety check: PassCustom licence
Setup Workspaceprobabl-ai/skills135—~1.5kAutomated safety check: PassBSD-3-Clause
Exploratory Data AnalysisOleafly/Oleafly2052 repos~3.4kAutomated safety check: NotesMIT
Add Remote Endpointnextcloud/android-library106—~1.1kAutomated safety check: PassCustom licence
dotclaude Project Setupposhan0126/dotclaude871—~3.6kAutomated safety check: PassMIT
Dx Harnesspproenca/dot-skills214—~1.5kAutomated safety check: PassMIT

Similar skills

  • Setup Workspace

    probabl-ai/skills

    Detect an existing ML workspace or scaffold a fresh one via python -m skoreskills scaffold --package <pkg.

    135 GitHub stars~1.5k tokensUpdated yesterday
    Data & AnalyticsAuto-check passed
  • Perform bounded, local exploratory analysis of explicitly supported scientific files.

    205 GitHub starsUsed in 2 repos~3.4k tokens
    Data & AnalyticsAuto-check: notes
  • Add Remote Endpoint

    nextcloud/android-library

    A skill your agent uses when adding a new remote/network endpoint (a RemoteOperation / OCSRemoteOperation) to this Nextcloud Android library, or when the user says "add an endpoint", "new remote…

    106 GitHub stars~1.1k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • dotclaude Project Setup

    poshan0126/dotclaude

    Scans a codebase, interviews you, and installs only the justified Claude Code rules, hooks, agents and skills, tailored to the project's stack.

    871 GitHub stars~3.6k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • Dx Harness

    pproenca/dot-skills

    Developer-experience friction auditing and fixing — slow onboarding, repeated manual setup steps, missing bootstrap/reset/seed scripts, undiscoverable conventions.

    214 GitHub stars~1.5k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Authoring

    OdradekAI/bundles-forge

    A skill your agent uses when writing, completing, improving, or adapting SKILL.md and agents/.md in a bundle-plugin — integrating external skills, filling scaffolded stubs, or rewriting for better…

    229 GitHub stars~3k tokensUpdated 5 mo ago
    Agent WorkflowsAuto-check passed

More from Drchronx/ai-agent-research-starter-kit

All 53 skills in this repo
  • Literature Reviewer Skill

    Drchronx/ai-agent-research-starter-kit

    Build high-quality literature reviews from a research topic using a 10-phase workflow.

    134 GitHub stars~2.5k tokensUpdated 4 mo ago
    Auto-check passed
  • Scenario Experiment Analysis

    Drchronx/ai-agent-research-starter-kit

    Analyze scenario/vignette experiment datasets for behavioral research.

    134 GitHub stars~1.1k tokensUpdated 4 mo ago
    Auto-check passed
  • Scenario Experiment Benchmark Mining

    Drchronx/ai-agent-research-starter-kit

    Mine and synthesize real top-journal scenario/vignette experiment patterns for behavioral research.

    134 GitHub stars~1.1k tokensUpdated 4 mo ago
    Auto-check passed
  • Web Browsing

    Drchronx/ai-agent-research-starter-kit

    Browse and summarize websites, extract content from URLs, search the web for information.

    134 GitHub stars~593 tokensUpdated 4 mo ago
    Auto-check passed
  • Multi Source Data Integration Extraction

    Drchronx/ai-agent-research-starter-kit

    Automatically merge scattered Excel and CSV files, normalize column names, and extract structured tables from PDF, HTML, TXT, or Markdown documents.

    134 GitHub stars~671 tokensUpdated 4 mo ago
    Auto-check passed
  • Scientific Slides

    Drchronx/ai-agent-research-starter-kit

    Build slide decks and presentations for research talks using Nano Banana Pro AI.

    134 GitHub stars~9.8k tokensUpdated 4 mo ago
    Auto-check: notes

Questions about Project Initializer

What does Project Initializer do?

Initialize a structured academic research project workspace. Project Initializer is an agent skill from Drchronx/ai-agent-research-starter-kit. Initialize a structured academic research project workspace.

When should I use Project Initializer?

Project Initializer fits situations like: creating doctoral project folders; project dashboard; literature/data/analysis/manuscript/submission/log directories; research project templates.

How do I install Project Initializer in Claude Code?

Run `npx skills add Drchronx/ai-agent-research-starter-kit --skill project-initializer -a claude-code`. Or copy the skill folder (本地Skills功能分类库/16_科研项目管理与版本控制Skills/project-initializer in Drchronx/ai-agent-research-starter-kit) into .claude/skills/project-initializer in your project. Claude Code loads it when a task matches its description.

How do I install Project Initializer in Codex?

Run `npx skills add Drchronx/ai-agent-research-starter-kit --skill project-initializer -a codex`. Or copy the skill folder (本地Skills功能分类库/16_科研项目管理与版本控制Skills/project-initializer in Drchronx/ai-agent-research-starter-kit) into .agents/skills/project-initializer in your project. Codex loads it when a task matches its description.

Can I use Project Initializer 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 Drchronx/ai-agent-research-starter-kit --skill project-initializer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/project-initializer, .gemini/skills/project-initializer, .github/skills/project-initializer and .opencode/skills/project-initializer in your project.

What does Project Initializer need to run?

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

Does Project Initializer 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 Project Initializer 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 Project Initializer use?

Project Initializer 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 Project Initializer use?

About 406 tokens (SKILL.md is roughly 1.6k 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 Project Initializer?

Skills that share tags, products or a category with Project Initializer: Setup Workspace (probabl-ai/skills, 135 stars), Exploratory Data Analysis (Oleafly/Oleafly, 205 stars), Add Remote Endpoint (nextcloud/android-library, 106 stars) and dotclaude Project Setup (poshan0126/dotclaude, 871 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Project Initializer?

Drchronx (a GitHub user) maintains it in Drchronx/ai-agent-research-starter-kit, which has 134 GitHub stars. The repository holds 53 skills in this directory. The repository was last updated on May 19, 2026.

Source: Drchronx/ai-agent-research-starter-kit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.