Agent skill

Init Project Course

by flonat in flonat/flonat-research

Bootstrap a university course or module folder with the canonical teaching structure, guidance, and starter files.

MITAuto-check passedDevelopment

Install Init Project Course

skills CLI
$ npx skills add flonat/flonat-research --skill init-project-course -a claude-code

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

GitHub CLI
$ gh skill install flonat/flonat-research init-project-course --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/flonat/flonat-research.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/init-project-course .claude/skills/init-project-course && 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
init-project-course
GitHub stars
145
Token cost
~1.6k tokens
SKILL.md length
623 words
Files
3 (incl. references)
Skills in repo
83
Repo updated
First seen
Licence
MIT

At a glance

Bootstrap a university course or module folder with the canonical teaching structure, guidance, and starter files.

  • Works in 8 steps: Scan → Interview (4-5 questions max) → Organise → …
  • Migrating a course workspace
  • SKILL.md covers When to Use, When NOT to Use — Escalate, Phase 1: Scan and Phase 2: Interview (4-5…, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Init Project Course is an agent skill from flonat/flonat-research. Bootstrap a university course or module folder with the canonical teaching structure, guidance, and starter files. Use when creating or migrating a course workspace. Not for checking an existing course without modifying it; use $audit-project-course.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/memory-and-settings.md` and `references/organise-templates.md`).

It sits in Development, covering Project scaffolding. The repository describes itself as: Shareable Claude Code + Codex infrastructure for PhD researchers — skills, agents, hooks, and rules for academic workflows. The licence is MIT.

When your agent uses it

  • Migrating a course workspace
  • Tasks that involve Project scaffolding

Example prompts

  • “/init-project-course”

Requirements

  • Pre-approved tools (allowed-tools): Bash(mkdir*), Bash(mv*), Bash(ls*), Bash(tree*), Bash(find*), Bash(rm*), Bash(cp*), Read, Write, Edit, Glob, Grep, AskUserQuestion

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. Scan
  2. Interview (4-5 questions max)
  3. Organise
  4. Create CLAUDE.md
  5. Seed MEMORY.md
  6. Settings
  7. Vault Sync
  8. Confirmation

What it can do on your machine

Read from SKILL.md and the folder at commit da27600. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(mkdir*)
    • Bash(mv*)
    • Bash(ls*)
    • Bash(tree*)
    • Bash(find*)
    • Bash(rm*)
    • Bash(cp*)
    • Read
    • Write
    • Edit

    …and 3 more on the same allowed-tools line.

    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

Init Project Course loads about 1.6k tokens when it runs, and up to ~3.2k if it reads all its reference files. Until then it costs about 68 tokens; SKILL.md has 623 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~68
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.2k

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 flonat/flonat-research at commit da27600, republished under its MIT licence (© flonat). 623 words, ~1,615 tokens.

Download SKILL.mdSave it as .claude/skills/init-project-course/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
init-project-course
description
Bootstrap a university course or module folder with the canonical teaching structure, guidance, and starter files. Use when creating or migrating a course workspace. Not for checking an existing course without modifying it; use $audit-project-course.
allowed-tools
Bash(mkdir*), Bash(mv*), Bash(ls*), Bash(tree*), Bash(find*), Bash(rm*), Bash(cp*), Read, Write, Edit, Glob, Grep, AskUserQuestion
argument-hint
[no arguments — runs in current directory]

Init Project Course

Bootstrap a university course or module folder into a clean, navigable structure. Designed for taught modules with lectures, workshops, assessments, and optionally recordings.

When to Use

  • University modules with lectures + workshops + assessments
  • Course folders that have accumulated files over a term
  • When the user says "organise this module", "init course", "set up this module folder"
  • Any taught course with recurring weekly components

When NOT to Use — Escalate

  • To init-project-light if it's a one-off document collection (no lectures/workshops structure)
  • To init-project-research if it's a research project that happens to be for a course

Phase 1: Scan

Read everything already in the directory before asking questions.

  1. List all files and folders (excluding .claude/, .DS_Store)
  2. Identify content types:
    • Lecture PDFs — files matching Lecture* or containing "lecture" in name
    • Seminar materials — files matching Seminar*, Session*, or containing "seminar" in name (discussion-based modules use seminars instead of lectures)
    • Lecture recordings — video files (.mp4, .mov, .mkv, .webm, .avi) or folders named recordings
    • Workshop folders — folders matching Workshop*, Lab*, Week*, or numbered folders with exercise content
    • Assessment folders — folders containing "group", "individual", "exam", "coursework", "assignment", "portfolio"
    • Workshop PDFs — PDFs inside workshop folders that are NOT lectures (exercise sheets, briefs)
    • Code projects — node_modules/, package.json, .py, .js, .ts files inside workshop folders
    • Notes — personal notes, reading lists, exercise solutions (common in student modules)
  3. Detect duplicates: lecture PDFs that appear in multiple locations
  4. Note workshop numbering gaps (normal — not every week has a workshop)
  5. Check for existing organisation (already has lectures/, workshops/, etc.)

Goal: Build a complete inventory so the interview is short.


Phase 2: Interview (4-5 questions max)

Use the available structured-question mechanism. Only ask what you couldn't infer from Phase 1.

Pick from these (skip any you can already answer):

  1. What module is this? — code + name (e.g., "IB9PK Advances in Behavioural Science")
  2. Are you a student or instructor? — determines template variant (see Phase 3)
  3. Who teaches it? — name(s) and role(s) (for student modules: instructor name; for instructor modules: module leader if different)
  4. What components exist? — lectures/seminars, workshops, group work, individual work, exams, recordings
  5. Status? — still in progress (more content coming) or archived/complete

If Phase 1 gave you enough, confirm your understanding instead of asking:

"This looks like [module code + name]. You're [student/instructor]. It has [N] workshops, [N] lecture PDFs, and [assessment types]. Still in progress. Correct?"

Always interview — even if scan is comprehensive. Course folders affect a full term of work; assumptions are expensive.


Show full SKILL.md (214 more words)Show less

Phase 3: Organise

Present the proposed structure and wait for explicit approval before moving anything.

Full templates (student + instructor directory structures), workshop naming, lecture/recording/assessment handling rules: references/organise-templates.md


Phase 4: Create CLAUDE.md

Follow the lean-guidance-files rule. Include only:

  1. Module overview — code, name, institution, programme, credits, 1-2 sentence description
  2. People — instructor(s) and/or student, role
  3. Assessment — type(s), format, word count/page limit, deadline(s) if known
  4. Directory structure — compact tree of the organised layout
  5. Conventions — detectable patterns (LaTeX compilation, GitHub repo naming, submission format)
  6. Status note — "in progress" or "complete/archived", with note on what's still to come

Do NOT include:

  • Lecture-by-lecture notes
  • Workshop solution details
  • Full assessment criteria (those live in docs/ or assessments/)
  • Anything that duplicates global rules

Phase 5: Seed MEMORY.md

Create MEMORY.md using the appropriate template (student or instructor). Templates, settings.local.json, and vault entry details: references/memory-and-settings.md


Phase 6: Settings

Create .claude/settings.local.json if missing. Full details: references/memory-and-settings.md


Phase 7: Vault Sync

Offer to create entries in the vault tracking for this module (Student or Instructor). Database IDs and field mappings: references/memory-and-settings.md


Phase 8: Confirmation

Short report:

Set up course project: <module code + name>
Role: Student / Instructor

Created:
  - CLAUDE.md
  - MEMORY.md (seeded with [student/instructor] template)
  - lectures/ or seminars/ (N PDFs, deduplicated from M locations)
  - notes/ (student only, if applicable)
  - recordings/ (if applicable)
  - workshops/ (N workshops, renamed from original folders)
  - assessments/{types}/ (moved from original folders)
  - docs/ (module specification, guidelines)
  - [.claude/settings.local.json if created]
  - [vault entry created in Modules Pipeline (Student/Instructor)]

Workshop naming:
  "Workshop 1 - JavaScript Bootcamp" → workshops/01-javascript-bootcamp
  "Workshop 6" → workshops/06-cwe-vulnerability-analysis
  ...

Cross-References

SkillRelationship
init-project-lightFor non-course document collections
init-project-researchFor research projects within a course
audit-project-courseRun later to check the structure is still clean
update-project-docRun later to refresh CLAUDE.md if the module grows

© flonat, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in skills/init-project-course of flonat/flonat-research.

  • SKILL.md
  • references/memory-and-settings.md
  • references/organise-templates.md

Open the folder on GitHubat commit da27600

Compare with similar skills

Init Project Course 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.

Init Project Course compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Init Project Course this skillflonat/flonat-research145—~1.6kAutomated safety check: PassMIT
Nx Generatenomcopter/react-mosaic4.8k7 repos~1.9kAutomated safety check: PassCustom licence
PonytailDavidObando/gsharp5658 repos~1.7kAutomated safety check: PassMIT
Run Nx Generatornrwl/nx29k2 repos~592Automated safety check: NotesMIT
Conductor Setupgemini-cli-extensions/conductor3.8k—~4.2kAutomated safety check: PassApache-2.0
Mirage VFS Adapter Authoringstrukto-ai/mirage3.7k—~2.5kAutomated safety check: PassApache-2.0

Similar skills

  • Nx Generate

    nomcopter/react-mosaic

    Generate code using nx generators. An agent skill from nomcopter/react-mosaic.

    4.8k GitHub starsUsed in 7 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Ponytail

    DavidObando/gsharp

    Forces the laziest solution that actually works, simplest, shortest, most minimal.

    565 GitHub starsUsed in 8 repos~1.7k tokens
    DevelopmentAuto-check passed
  • Run Nx generators with prioritization for workspace-plugin generators.

    29k GitHub starsUsed in 2 repos~592 tokens
    DevelopmentAuto-check: notes
  • Conductor Setup

    gemini-cli-extensions/conductor

    Scaffolds the project and sets up the Conductor environment.

    3.8k GitHub stars~4.2k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Builds or extends a custom Mirage virtual filesystem adapter for an API, database, object store or app data, with a working mount configuration and filesystem tests.

    3.7k GitHub stars~2.5k tokensUpdated today
    DevelopmentAuto-check passed
  • Enforces this repository's TypeScript backend module architecture under server/: feature folders, barrel exports, and where shared types and utilities belong.

    14k GitHub stars~1.2k tokensUpdated today
    DevelopmentAuto-check passed

More from flonat/flonat-research

All 83 skills in this repo
  • Latex Posters

    flonat/flonat-research

    Create a large-format academic poster in LaTeX using beamerposter, tikzposter, or baposter.

    145 GitHub stars~1.5k tokensUpdated 8 days ago
    Auto-check: notes
  • Skill Creator

    flonat/flonat-research

    Create, revise, and evaluate reusable AI workflow skills, including trigger-quality tests.

    145 GitHub stars~4.4k tokensUpdated 8 days ago
    Auto-check passed
  • DOCX

    flonat/flonat-research

    Create, read, edit, or convert Microsoft Word documents while preserving professional document structure.

    145 GitHub stars~1.2k tokensUpdated 8 days ago
    Auto-check passed
  • PDF

    flonat/flonat-research

    Read, create, combine, split, rotate, OCR, watermark, secure, or extract content from PDF files.

    145 GitHub stars~488 tokensUpdated 8 days ago
    Auto-check passed
  • Init Project Orchestration

    flonat/flonat-research

    Create or migrate project-level agents, repeatable project workflows, and planning state from one client-neutral contract, then render repository-scoped adapters for both Claude Code and Codex.

    145 GitHub stars~1.6k tokensUpdated 8 days ago
    Auto-check passed
  • Pre Commit Audit

    flonat/flonat-research

    Deliver a fast pre-commit safety scan: file size, anonymity (author / affiliation strings in tex/bib), hardcoded secrets, and invisible-Unicode carriers.

    145 GitHub stars~2.8k tokensUpdated 8 days ago
    Auto-check: notes

Categories

Questions about Init Project Course

What does Init Project Course do?

Bootstrap a university course or module folder with the canonical teaching structure, guidance, and starter files. Init Project Course is an agent skill from flonat/flonat-research. Bootstrap a university course or module folder with the canonical teaching structure, guidance, and starter files.

When should I use Init Project Course?

Init Project Course fits situations like: migrating a course workspace; tasks that involve Project scaffolding.

How do I install Init Project Course in Claude Code?

Run `npx skills add flonat/flonat-research --skill init-project-course -a claude-code`. Or copy the skill folder (skills/init-project-course in flonat/flonat-research) into .claude/skills/init-project-course in your project. Claude Code loads it when a task matches its description.

How do I install Init Project Course in Codex?

Run `npx skills add flonat/flonat-research --skill init-project-course -a codex`. Or copy the skill folder (skills/init-project-course in flonat/flonat-research) into .agents/skills/init-project-course in your project. Codex loads it when a task matches its description.

Can I use Init Project Course 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 flonat/flonat-research --skill init-project-course -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/init-project-course, .gemini/skills/init-project-course, .github/skills/init-project-course and .opencode/skills/init-project-course in your project.

What does Init Project Course need to run?

SKILL.md names no scripts, command-line tools or credentials: Init Project Course is instructions for the agent only. Its frontmatter pre-approves these tools: Bash(mkdir*), Bash(mv*), Bash(ls*), Bash(tree*), Bash(find*), Bash(rm*), Bash(cp*), Read, Write, Edit, Glob, Grep, AskUserQuestion.

Does Init Project Course 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 Init Project Course 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 Init Project Course use?

Init Project Course 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 Init Project Course use?

About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.5k tokens, read only when the agent opens those files.

What are the alternatives to Init Project Course?

Skills that share tags, products or a category with Init Project Course: Nx Generate (nomcopter/react-mosaic, 4.8k stars), Ponytail (DavidObando/gsharp, 565 stars), Run Nx Generator (nrwl/nx, 29k stars) and Conductor Setup (gemini-cli-extensions/conductor, 3.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Init Project Course?

flonat (a GitHub user) maintains it in flonat/flonat-research, which has 145 GitHub stars. The repository holds 83 skills in this directory. The repository was last updated on September 29, 2026.

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