Claude Skill

setting-up-a-project

Use whenever asked to set up, onboard, initialize, or spec a project — the front door when the workspace has no spec graph yet (brand-new or an existing codebase); also seeded by the app's Set-up-project card (/skill:setting-up-a-project). Not for feature work in an already-specc

LLM Mart · 0 points · 15 views 0 listing impressions 0 install-command copies
Virus-scanned Reviewed automatically before listing.

Full trust report

Download JetBrains-thinkrail-packages_pi-thinkrail-workflow_skills_setting-up-a-project-ba76462.zip · 1 KB
Part of jetbrains/thinkrail — 11 skills

Install

skills CLI npx skills add https://github.com/JetBrains/thinkrail/tree/main/packages/pi-thinkrail-workflow/skills/setting-up-a-project
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install jetbrains-thinkrail@llmmart
Git git clone https://github.com/JetBrains/thinkrail.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole jetbrains/thinkrail collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Setting up a project — dispatcher

The single entry point for turning a project into a spec graph. Figure out which situation you're in, then follow the matching skill — don't improvise the flow yourself.

1. Detect

Look at the workspace and use the spec tools (spec_grep / spec_graph):

  • Is there already a spec graph (a goal-and-requirements.md or any SPEC.md)?
  • Is there real source code, or is the repo empty / near-empty (just a README or scaffolding)?

2. Route

Situation Follow
Already has specs Don't redo it. Briefly offer to review/extend the graph (fill obvious gaps — a missing architecture.md, un-specced modules). For other work, use brainstorming only when product scope, user-visible behavior, or architecture remains to decide; otherwise proceed directly. Declined → stop. Accepted → Graph extension below.
No specs · empty / near-empty repo The starting-a-new-project skill — interview the user to turn the idea into goal-and-requirements.md.
No specs · real source code The importing-a-codebase skill — analyze the code + agent files and draft the first spec graph, asking only for intent the code can't reveal.

Read and follow that skill's steps.

Graph extension (no dedicated skill)

No dedicated skill covers extending an existing graph. If the offer is accepted, align and adapt to the user's request with your own judgment, holding the writing-specs bar without a routing announcement.

Handoff

Ends by naming exactly one of: starting-a-new-project, importing-a-codebase, or — when specs already exist — the review/extend offer above (declined → stop; accepted → graph extension on judgment against the writing-specs bar).

Files (thinkrail)
  • SKILL.md 2 KB
    ---
    name: setting-up-a-project
    description: "Use when asked to set up, onboard, initialize, or spec a project with no spec graph, or when invoked by the app's Set-up-project card. Not for ordinary work in an already-specced project."
    ---
    
    # Setting up a project — dispatcher
    
    The single entry point for turning a project into a spec graph. Figure out which situation you're in, then
    follow the matching skill — don't improvise the flow yourself.
    
    ## 1. Detect
    
    Look at the workspace and use the spec tools (`spec_grep` / `spec_graph`):
    
    - Is there already a spec graph (a `goal-and-requirements.md` or any `SPEC.md`)?
    - Is there real source code, or is the repo empty / near-empty (just a README or scaffolding)?
    
    ## 2. Route
    
    | Situation | Follow |
    |---|---|
    | **Already has specs** | Don't redo it. Briefly offer to review/extend the graph (fill obvious gaps — a missing `architecture.md`, un-specced modules). For other work, use `brainstorming` only when product scope, user-visible behavior, or architecture remains to decide; otherwise proceed directly. Declined → stop. Accepted → **Graph extension** below. |
    | **No specs · empty / near-empty repo** | The **`starting-a-new-project`** skill — interview the user to turn the idea into `goal-and-requirements.md`. |
    | **No specs · real source code** | The **`importing-a-codebase`** skill — analyze the code + agent files and draft the first spec graph, asking only for intent the code can't reveal. |
    
    Read and follow that skill's steps.
    
    ## Graph extension (no dedicated skill)
    
    No dedicated skill covers extending an existing graph. If the offer is accepted, align and adapt to
    the user's request with your own judgment, holding the **writing-specs** bar without a routing
    announcement.
    
    ## Handoff
    
    Ends by naming exactly one of: **starting-a-new-project**, **importing-a-codebase**, or — when specs
    already exist — the review/extend offer above (declined → stop; accepted → graph extension on
    judgment against the **writing-specs** bar).
    

Comments (0)

Sign in to join the conversation.

No comments yet.

Reviews (0)

No reviews yet.

Related