Index of every page on this site: llms.txt
All skills
jetbrains avatar

/setting-up-a-project

@e85862d
by jetbrainsjetbrains/thinkrail8.4k stars
532
Run it yourself

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.

Use this Skill: https://skilld.dev/gh/jetbrains/thinkrail/setting-up-a-project

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈52 tokens for metadata: the name and description. ≈445 when used: this file.

Description uses 2.6% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈210 characters, or 2.6%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

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). Other work routes as usual: features, behavior changes, and bug fixes through brainstorming; work that changes no behavior proceeds 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).

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts22d3 checks · Risk SAFE
  • Gen Agent Trust Hub22d

    The skill acts as a dispatcher for project initialization tasks by analyzing workspace files to determine the current project state. While functionally legitimate, it presents an attack surface for indirect prompt injection because it processes untrusted repository content without explicit sanitization or boundary markers.

  • Socket26d

    No alerts

  • Snyk26d

    Risk: LOW · No issues

Signed by skilld at e85862d. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 days ago.

Activeupdated last month

README badge

README badge for jetbrains/thinkrail/setting-up-a-project