bootstrap-project
- Repo stars 0
- Author updated Live
- Author repo skills-registry
- Domain
- Engineering
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @tomevault-io · no license declared
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Env read
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools,默认拥有全部工具权限。
---
name: bootstrap-project
description: Use when creating a new project repository to initialize it with standard CLAUDE.md, .cursorrule…
category: engineering
runtime: no special runtime
---
# bootstrap-project output preview
## PART A: Task fit
- Use case: Use when creating a new project repository to initialize it with standard CLAUDE.md, .cursorrules, CLAUDE.local.md, SESSION_LOG.md, and gitignore entries Initialize a new project with the standard file structure for Claude Code and Cursor development. runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Usage / Process / 1. Gather Project Information” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Use when creating a new project repository to initialize it with standard CLAUDE.md, .cursorrules, CLAUDE.local.md, SESSION_LOG.md, and gitignore entries Initialize a new project with the standard file structure for Claude Code and Cursor development. runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “Usage / Process / 1. Gather Project Information” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files, read environment variables; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files, read environment variables; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. The source mentions slash commands such as `/bootstrap-project`; use them first when your agent supports command triggers.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files, read environment variables.
Start with a small task and check whether the result follows “Usage / Process / 1. Gather Project Information”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: bootstrap-project
description: Use when creating a new project repository to initialize it with standard CLAUDE.md, .cursorrule…
category: engineering
source: tomevault-io/skills-registry
---
# bootstrap-project
## When to use
- Use when creating a new project repository to initialize it with standard CLAUDE.md, .cursorrules, CLAUDE.local.md, SE…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Usage / Process / 1. Gather Project Information” and keep inference separate from source facts.
- read files, write/modify files, read environment variables; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "bootstrap-project" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Usage / Process / 1. Gather Project Information
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files, read environment variables | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
} Bootstrap Project
Initialize a new project with the standard file structure for Claude Code and Cursor development.
Usage
/bootstrap-project
Process
1. Gather Project Information
Ask the user for:
- Project name (e.g.,
davidshaevel-k8s-platform) - Brief description (one sentence)
- Tech stack (e.g., Terraform, Kubernetes, Go)
- Cloud providers (e.g., Azure, GCP, AWS)
- Linear project URL (if exists)
- GitHub organization (default:
davidshaevel-dot-com)
2. Generate CLAUDE.md
Create CLAUDE.md from the project template. Fill in the project-specific sections:
- Project Overview (name, description, technologies, project management)
- Architecture (placeholder diagram)
- Repository Structure (directory tree)
- Important File Locations (key paths)
- Helpful Commands (project-specific commands)
- Environment Variables (table of required vars)
- References (docs links, Linear project URL)
What NOT to include: Git workflow, commit format, PR process, code review handling, worktree conventions — these are injected by the davidshaevel-claude-toolkit plugin automatically.
3. Generate .cursorrules
Create .cursorrules with:
- Session continuity instructions (read/write SESSION_LOG.md)
- Development conventions (adapted from plugin conventions)
- Project-specific context
4. Generate CLAUDE.local.md
Create CLAUDE.local.md from the template:
- Cloud account details (placeholder table)
- Infrastructure details
- GitHub repository info
- Linear project info
- Cost summary
5. Generate SESSION_LOG.md
Create SESSION_LOG.md with the empty scaffold:
- Current State section (all fields set to initial values)
- Empty Session History section
6. Update .gitignore
Append to .gitignore (if not already present):
# Agent context files (sensitive/local)
CLAUDE.local.md
SESSION_LOG.md
7. Report
Output a checklist of what was created:
Project bootstrapped:
- [x] CLAUDE.md — project-specific context
- [x] .cursorrules — Cursor development rules
- [x] CLAUDE.local.md — sensitive config template (gitignored)
- [x] SESSION_LOG.md — cross-agent memory (gitignored)
- [x] .gitignore — updated with agent files
Next steps:
1. Fill in CLAUDE.local.md with actual account IDs and resource details
2. Review CLAUDE.md and customize for your project
3. Start your first session — conventions will be injected by the plugin
Source: davidshaevel-dot-com/davidshaevel-marketplace — distributed by TomeVault.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review