本文へ移動
cccskills
無料GitHub で公開

ln-700-project-bootstrap

Universal project bootstrapper: CREATE new or TRANSFORM existing project to production-ready structure

インストール方法を見る

含まれるファイル(4)

  • SKILL.md12.1 KB
  • references/stack_detection.md8.4 KB
  • references/transformation_plan_template.md7.4 KB
  • references/verification_checklist.md6.4 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Paths: File paths (shared/, references/, ../ln-*) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root.

ln-700-project-bootstrap

Type: L1 Top Orchestrator Category: 7XX Project Bootstrap

Universal project bootstrapper with two modes: CREATE (generate production-ready project from scratch) or TRANSFORM (migrate existing prototype from any platform to production structure). Output: Clean Architecture, Docker, CI/CD, quality tooling.


Mode Selection

AspectCREATETRANSFORM
InputEmpty directory or target stack configExisting project (Replit, StackBlitz, CodeSandbox, Glitch, custom)
DetectionNo source files foundSource files + optional platform config detected
ln-820SKIP (no deps to upgrade)RUN (upgrade existing deps)
ln-720SCAFFOLD + GENERATERESTRUCTURE + MIGRATE
ln-724SKIP (no artifacts)CONDITIONAL (if platform detected)
ln-730–780RUN (same for both modes)RUN (same for both modes)

Overview

AspectDetails
InputEmpty directory (CREATE) or source project (TRANSFORM)
OutputProduction-ready project with all infrastructure
Delegationsln-820 (conditional) -> ln-720 -> ln-730 -> ln-740 -> ln-760 -> ln-770 -> ln-780

Workflow

Phase 0: Analyze (Tech Detection)
    |
    v
Phase 1: Plan (Generate Transformation Plan)
    |
    v
Phase 2: Confirm (User Approval)
    |
    v
Phase 3: Execute (Delegate to L2 Coordinators)
    |
    +---> ln-820: Dependency Upgrader
    +---> ln-720: Structure Migrator
    +---> ln-730: DevOps Setup
    +---> ln-740: Quality Setup
    +---> ln-760: Security Setup
    +---> ln-770: Crosscutting Setup
    +---> ln-780: Bootstrap Verifier
    |
    v
Phase 4: Report (Summary of Changes)

Phase 0: Technology Detection

Step 0.0: Mode Detection

ConditionModeAction
Empty directory (no source files)CREATEAsk user for target stack, project name, entities
Source files foundTRANSFORMAuto-detect stack, scan for platform artifacts
Ambiguous (few files, unclear)ASKPresent both options, let user choose

Step 0.1: CREATE Mode — User Input

ParameterRequiredDefaultExample
Project nameYes—MyApp
Target backendYes—.NET / Node.js / Python
Target frontendYes—React / Vue / Angular / Svelte
DatabaseYes—PostgreSQL / MongoDB / MySQL
Main entitiesNoUser, Role (starter)User, Product, Order

Step 0.2: Idempotency Pre-flight

If target directory contains existing files:

  1. Detect existing structure (package.json, .csproj, etc.)
  2. Warn user: "Target directory is not empty. Existing files may be overwritten."
  3. Ask: Overwrite (replace all) / Merge (keep existing, add missing) / Abort

Step 0.3: Technology Detection (TRANSFORM mode) / Stack Config (CREATE mode)

Analyze project to detect tech stack before delegations.

Detection Rules

Frontend:
  React:
    - package.json contains "react"
    - Files: *.tsx, *.jsx with React imports
  Vue:
    - package.json contains "vue"
    - Files: *.vue
  Angular:
    - package.json contains "@angular/core"
    - Files: *.component.ts
  Svelte:
    - package.json contains "svelte"
    - Files: *.svelte

Backend:
  .NET:
    - *.csproj files exist
    - *.sln files exist
  Node.js:
    - package.json + (express|fastify|nest|koa)
    - tsconfig.json or jsconfig.json
  Python:
    - requirements.txt OR pyproject.toml OR setup.py
    - (fastapi|flask|django) in dependencies
  Go:
    - go.mod exists

Database:
  PostgreSQL:
    - DATABASE_URL contains "postgres"
    - docker-compose.yml contains "postgres"
  MongoDB:
    - MONGODB_URI in env
    - docker-compose.yml contains "mongo"
  MySQL:
    - DATABASE_URL contains "mysql"

ORM:
  Drizzle: drizzle.config.ts exists
  Prisma: prisma/schema.prisma exists
  EF Core: *.csproj references Microsoft.EntityFrameworkCore
  SQLAlchemy: "sqlalchemy" in requirements

Detection Output

Detected Stack:
  Frontend:
    Framework: React
    Version: 19.x
    Build Tool: Vite
    UI Library: shadcn/ui
    State: React Query

  Backend:
    Current: Node.js + Express
    Target: .NET 10 (user preference)
    ORM: Drizzle -> EF Core

  Database:
    Type: PostgreSQL
    Version: 17

  Structure:
    Type: Monolith (Prototype)
    Origin: replit | stackblitz | codesandbox | glitch | custom
    Target: Clean Architecture

Phase 1: Generate Transformation Plan

Based on detected stack, create detailed plan:

# Bootstrap Transformation Plan

## Source Analysis
- Frontend: React 19 + Vite + TypeScript
- Backend: Express + Drizzle (to be replaced with .NET)
- Database: PostgreSQL 17

## Transformations

### 1. Dependencies (ln-820)
- Upgrade React 18 -> 19
- Upgrade Vite 5 -> 6
- Add missing peer dependencies

### 2. Structure (ln-720)
- Move frontend to src/frontend/
- Create .NET backend: MyApp.Api, MyApp.Domain, etc.
- Migrate mock data from Drizzle to MockData classes

### 3. DevOps (ln-730)
- Create Dockerfile.frontend (multi-stage)
- Create Dockerfile.backend (.NET SDK)
- Create docker-compose.yml
- Create .github/workflows/ci.yml

### 4. Quality (ln-740)
- Configure ESLint (flat config)
- Add Prettier
- Setup Husky + lint-staged
- Create test infrastructure (Vitest, xUnit)

### 5. Security (ln-760)
- Scan for hardcoded secrets
- Run npm audit
- Create SECURITY.md

### 6. Crosscutting (ln-770)
- Configure Serilog logging
- Add GlobalExceptionMiddleware
- Configure CORS policy
- Add /health endpoints
- Enable Swagger

### 7. Verification (ln-780)
- Build all projects
- Run tests
- Start Docker containers
- Verify health checks

## Estimated Changes
- Files created: ~45
- Files modified: ~12
- Files deleted: ~8 (replaced backend)

Phase 2: User Confirmation

Present plan and ask for approval:

Bootstrap Plan Ready!

Summary:
- Frontend: React 19 (upgrade from 18)
- Backend: .NET 10 (replacing Node.js)
- Docker: Multi-container setup
- CI/CD: GitHub Actions
- Quality: ESLint, Prettier, Husky

Proceed with bootstrap? [Y/n]

If user declines, ask for modifications.


Phase 3: Execute Delegations

Sequential delegation to L2 coordinators:

OrderSkillPurposeCREATE modeTRANSFORM modeDepends On
1ln-820Upgrade dependenciesSKIPRUN—
2ln-720Structure (SCAFFOLD/RESTRUCTURE)RUN (SCAFFOLD)RUN (RESTRUCTURE)ln-820
3ln-730Setup Docker/CIRUNRUNln-720
4ln-740Configure quality toolsRUNRUNln-720
5ln-760Security scanningRUNRUNln-820
6ln-770Crosscutting concernsRUNRUNln-720
7ln-780Build and verifyRUNRUNAll above

Delegation Protocol

For each L2 coordinator:

  1. Prepare context:

    Stack:
      frontend: { framework, version, buildTool }
      backend: { framework, version }
      database: { type, version }
    
    Paths:
      root: /project
      frontend: /project/src/frontend
      backend: /project/src/MyApp.Api
    
    Options:
      skipTests: false
      allowFailures: false
    
  2. Invoke skill: Pass context as input

  3. Collect result:

    Status: success | partial | failed
    FilesCreated: [...]
    FilesModified: [...]
    Warnings: [...]
    Errors: [...]
    
  4. Handle errors:

    • Log error details
    • Ask user: continue or abort?
    • If abort, rollback if possible

Phase 4: Generate Report

Bootstrap Completeness Assessment

Context: Final verification that bootstrap produced a working project, not just files.

#CategoryCheckSource
1StructureClean Architecture layers presentln-720 result
2DependenciesAll packages installed, no version conflictsln-820 result
3DevOpsDocker builds, CI pipeline validln-730 result
4QualityLinters/formatters configured and passln-740 result
5SecurityNo hardcoded secrets, scanning configuredln-760 result
6BuildProject compiles/builds without errorsln-780 result

Completeness Score = count of PASS / 6

  • 6/6: Bootstrap complete
  • 4-5/6: Bootstrap complete with warnings (list failing categories)
  • <4/6: Bootstrap incomplete — list blocking issues for user action

Summary Report

Final summary after all delegations:

Bootstrap Complete!

Duration: 24 minutes 32 seconds

Changes Summary:
  Files Created: 47
  Files Modified: 15
  Files Deleted: 9

By Category:
  Dependencies:
    - Upgraded 23 packages
    - No breaking changes detected

  Structure:
    - Created 5 .NET projects
    - Restructured frontend (12 components extracted)
    - Migrated 8 mock data files

  DevOps:
    - Created Dockerfile.frontend
    - Created Dockerfile.backend
    - Created docker-compose.yml
    - Created .github/workflows/ci.yml

  Quality:
    - Configured ESLint + Prettier
    - Installed Husky hooks
    - Created 3 test files

  Security:
    - Scanned 156 files
    - Found 0 secrets
    - 2 vulnerability warnings (low severity)

  Crosscutting:
    - Configured Serilog
    - Added error handling
    - CORS enabled for localhost
    - Health checks at /health
    - Swagger at /swagger

Verification:
  Build: SUCCESS
  Tests: 42 passed, 0 failed
  Docker: 3 containers running
  Health: All endpoints responding

Next Steps:
  1. Open http://localhost:3000 (frontend)
  2. Open http://localhost:5000/swagger (API docs)
  3. Run 'git add . && git commit -m "Bootstrap complete"'

Error Handling

Recoverable Errors

ErrorAction
Dependency conflictTry with --legacy-peer-deps
Build failureLog error, suggest fix, continue
Test failureLog warning, continue with --allow-failures
Docker build failSuggest Dockerfile fixes

Fatal Errors

ErrorActionMode
No package.json (TRANSFORM)Abort: "Not a Node.js project"TRANSFORM
Unsupported stackAbort: "Stack not supported: {stack}"Both
Permission deniedAbort: "Cannot write to {path}"Both
No stack selectedAbort: "Target stack required for CREATE mode"CREATE
Conflicting filesAbort if user chose "Abort" in pre-flightCREATE

Configuration

Skill Options

Options:
  # Backend replacement
  targetBackend: ".NET" | "Node" | "Python" | "keep"

  # Frontend refactoring depth
  frontendRefactoring: "minimal" | "moderate" | "full"

  # Docker setup
  dockerEnabled: true
  dockerRegistry: null  # Optional: ghcr.io/user

  # CI/CD
  cicdProvider: "github" | "azure" | "gitlab" | "none"

  # Quality tools
  linterConfig: "recommended" | "strict"
  precommitHooks: true

  # Verification
  runTests: true
  startContainers: true
  keepContainersRunning: true

Environment Variables

# Optional: Override detection
BOOTSTRAP_FRONTEND=react
BOOTSTRAP_BACKEND=dotnet
BOOTSTRAP_DB=postgres

# Optional: Skip steps
SKIP_DEPENDENCIES=false
SKIP_DOCKER=false
SKIP_TESTS=false

Integration with Existing Skills

SkillIntegration
ln-001-standards-researcherQuery for best practices during ln-720
ln-002-best-practices-researcherGenerate guides during ln-720
ln-100-documents-pipelineCall after bootstrap for docs
ln-310-multi-agent-validatorValidate generated tasks

References

MANDATORY READ: Load these files at the phases indicated:

  • references/stack_detection.md — Phase 0 detection rules and patterns
  • references/transformation_plan_template.md — Phase 1 plan template
  • references/verification_checklist.md — Phase 3 verification steps

Version: 2.0.0 Last Updated: 2026-02-07

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA standards. Use this skill to generate semantic ARIA for Web and accessibility traits for Web and Native platforms (iOS/Android).

日本語の概要は準備中です。原文の説明を表示しています。

tensology/decisionsai172026年10月13日 更新

Whole site or product — a full web accessibility (a11y) audit against WCAG 2.2, following the WCAG-EM methodology. Defines scope, samples representative pages and flows, runs the automated tier (`accessibility-scan`) and the hands-on manual tier (`accessibility-inspect`), and produces one conformance report. Grades each finding by severity and evidence basis, and states per-criterion conformance as pass, fail, or undetermined (needs a human). Use it for 'audit my site for accessibility', 'is this product accessible', 'a11y audit', 'WCAG or Section 508 conformance report', or any multi-page assessment. Assesses; does not fix (use `accessibility-fix`) or diff (use `accessibility-diff`). For a single page use `accessibility-scan`; for hands-on keyboard and screen-reader checks use `accessibility-inspect`.

日本語の概要は準備中です。原文の説明を表示しています。

tensology/decisionsai172026年10月13日 更新

Regression check — diff a live page's web accessibility (a11y) violations against a baseline. By default it compares your uncommitted changes (stash-based); pass `--branch [<name>]` to compare against a branch. Reports the new WCAG violations introduced, the ones fixed, and the count of pre-existing ones. Use it for 'did my change break accessibility', 'what a11y issues did this PR add', or as a CI gate. For a full scan of one page use `accessibility-scan`; for a whole site use `accessibility-audit`.

日本語の概要は準備中です。原文の説明を表示しています。

tensology/decisionsai172026年10月13日 更新

Remediation only — repair web accessibility (a11y) violations against WCAG 2.2 with a baseline, edit, and verify loop. Takes a target (URL, files, directory) or a findings worklist from `accessibility-scan`/`accessibility-inspect`/`accessibility-audit`, applies mechanical fixes as given, leaves TODOs for visual or contextual judgment, and verifies by re-running the baseline check. It only fixes. To find issues use `accessibility-scan` (one page, automated), `accessibility-inspect` (one page, manual), or `accessibility-audit` (whole site, WCAG-EM); to check for regressions use `accessibility-diff`. Use it for 'fix the a11y issues in X', 'make this accessible', 'add missing alt text and labels', 'apply these accessibility fixes', 'remediate these violations'.

日本語の概要は準備中です。原文の説明を表示しています。

tensology/decisionsai172026年10月13日 更新

One page, hands-on manual tier — drive a live page through the web accessibility (a11y) checks a rule engine can't decide: keyboard operation and focus order, screen-reader names, roles and states from the accessibility tree, reflow and zoom, reduced motion, form errors, and target size. Grades each finding by evidence basis (verified / confirm-with-a-human / human-required) and severity, and closes every criterion in a ledger: verified, flagged, not exercised, or N/A. Locates and assesses; does not fix (use `accessibility-fix`). Use it for keyboard testing, focus-order checks, screen-reader or a11y-tree review, reflow and zoom at 200%, or 'is this operable, not just lint-clean'. The automated tier is `accessibility-scan`; `accessibility-audit` runs both across a sampled site.

日本語の概要は準備中です。原文の説明を表示しています。

tensology/decisionsai172026年10月13日 更新

One page, automated tier — run the web accessibility (a11y) rule engine against a live page and locate every violation it can detect mechanically. Pass a URL, a config target name (e.g. `accesslint:accessibility-scan dev`), or nothing to use the default target from `accesslint.config.json`. Ensures a debuggable Chrome, runs the @accesslint/core engine over CDP, and returns a worklist of live-DOM WCAG 2.2 violations, each grounded to its DOM selector and source `file:line`. Locates; doesn't edit. Use it for 'is this page accessible', 'check a11y on this URL', 'find contrast and alt-text issues', or to verify a UI change. For hands-on keyboard and screen-reader checks use `accessibility-inspect`; for a whole site or product use `accessibility-audit`; to diff against uncommitted changes or a branch use `accessibility-diff`.

日本語の概要は準備中です。原文の説明を表示しています。

tensology/decisionsai172026年10月13日 更新

tensology のスキルをすべて見る

このスキルの問題を報告する