Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Tad Init

ASecurity

Initialize TAD Framework in a project. Sets up directory structure and configuration.

3 stars
0 votes
0 copies
0 views
Added 10/6/2026
ai-agentstypescriptgobashtestingrefactoringcode-reviewsecurityperformance

Works with

terminal

Security Analysis

A100/100

Scanned 10/6/2026

$npx -y skills add Sheldon-92/TAD --skill tad-init --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Tad Init?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Tad Init
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/sheldon-92-tad-init/badge)](https://www.skillsdirectory.com/skills/sheldon-92-tad-init)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: tad-init
description: Initialize TAD Framework in a project. Sets up directory structure and configuration.
---

# TAD Initialize Command

When this command is triggered, execute the following:

## ⚠️ MANDATORY OUTPUT FORMAT

**This command MUST produce standardized output in the following format:**

### 📋 Initialization Checklist
Use this checklist format to track progress:
- [ ] TAD directory structure verification
- [ ] Core agent files installation
- [ ] Template files setup
- [ ] Project context initialization
- [ ] Success confirmation and next steps

### 📝 Required Output Sections
1. **Status Report**: Current state and actions taken
2. **File Operations**: List all files created/modified with paths
3. **Verification**: Confirm all components installed correctly
4. **Next Steps**: Clear instructions for agent activation
5. **Error Handling**: Any issues encountered and resolutions

---

## Initialize TAD Framework

1. **Check if TAD already exists**
   - Look for `.tad/` directory
   - If exists, warn user and ask for confirmation to reinitialize

2. **Create TAD structure**
   ```bash
   mkdir -p .tad/active/handoffs
   mkdir -p .tad/archive/handoffs
   mkdir -p .tad/gates
   mkdir -p .tad/project-knowledge
   mkdir -p .tad/templates/output-formats
   mkdir -p .claude/commands
   mkdir -p .claude/skills
   ```

3. **Copy core files from TAD repository**

   ⚠️ **IMPORTANT**: Only copy TAD-specific files, NOT entire directories!

   **TAD config:**
   - Copy `.tad/config.yaml`
   - Copy `.tad/version.txt`
   - Copy `.tad/templates/` (recursive)
   - Copy `.tad/skills/` (recursive)
   - Copy `.tad/schemas/` (recursive)

   **TAD skills** (DO NOT copy non-TAD files like BMad):
   - Copy `.claude/skills/` (recursive — each skill is a directory with SKILL.md)
   - ❌ DO NOT copy files that don't belong to TAD

   **TAD skills:**
   - Copy `.claude/skills/code-review/` (recursive)

4. **Create initial project files**
   - Create `PROJECT_CONTEXT.md` in project root
   - Create `NEXT.md` for task tracking
   - Create `CLAUDE.md` with TAD rules

5. **Bootstrap Project Knowledge** ⚠️ NEW
   - Read `.tad/templates/knowledge-bootstrap.md` for guidance
   - For each knowledge category, extract foundational info from codebase:

   ```yaml
   UX Knowledge:
     sources:
       - tailwind.config.ts (colors, fonts, spacing)
       - app/globals.css (CSS variables, theme)
       - components/ui/ (component library)
     output: .tad/project-knowledge/ux.md → "Foundational" section

   Code Quality:
     sources:
       - package.json (tech stack)
       - tsconfig.json (TypeScript config)
       - src/ structure (file organization)
     output: .tad/project-knowledge/code-quality.md → "Foundational" section

   Testing:
     sources:
       - vitest.config.ts or jest.config.js
       - existing test files (patterns)
       - package.json scripts
     output: .tad/project-knowledge/testing.md → "Foundational" section
   ```

   - If sources don't exist (new project), prompt user for inputs
   - Write "Foundational" section to each knowledge file
   - Mark "Accumulated Learnings" section as empty (to be filled during development)

6. **Verify Knowledge Bootstrap**
   - Check each `.tad/project-knowledge/*.md` file has content beyond template header
   - Report any files that need manual completion:
   ```
   Knowledge Bootstrap Status:
   ✅ ux.md - Foundational section populated
   ✅ code-quality.md - Foundational section populated
   ⚠️ security.md - Needs manual input (no auth config found)
   ✅ testing.md - Foundational section populated
   ```

7. **Display success message**
   ```
   ✅ TAD Framework initialized successfully!

   ## Quick Start
   | Command | Description |
   |---------|-------------|
   | /alex   | Start Alex (Solution Lead) |
   | /blake  | Start Blake (Execution Master) |
   | /gate   | Run quality gate |

   ## Next Steps
   1. Terminal 1: Activate Alex for design
   2. Terminal 2: Activate Blake for execution
   3. State your project requirements
   4. Begin triangle collaboration

   Available scenarios:
   - new_project: Starting from scratch
   - add_feature: Adding new functionality
   - bug_fix: Fixing problems
   - performance: Optimizing performance
   - refactoring: Code cleanup
   - deployment: Release preparation
   ```

Attribution

Sheldon-92Sheldon-92
View sourceSee grades on GitHubMore from Sheldon-92 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →