Technical Spec logo

Technical Spec

Community
shinpr
technical-spec

Defines environment variables, architecture design, and build/test commands. Use when configuring environment or designing architecture.

Overview

Publishershinpr
Repositoryai-coding-project-boilerplate
Skill nametechnical-spec
Stars
234
Forks
28
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by shinpr on GitHub. Read the source before you install it.

Installation

Install the Technical Spec AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/shinpr/ai-coding-project-boilerplate/tree/main/.claude/skills-en/technical-spec
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/shinpr/ai-coding-project-boilerplate.git /tmp/ai-coding-project-boilerplate
mkdir -p .claude/skills
cp -r /tmp/ai-coding-project-boilerplate/.claude/skills-en/technical-spec .claude/skills/technical-spec
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Technical Spec in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Technical Spec on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Technical Spec is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Technical Design Rules

Prerequisite Detection

Inspect manifests, lockfiles, build/test configuration, CI definitions, and representative source files before applying a technology- or command-specific rule. Treat a tool, script, path alias, or runtime as observed only when repository evidence names it. Label conclusions from surrounding patterns as inferred. When a missing decision changes architecture, compatibility, security, or verification, stop and name the exact configuration or user decision required.

Basic Technology Stack Policy

These rules apply to a TypeScript application when repository configuration confirms that stack. Select architecture by mapping current requirements and accepted constraints to explicit module responsibilities, dependency direction, data flow, and verification boundaries.

Environment Variable Management and Security

Environment Variable Management

  • Centrally manage environment variables and the build-time validation mechanism that enforces their type safety
  • Read environment variables through one typed configuration boundary; application code consumes validated configuration values
  • Give a variable a default only when requirements define valid behavior for absence; otherwise fail configuration validation with the variable name and expected format

Security

  • Keep local .env files outside version control and provide non-secret example files for required variable names
  • Load API keys and secrets from the configured secret store or runtime environment boundary
  • Log and return only fields approved for the current trust boundary; redact credentials, tokens, personal data, and internal diagnostics before returning data across an untrusted boundary

Architecture Design

Architecture Design Principles

Select architecture using these observable decisions:

  • Responsibilities: Each module/layer names the behavior it owns and the behavior it delegates
  • Dependency direction: Imports and runtime calls follow the project boundary rules observed in configuration or representative implementations
  • State/data ownership: Each persisted or mutable value has one authoritative owner
  • Verification boundary: Each public contract has a unit, integration, or E2E check that can observe it

Unified Data Flow Principles

Basic Principles
  1. Single Data Source: Store the same information in only one place
  2. Structured Data Priority: Use parsed objects rather than JSON strings
  3. Responsibility Separation: Each layer names the data or behavior it owns and the boundary through which other layers use it
Data Flow Best Practices
  • Validation at Input: Validate data at input layer and pass internally in type-safe form
  • Centralized Transformation: Consolidate data transformation logic in dedicated utilities
  • Structured Logging: Output structured logs at each stage of data flow

Build and Testing

Select the package manager from the packageManager field, lockfile, or established CI command in that order. Execute only scripts present in the selected manifest.

Build Commands

  • build - TypeScript build
  • type-check - Type check (no emit)

Testing Commands

  • test - Run tests

Quality Assurance Mechanism Awareness

Before executing quality checks, identify what quality mechanisms exist for the change area:

  • Primary detection: inspect the change area's file types, project manifest, and configuration to identify applicable quality tools
    • Check CI pipeline definitions for checks that cover the affected paths
    • Check for domain-specific linter or validator configurations (e.g., schema validators, API spec validators, configuration file linters)
    • Check for domain-specific constraints in project configuration (naming rules, length limits, format requirements)
  • When a task file supplies Operation Verification Methods, run them as task-specific checks
  • Include discovered domain-specific checks alongside standard quality phases below

Quality Check Requirements

Quality checks are mandatory upon implementation completion:

Phase 1-3: Code Quality Checks

  • Auto-detect and execute the following from package.json scripts:
    • lint + format check
    • Detect unused exports
    • Detect circular dependencies
    • TypeScript build

Transition evidence: every applicable static/domain check exits successfully. A missing required script is reported with the manifest/configuration path, and the remaining checks still run; whether the missing check leaves required proof unavailable is decided by the quality-fixer result.

Phase 4: Tests

  • test - Test execution

Transition evidence: all applicable configured test suites pass, or an environment-dependent suite is recorded as blocked with its exact prerequisite.

Phase 5: Code Quality Re-verification

  • check:code - Re-verify code quality (clean up side effects from test fixes in Phase 4)

Completion evidence: static/domain checks still pass after test-related fixes, the build succeeds, and every required test has passed or is explicitly blocked.

Auxiliary Commands

  • check:all - Overall integrated check (check:code + test) *for manual batch verification
  • format - Format fixes
  • lint:fix - Lint fixes

Troubleshooting

  • Dependency errors: First record the failing resolver output, selected package manager, manifest, and lockfile state. Use the repository's established clean-install command only when it preserves the lockfile and generated artifacts; request approval before an operation that removes or regenerates dependency state

Frequently asked questions

What does the Technical Spec AI skill do?

Defines environment variables, architecture design, and build/test commands. Use when configuring environment or designing architecture.

Why use Technical Spec on TypingMind?

Because you install it once and use it with any model. Technical Spec is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Technical Spec in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/shinpr/ai-coding-project-boilerplate/tree/main/.claude/skills-en/technical-spec. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Technical Spec?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Technical Spec?

As many as you like. As long as a model supports skills, you can use Technical Spec with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Technical Spec AI skill free?

Yes. It is published on GitHub by shinpr under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇