Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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
  • 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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Tinystruct Patterns

ASecurity

Use when developing with the tinystruct Java framework — Application classes, @Action routes, JSON, persistence, SSE, uploads, and MCP tools. Triggers on \"tinystruct-patterns\", \"tinystruct\", \"@Action\".

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsjavatestingdebuggingapidatabase

Works with

terminalcliapimcp

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add majinmagros/magros.ai-skills --skill tinystruct-patterns --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Tinystruct Patterns?

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

Security grade badge for Tinystruct Patterns
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-tinystruct-patterns/badge)](https://www.skillsdirectory.com/skills/majinmagros-tinystruct-patterns)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: tinystruct-patterns
description: "Use when developing with the tinystruct Java framework — Application classes, @Action routes, JSON, persistence, SSE, uploads, and MCP tools. Triggers on \"tinystruct-patterns\", \"tinystruct\", \"@Action\"."
metadata:
  origin: ECC
---

# tinystruct Development Patterns

Dual-mode Java framework: CLI and HTTP are equal citizens, no `main()` needed. Detalhes em `references/`.

## When to Activate

- Creating `Application` modules extending `AbstractApplication`
- Defining routes and CLI actions with `@Action`
- JSON via native `Builder`/`Builders`; persistence via `AbstractData` POJOs
- SSE push, file uploads, outbound HTTP with `URLRequest`
- MCP tools/servers, config, or routing/CLI debugging

## Core Principles

1. **Dual-mode actions** — every `@Action` runs from terminal and browser
2. **`init()` for setup, `@Action` for discovery** — no `main()`, no manual registry
3. **Zero-dependency JSON** — `Builder`/`Builders`, never Gson/Jackson
4. **Mode-aware actions** — restrict sensitive ops to CLI or specific HTTP verbs
5. **Sanitize MCP inputs** — tool returns feed the model context (prompt injection)

## Example

```java
public class MyService extends AbstractApplication {
    @Override public void init() { setTemplateRequired(false); }
    @Action("greet")
    public String greet(String name) { return "Hello, " + name + "!"; }
}
```

## References

- `references/architecture.md` — abstractions, package map, properties
- `references/routing.md` — annotation details, modes, parameters
- `references/data-handling.md` — Builder, Builders, JSON serialization
- `references/database.md` — AbstractData POJOs, CRUD, mapping XML, generation
- `references/system-usage.md` — Context, sessions, SSE, uploads, events, networking
- `references/testing.md` — JUnit 5 unit and HTTP integration testing
- `references/mcp-integration.md` — MCP tools/servers, prompt-injection sanitizing
- `references/config-antipatterns.md` — application.properties, red flags, best practices

## Checklist

- [ ] `public` `@Action` methods; `setTemplateRequired(false)` for API-only apps
- [ ] `Builders` for arrays, `Builder` for objects; no external JSON lib
- [ ] Explicit `mode` where GET/POST or CLI/HTTP could collide
- [ ] MCP tool args validated (length, charset, nullity) before returning
- [ ] Config externalized in `application.properties`; entry via `bin/dispatcher`

Attribution

majinmagrosmajinmagros
View sourceMore from majinmagros →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 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', ...

686011 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.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →