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

Mermate Tab Typescript

ASecurity

Stage 5 tab (TypeScript) of the Mermate pipeline — TypeScript runtime generation from a verified TLA+ spec, tsc compile, tsx test harness, coverage, and the terminal progressionUpdate. Use when editing TS generation, the test harness, /api/render/ts endpoints, or TS↔TLA+ conformance. Refinement judgments defer to tla-refinement / specification-master-agent.

3 stars
0 votes
0 copies
0 views
Added 9/11/2026
testingtypescriptrustreactnodeapibackend

Works with

terminalapi

Security Analysis

A92/100
mediumUses curl or wget to download content

Scanned 9/11/2026

Install to Claude Code

$npx -y skills add DylanCkawalec/Mermate --skill mermate-tab-typescript --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mermate Tab Typescript?

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

Security grade badge for Mermate Tab Typescript
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/dylanckawalec-mermate-tab-typescript/badge)](https://www.skillsdirectory.com/skills/dylanckawalec-mermate-tab-typescript)

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

Download Zip
Files
SKILL.md
---
name: mermate-tab-typescript
description: Stage 5 tab (TypeScript) of the Mermate pipeline — TypeScript runtime generation from a verified TLA+ spec, tsc compile, tsx test harness, coverage, and the terminal progressionUpdate. Use when editing TS generation, the test harness, /api/render/ts endpoints, or TS↔TLA+ conformance. Refinement judgments defer to tla-refinement / specification-master-agent.
---

# Mermate Tab 5 · TypeScript (ts)

Operates under `mermate` master invariants; Lamport standards via `specification-master-agent`. The TS runtime is a refinement of the TLA+ spec — conformance claims route through `tla-refinement` discipline, not vibes.

## Stage Identity (from `STAGE_REGISTRY.ts`, public/js/mermaid-gpt-app.js)
- Label: **TypeScript** · reveal: `STAGE 5 · TYPESCRIPT` · color `#34d399`
- Expected duration: ≈20–90s · enhance default: OFF · no upload (runtime is generated)
- **IPO contract**:
  - Input: verified TLA+ spec (mastered run)
  - Process: runtime generation → `tsc` compile → `tsx` test harness + Specula review against the TLA+ spec
  - Output: state-machine implementation, test harness, coverage reports

## Owning Code
- Backend: `server/routes/ts.js` —
  - `POST /api/render/ts` (generate, lines 103–421)
  - `GET /api/render/ts/source/:run_id` (read back without recompile, lines 70–101)
  - `GET /api/render/ts/status`
- Toolchain: `tsc` + `tsx`; Specula LLM reviews generated TS against the TLA+ spec
- Terminal artifacts + bundle: `GET /api/runs/:runId/bundle` (server/routes/bundle.js)
- Tests: `test/test-ts-compiler.js`
- Optional extensions: `/api/render/tsx` (React scaffold, server/routes/tsx.js), `/api/render/rust` (server/routes/rust.js)

## Stage Invariants
1. **Spec precedes code**: TS generation requires a SANY-verified TLA+ artifact from the same `run_id`; never generate TS from a diagram directly.
2. Terminal honesty: outcomes are `ts_complete`, `ts_partial` (compiles, tests incomplete), or `ts_failed` — reported verbatim to Opseeq and in `progressionUpdate` (unlocks all stages incl. `ts`).
3. The generated runtime implements the spec's state machine: same variables, same action boundaries. Divergence is a defect to report, not a feature.
4. `GET /api/render/ts/source/:run_id` must return persisted source — no hidden regeneration.

## Anti-Patterns (Reject)
- Editing generated TS to "fix" behavior that contradicts the TLA+ spec — fix the spec, re-verify, regenerate.
- Swallowing `tsc`/harness failures to present a green tab.
- Adding runtime features with no counterpart in the spec's actions.

## Verification
- `node --test test/test-ts-compiler.js`
- `node --test test/test-e2e-full-pipeline.js` — end-to-end idea→TS
- `curl -s http://localhost:3333/api/render/ts/status`

Attribution

DylanCkawalecDylanCkawalec
View sourceMore from DylanCkawalec →
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

Screen Reader Testing

Practical guide to testing web applications with screen readers for comprehensive accessibility validation.

393431 votes

Python Testing

使用pytest、TDD方法、夹具、模拟、参数化和覆盖率要求的Python测试策略。

2456590 votes

Springboot Tdd

使用JUnit 5、Mockito、MockMvc、Testcontainers和JaCoCo进行Spring Boot的测试驱动开发。适用于添加功能、修复错误或重构时。

2456590 votes

Tdd Workflow

在编写新功能、修复错误或重构代码时使用此技能。强制执行测试驱动开发,包含单元测试、集成测试和端到端测试,覆盖率超过80%。

2456590 votes

Eval Harness

克劳德代码会话的正式评估框架,实施评估驱动开发(EDD)原则

2456590 votes
View all in testing →