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
  • 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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Build

ASecurity

OMP-only — grill then validate spec, then plan→impl→PR→review→reviewed→watch merge. Not host /dev.

9 stars
0 votes
0 copies
0 views
Added 9/23/2026
developmentjavascriptjavanodeapisecurity

Works with

api

Security Analysis

A100/100

Scanned 9/23/2026

Install to Claude Code

$npx -y skills add Roxabi/roxabi-plugins --skill build --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Build?

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

Security grade badge for Build
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/roxabi-build/badge)](https://www.skillsdirectory.com/skills/roxabi-build)

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

Download with Pro
Files
SKILL.md
---
name: build
disable-model-invocation: true
argument-hint: '[#N | --spec <path>]'
description: OMP-only — grill then validate spec, then plan→impl→PR→review→reviewed→watch merge. Not host /dev.
version: 0.3.0
---

# Build

One cycle in this session. Grill and spec stay here (HITL). `run()` starts at plan.

`agent()` has no `cwd`. Isolation apply hits **session HEAD**. Implement never runs on the principal checkout.

## 1. Be in ω

Done when this dir is a worktree and `HEAD` is `<type>/<N>-<slug>`.

If not: tell the user to run `omp-wt` from the principal and stop. Do not grill. Do not implement.

## 2. Load the spec

Path: `--spec` in `$ARGUMENTS`, else `artifacts/specs/{N}-*-spec.md`.

If frontmatter `status: validated` → skip to 4.

## 3. Grill then spec

Read `skill://grilling` if it exists. Otherwise: one **frontier** per round — numbered questions, each with a recommended answer — then wait.

Subject = spec TL;DR, else issue title, else `$ARGUMENTS`.

Domain only: TL;DR, data model, acceptance, out of scope, invariants, CONTEXT terms. No stack, files, or API shapes.

Write `artifacts/specs/{N}-{slug}-spec.md` to `skill://build/SPEC.md`. Keep `issue:` and the filename slug. Set `status: draft`.

Done when that file has every required section and `status: draft`.

Ask: « Spec prêt — tape `validated` pour lancer le plan. »

Stop. Wait. Do not call `run()` until the user says `validated` (or an equivalent explicit confirm).

On confirm: set `status: validated`. Done when frontmatter is `validated`.

## 4. Plan onward

```javascript
const { run } = await import(`${env('HOME')}/.omp/plugins/node_modules/omp-build/skills/build/workflow.js`)
const result = await run({ issue, specPath, cwd })
```

| `result.status` | Action |
|---|---|
| `need-relaunch` | `omp --cwd <result.worktree>` then `/build #N`. Do not implement here. |
| `red` | Stop. Show review or land blocker (`reason`: ci-failed\|ci-skipped\|no-required-checks\|auto-merge-failed\|closed\|timeout). Leave the worktree. |
| `green` | PR merged after required status checks succeed; `reviewed` label triggers auto-merge, not the ruleset gate. Print `result.cleanup` (remove ω from the principal). Never delete cwd from inside it. |

- Grill in this turn. Do not Skill() `grill-me`.
- Do not Skill() dev-core children.
- Do not `pipeline()` the SDLC chain.
- Review = sibling `reviewer` + `security-reviewer`. No nested `task`.

Attribution

RoxabiRoxabi
View sourceMore from Roxabi →
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

Browser Extension Developer

Use this skill when developing or maintaining browser extension code in the `browser/` directory, including Chrome/Firefox/Edge compatibility, content scripts, background scripts, or i18n updates.

284072 votes

Seo Optimizer

SEO optimization with keyword analysis, readability assessment, technical validation, content quality. Use for search rankings, blog posts, content audits, or encountering keyword density, readability scores, meta tags, schema markup errors.

2192 votes

Google Official Seo Guide

Official Google SEO guide covering search optimization, best practices, Search Console, crawling, indexing, and improving website search visibility based on official Google documentation

1862 votes

Tanstack Start

Build a full-stack TanStack Start app on Cloudflare Workers from scratch — SSR, file-based routing, server functions, D1+Drizzle, better-auth, Tailwind v4+shadcn/ui. Use whenever the user mentions TanStack Start, asks to scaffold a full-stack Cloudflare app with SSR, wants an SSR dashboard, or asks for a React 19 + Cloudflare Workers app with file-based routing and server functions — even if they don't name TanStack Start specifically. No template repo — Claude generates every file fresh per ...

9881 votes

Pentest

PTES-aligned adversarial security audit for backend, frontend, and mobile applications. Produces a CVSS-scored Hacker Report with verified PoCs and phased remediation.

5491 votes
View all in development →