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

Oma Bootstrap

ASecurity

Install or verify the oma CLI and its runtimes (bun, uv, serena) before any oma-* skill, agent, or workflow runs an `oma` command. Use when `oma` is missing from PATH, when a skill says to run `oma ...` and the shell reports "command not found", or on the first task in a fresh Cursor or Grok Bot workspace.

1,336 stars
0 votes
0 copies
0 views
Added 10/6/2026
ai-agentsshellbashgit

Works with

cursorclimcp

Security Analysis

A96/100
mediumUses curl or wget to download content

Pro shows the line behind each finding and how to fix it

Scanned 10/6/2026

$npx -y skills add first-fluke/oh-my-agent --skill oma-bootstrap --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Oma Bootstrap?

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

Security grade badge for Oma Bootstrap
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/first-fluke-oma-bootstrap/badge)](https://www.skillsdirectory.com/skills/first-fluke-oma-bootstrap)

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: oma-bootstrap
description: Install or verify the oma CLI and its runtimes (bun, uv, serena) before any oma-* skill, agent, or workflow runs an `oma` command. Use when `oma` is missing from PATH, when a skill says to run `oma ...` and the shell reports "command not found", or on the first task in a fresh Cursor or Grok Bot workspace.
---

# oma bootstrap

The oma-* skills in this plugin describe *what* to do. Several of them delegate
the mechanics to the `oma` CLI (`oma agent spawn`, `oma market run`,
`oma recap`, `oma hook run`, `oma doctor`), and code search expects the
Serena MCP binary. Marketplace installs ship the skill text, not the binaries,
so a fresh workspace may have neither.

## When to run

- A skill instruction contains an `oma ...` command and `command -v oma` is empty.
- The shell reports `oma: command not found` or `serena: command not found`.
- The workspace has no `.agents/` directory and a skill needs project state
  (`.agents/state/`, `.agents/results/`, `oma-config.yaml`).

Skip this skill when `oma --version` already prints a version.

## Steps

Run from the repository root. Every step is idempotent; rerunning is safe.

1. Check: `command -v oma && oma --version`. If both succeed, stop here.
2. Provision the runtimes with the official installer in non-interactive
   mode. It installs bun, uv, serena-agent, and cue when missing, and
   `OMA_INSTALL_NO_RUN=1` skips the interactive setup it would otherwise
   launch at the end:

   ```bash
   curl -fsSL https://raw.githubusercontent.com/first-fluke/oh-my-agent/main/cli/install.sh \
     | OMA_INSTALL_NO_RUN=1 bash
   export PATH="$HOME/.bun/bin:$HOME/.local/bin:$PATH"
   ```

   Without `curl`, use `wget -qO-` in its place. Each dependency is
   best-effort: the installer warns and continues when one fails.

3. Install the CLI as a persistent global binary (skills call bare `oma`):

   ```bash
   bun install --global oh-my-agent
   ```

4. Wire the project non-interactively. This creates `.agents/` with the
   default preset and leaves existing files untouched:

   ```bash
   oma install --yes
   ```

5. Verify: `oma doctor`. It reports whether `serena` is on PATH and whether
   the project is registered. Report any warning before continuing with the
   original task.

## Rules

- Ask before `oma install --yes` when the repository is not yours or when
  `.agents/` already exists with local changes.
- Do not fall back to re-implementing an `oma` command by hand. If the CLI
  cannot be installed, say so and complete only the parts of the task that do
  not need it.
- Do not run the installer without `OMA_INSTALL_NO_RUN=1` in a headless Bot:
  the interactive setup reads from `/dev/tty` and hangs.
- If `serena` is still missing after step 2, run
  `uv tool install -p 3.13 serena-agent@latest --prerelease=allow` once, then
  `uv tool update-shell`.

Attribution

first-flukefirst-fluke
View sourceSee grades on GitHubMore from first-fluke →
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', ...

698621 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 →