oma-bootstrap

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.

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

100%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exemplary single-purpose bootstrap skill: fully executable commands, a clearly sequenced idempotent workflow with an explicit verification step and failure-handling rules, and lean content with no filler. Safety-relevant edge cases (headless /dev/tty hang, non-owned repos, pre-existing .agents/ state) are called out in a dedicated Rules section.

Dimension	Reasoning	Score
Conciseness	Every section earns its place: a brief project-specific rationale, a tight "When to run" list, five numbered steps with commands, and four operational rules. There is no explanation of concepts Claude already knows and no padding, matching the lean-and-efficient anchor.	5 / 5
Actionability	All guidance is copy-paste-ready and executable: `command -v oma && oma --version`, the curl-piped installer with `OMA_INSTALL_NO_RUN=1`, `export PATH=...`, `bun install --global oh-my-agent`, `oma install --yes`, and `oma doctor`, plus concrete fallbacks (wget, and `uv tool install -p 3.13 serena-agent@latest --prerelease=allow` for a missing serena).	5 / 5
Workflow Clarity	The five steps are clearly sequenced with an early-exit check in step 1, stated idempotency ("Every step is idempotent; rerunning is safe"), an explicit verification checkpoint (`oma doctor`, with instructions to report warnings before continuing), and failure-handling rules covering a hung interactive installer and a missing CLI. This matches the anchor requiring explicit validation and error-recovery guidance.	5 / 5
Progressive Disclosure	The skill is self-contained with no bundle files present or needed, and content is well organized into "When to run", "Steps", and "Rules" sections with no buried references. Per the rubric's simple-skill guidance, a short skill with no need for external references scores 5 on well-organized sections alone.	5 / 5
	Total	20 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third-person, concrete, and compact, with an explicit "Use when" clause covering missing PATH entry, the literal "command not found" error, and fresh-workspace scenarios. Its only weakness is moderate rather than comprehensive action coverage in the what-clause.

Dimension	Reasoning	Score
Specificity	"Install or verify the oma CLI and its runtimes (bun, uv, serena)" names concrete actions and specific components, matching the several-specific-actions anchor; it falls short of a 5 because the action list (install, verify) is narrower than the comprehensive multi-action example.	4 / 5
Completeness	It explicitly answers both what ("Install or verify the oma CLI and its runtimes") and when, with a "Use when" clause listing three concrete trigger conditions including the exact shell error string; this matches the top anchor exactly.	5 / 5
Trigger Term Quality	Triggers like "command not found", "missing from PATH", and "first task in a fresh Cursor or Grok Bot workspace" are natural phrases users and shells actually produce, giving good keyword coverage; a few natural synonyms and variations are missing, so it does not reach the comprehensive 5 anchor.	4 / 5
Distinctiveness Conflict Risk	The niche is unambiguous — bootstrapping the oma CLI for oma-* skills — and triggers are scoped to the `oma` command specifically, so conflict with other skills is minimal despite "command not found" being generically worded.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: first-fluke/oh-my-agent
Path: .cursor-plugin/skills/oma-bootstrap/SKILL.md
Commit: 0e87272

Reviewed: 18 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.