CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

The content is a well-sequenced, highly actionable bootstrap runbook: executable commands with fallbacks, a failure/recovery table, and validation checkpoints throughout. Its weaknesses are repetition of two core guardrails across sections, the missing concrete Windows PowerShell command, and references that point outside the skill bundle.

Suggestions

State the check-independently and preserve-existing-installation guardrails once each (e.g., in the Guardrails section) and remove the restatements in Scheduling, Structural Flow, and the Canonical command path to cut roughly 10 lines of repetition.

Add the actual PowerShell invocation for the Windows branch (e.g., the equivalent of `OMA_INSTALL_NO_RUN=1` with install.ps1) or explicitly instruct running the referenced install.ps1, so the Windows path is as executable as the Linux/macOS one.

Briefly note what to look for in `oma doctor --json` output (which fields indicate provider or project readiness) so the final validation step is actionable rather than just "inspect".

DimensionReasoningScore

Conciseness

The body is operational throughout with no explanations of concepts Claude already knows, but the guardrails "check CLI/providers independently" (e.g., "Do not stop after the CLI check", "plugin import alone does not verify them") and "preserve existing installations" are each restated 3-4 times across Scheduling, Structural Flow, and Guardrails, which could be trimmed.

4 / 5

Actionability

Mostly executable guidance with copy-paste commands (curl|bash with OMA_INSTALL_NO_RUN=1, PATH export, wget fallback, `uv tool install -p 3.13 serena-agent@latest --prerelease=allow`, `env -u OMA_YES CI=1 oma install`), but the Windows path gives no actual PowerShell command and "Inspect `oma doctor --json`" offers no interpretation of the output, leaving minor gaps that keep it below fully executable.

4 / 5

Workflow Clarity

The five-step canonical path is clearly sequenced with explicit validation checkpoints (recheck after install, `oma doctor --json` at completion) and a failure/recovery table mapping each failure to a concrete recovery command — a genuine feedback loop — plus careful guardrails around the file-overwriting `oma install`, matching the 5 anchor.

5 / 5

Progressive Disclosure

Good structure with clear section headers and two clearly signaled one-level-deep references ([Linux/macOS bootstrap](../../../cli/install.sh), [Windows bootstrap](../../../cli/install.ps1)), but the body exceeds 50 lines, the references point to plugin-root installer scripts rather than bundled reference files, and the Scheduling metadata section is boilerplate-like, leaving minor organization gaps.

4 / 5

Total

17

/

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: it states concrete capabilities with named runtimes, provides an explicit multi-condition "Use when" clause anchored to the exact shell error users will see, and occupies a clearly distinct niche. Only minor headroom remains in trigger synonym coverage and breadth of action verbs.

DimensionReasoningScore

Specificity

"Install or verify the oma CLI and its runtimes (bun, uv, serena)" names two concrete actions and the exact runtime components, which is more specific than the 3 anchor's generic action pair but lacks the several-action coverage of the 5 anchor.

4 / 5

Completeness

The description explicitly states what it does ("Install or verify the oma CLI and its runtimes") and when to use it via an explicit "Use when" clause with three concrete trigger phrases, exactly matching the 5 anchor; it is not the 4 anchor because the when-clause is already fully explicit and specific.

5 / 5

Trigger Term Quality

Triggers include the exact shell error "command not found", "oma is missing from PATH", and "first task in a fresh Cursor or Grok Bot workspace" — natural phrases users would encounter — but common variations like "oma not installed" or "set up oma" are absent, so it falls just short of comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The scope is tightly pinned to the oma CLI, oma-* skills, and oma-specific error conditions ("oma: command not found"), giving it a clear niche with distinct triggers and minimal conflict risk with any other skill.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 suspicious

Warning

Total

15

/

16

Passed

Repository

first-fluke/oh-my-agent

Path

.cursor-plugin/skills/oma-bootstrap/SKILL.md

Reviewed

Table of Contents

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.