oma-orchestrator

Automated multi-agent orchestrator that spawns CLI subagents in parallel, coordinates via MCP Memory, and monitors progress. Use for orchestration, parallel execution, and automated multi-agent workflows.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/oma-orchestrator/SKILL.md

Quality

Content

70%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.

A well-sequenced, validation-rich orchestration workflow with concrete commands and a strong review loop, undermined by redundant restatements of the same flow and a large share of broken/missing reference files in the bundle. Actionability and workflow clarity are high; conciseness and progressive disclosure need work.

Suggestions

Collapse the redundant Structural Flow, Workflow Phases, and Loop Flow sections into a single canonical sequence to remove repetition.

Restore or create the missing referenced files (resources/subagent-prompt-template.md, resources/memory-schema.md, config/cli-config.yaml, templates/, ../_shared/core/*, orchestrate.md) so inline 'See X' navigation resolves.

Move the full memory-config JSON, retry logic, and Clarification Debt protocol into separate reference files and keep SKILL.md as an overview.

Dimension	Reasoning	Score
Conciseness	Dense operational detail with no basic-concept padding, but the same flow is restated across Structural Flow, Workflow Phases, and Loop Flow, and the exposed_skill_set/domain-gate is explained three times, so it could be tightened.	3 / 5
Actionability	Provides concrete executable commands ('oma agent:spawn ...', 'oma verify ... --json') and a copy-paste memory-config JSON plus concrete file-ownership and loop-limit tables, with minor gaps from placeholder-heavy commands and a missing orchestrate.md reference.	4 / 5
Workflow Clarity	Phases 1-5, explicit scenes, conditional transitions, and a checkpoint-rich review loop ([1] self-check -> [2] verify -> [3] cross-review) with FAIL->feedback->retry, loop-limit and termination tables give clear sequence, validation, and feedback loops for this batch operation.	5 / 5
Progressive Disclosure	Good section structure and inline 'See X' signals exist, but substantial content is inlined (memory-config JSON, full retry and CD-monitoring protocols) and most referenced paths are absent from the bundle (only scripts/*.sh exist; resources/, config/, templates/, ../_shared/, and orchestrate.md are missing).	3 / 5
	Total	15 / 20 Passed

Description

83%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, third-person description that answers both 'what' and 'when' with concrete actions and an explicit Use-for trigger clause. Keyword coverage is good but could include more natural synonyms, and triggers overlap slightly with sibling coordination skills.

Suggestions

Add natural user phrasings like 'run in parallel' or 'automate execution' alongside the existing trigger terms.

Mention task decomposition or verification/retry in the description to round out capability coverage.

Sharpen the Use-for clause to differentiate from oma-coordination (e.g., emphasize fully automated end-to-end vs. manual step-by-step).

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('spawns CLI subagents in parallel', 'coordinates via MCP Memory', 'monitors progress'), but omits decomposition/verification/retry that the body covers, so minor gaps remain.	4 / 5
Completeness	Explicitly states what it does and follows with a concrete 'Use for orchestration, parallel execution, and automated multi-agent workflows' trigger clause.	5 / 5
Trigger Term Quality	'orchestration, parallel execution, and automated multi-agent workflows' gives good keyword coverage, but lacks common natural phrasings a user would say like 'run in parallel' or 'automate'.	4 / 5
Distinctiveness Conflict Risk	The multi-agent orchestration niche is mostly distinct, but 'parallel execution' and 'automated multi-agent workflows' carry minor overlap risk with the sibling oma-coordination skill.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: first-fluke/oh-my-agent
Path: .agents/skills/oma-orchestrator/SKILL.md
Commit: 032c988

Reviewed: 2 days 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.