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

72%

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 ./benchmarks/runs/oma/.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-structured, actionable orchestrator skill with an excellent validation/feedback workflow, undermined by triplicated pipeline descriptions and a large set of referenced files that do not exist in the bundle.

Suggestions

Consolidate the three overlapping pipeline descriptions (Scenes, Workflow Phases, Entry/Transitions) into a single canonical sequence to remove redundancy.

Create the referenced bundle files (resources/subagent-prompt-template.md, resources/memory-schema.md, config/cli-config.yaml, templates/) or remove the broken references from the References section.

Move the Clarification Debt monitoring and full Agent-to-Agent Review Loop details into separate reference files to keep SKILL.md a lean overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with useful tables and flow diagrams, but the pipeline is described three times (Structural Flow/Scenes, Workflow Phases, Entry/Transitions) and includes some justifying asides ('ref: Anthropic harness design research') that could be trimmed.	3 / 5
Actionability	Provides concrete, copy-pasteable commands (`oma agent:spawn ...`, `oma verify ... --json`, native executor paths) and a review-feedback template, though several commands rely on placeholders the user must fill.	4 / 5
Workflow Clarity	The review loop is explicitly sequenced with validation checkpoints (mechanical self-check -> verify -> cross-review) and feedback loops (FAIL -> fix -> back to [1]), plus a loop-limits table and retry/escalation rules.	5 / 5
Progressive Disclosure	References are clearly signaled in a dedicated section, but only scripts/ actually exists as a bundle — resources/, templates/, config/, and ../_shared/core/* are broken links — and substantial inline content (CD monitoring, full review protocol, memory config) could live in separate files.	3 / 5
	Total	15 / 20 Passed

Description

75%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 solid, specific description that clearly conveys both capability and use cases in third person. It is concise without fluff, with only minor gaps in trigger-phrase naturalness and completeness.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — 'spawns CLI subagents in parallel', 'coordinates via MCP Memory', 'monitors progress' — giving multiple specific capabilities, though coverage is not fully comprehensive.	4 / 5
Completeness	It states both what it does and when to use it ('Use for orchestration, parallel execution...'), but the 'when' lists use-categories rather than concrete user-mentionable trigger phrases, keeping it just below a 5.	4 / 5
Trigger Term Quality	'Use for orchestration, parallel execution, and automated multi-agent workflows' provides good keyword coverage, but a few natural user phrases (e.g. 'run it automatically', 'automate') are missing.	4 / 5
Distinctiveness Conflict Risk	The CLI-subagent + MCP Memory coordination niche is mostly distinct, though there is minor overlap risk with closely related coordination/orchestration skills.	4 / 5
	Total	16 / 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: benchmarks/runs/oma/.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.