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

70%

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

62%

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

The content excels at workflow clarity with a well-sequenced, validation-checkpointed orchestration loop. Its weaknesses are mild redundancy across overlapping sections and progressive-disclosure gaps where referenced files are missing and detail that belongs in separate files is inlined.

Suggestions

Collapse the redundant pipeline descriptions in Scheduling/Scenes/Workflow Phases into a single canonical sequence to remove ~100 lines of overlap.

Create the referenced bundle files (resources/subagent-prompt-template.md, resources/memory-schema.md, config/cli-config.yaml, templates/) or remove the dangling references so navigation is one level deep and resolvable.

Move the detailed Clarification Debt protocol and full review-loop step details into referenced files, leaving the SKILL.md body as a concise overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and well-structured, but ~300 lines restate the same pipeline across the Scheduling, Scenes, and Workflow Phases sections, plus a duplicated native-dispatch preference, so it could be tightened.	2 / 3
Actionability	Concrete commands and templates are present (oma agent:spawn, oma verify --json, native executor paths, config JSON), but many are placeholder templates rather than copy-paste ready and key referenced artifacts (prompt template, memory schema, config) are not in the bundle.	2 / 3
Workflow Clarity	Provides a clearly sequenced PHASE pipeline with explicit validation checkpoints, a PASS/FAIL review loop with feedback branches, loop-limit and retry tables, and recovery actions — matching the score-3 anchor.	3 / 3
Progressive Disclosure	A References section and real scripts/ bundle exist, but several referenced paths (resources/, config/, templates/, ../_shared/core/*) are missing and substantial detail (review loop, CD protocol) is inlined rather than split out.	2 / 3
	Total	9 / 12 Passed

Description

77%

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 description that states concrete capabilities and includes an explicit use-when clause. It could be improved by broadening natural trigger terms and sharpening distinctiveness to reduce overlap with generic coordination skills.

Suggestions

Broaden trigger terms to include phrasings users actually say, e.g. "run it automatically", "coordinate agents end to end", "automate full-stack work".

Add a distinguishing qualifier to the when-clause (e.g. "when multiple specialist agents must run in parallel with persistent review/remediation") to lower conflict risk with generic coordination skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "spawns CLI subagents in parallel, coordinates via MCP Memory, and monitors progress" — matching the score-3 anchor for several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (spawn/coordinate/monitor) and when ("Use for orchestration, parallel execution, and automated multi-agent workflows"), matching the score-3 anchor with an explicit trigger clause.	3 / 3
Trigger Term Quality	"Use for orchestration, parallel execution, and automated multi-agent workflows" gives some natural keywords, but coverage is narrow and omits common user phrasings like "run it automatically" or "coordinate agents end to end".	2 / 3
Distinctiveness Conflict Risk	The MCP Memory and CLI-subagent framing gives it a niche, but the trigger terms (orchestration, parallel execution) are broad enough to overlap with a generic coordination skill.	2 / 3
	Total	10 / 12 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: 3021301

Reviewed: about 21 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.