oma-coordination

Guide for coordinating PM, Frontend, Backend, Mobile, and QA agents on complex projects via CLI. Use for manual step-by-step coordination and workflow guidance.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/runs/oma/.agents/skills/oma-coordination/SKILL.md

Quality

Content

77%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 body is well-structured with executable commands, clear sequencing, and explicit validation/feedback loops for multi-agent spawning. Its main weakness is progressive disclosure: it references a resources/examples.md file that is not present and inlines reference-style content.

Suggestions

Add the referenced resources/examples.md file (or remove the reference) so navigation links resolve to real bundle content.

Move the SSL-primitive action tables and resource-scope tables into a separate reference file, keeping SKILL.md as a lean overview with one-level-deep links.

Trim redundancy between the Scheduling, Scenes, Guardrails, and Workflow sections to reduce repeated coordination guidance.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with bullet/table structure and no concept over-explanation, though the Scheduling, Scenes, Guardrails, and Workflow sections repeat coordination guidance that could be tightened.	4 / 5
Actionability	Provides concrete executable commands (oma agent:spawn ... -w ./backend &) and specific files (progress-{agent}.md), but a few steps stay high-level and reference a spawn-agent.sh that is not part of the bundle.	4 / 5
Workflow Clarity	Clear sequenced 4-step Workflow plus Scenes with explicit validation checkpoints (contract alignment verification, QA re-spawn on CRITICAL) and feedback loops for the batch-spawn operation.	5 / 5
Progressive Disclosure	Structure is present and references one file (resources/examples.md), but that referenced file does not exist in the bundle and a fair amount of content (SSL-primitive tables, guardrails) is inlined that could live in separate files.	3 / 5
	Total	16 / 20 Passed

Description

62%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.

The description clearly states what the skill does and when to use it, with a well-scoped niche. It is held back by generic action language and trigger terms that lack the natural phrasings and synonyms users would actually say.

Suggestions

Add concrete trigger phrases users would naturally say, e.g. 'Use when the user asks to coordinate multiple agents, orchestrate full-stack work, or sequence PM/frontend/backend/mobile/QA handoffs'.

Replace generic actions ('Guide', 'workflow guidance') with specific capabilities like 'decompose tasks with PM, spawn agents by priority tier, and align API/data contracts'.

Include synonyms and concrete terms (e.g. 'multi-agent', 'agent spawning', 'CLI coordination') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (coordinating PM/Frontend/Backend/Mobile/QA agents via CLI) and 1-2 concrete actions (manual coordination, workflow guidance), but the actions remain generic and not comprehensive.	3 / 5
Completeness	Explicitly answers both what (coordinate five specialist agents via CLI) and when ('Use for manual step-by-step coordination and workflow guidance'), though the when clause could be more specific with concrete triggers.	4 / 5
Trigger Term Quality	Includes some relevant natural keywords ('coordination', 'workflow guidance', 'step-by-step') but misses common variations, synonyms, or concrete trigger phrases a user would naturally say.	3 / 5
Distinctiveness Conflict Risk	The niche (multi-agent coordination across these specific five roles) is clearly distinct from generic skills; minor overlap risk only via the broad phrase 'workflow guidance'.	4 / 5
	Total	14 / 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: benchmarks/runs/oma/.agents/skills/oma-coordination/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.