CtrlK
BlogDocsLog inGet started
Tessl Logo

oma-coordination

Coordinate assigned specialist tasks and handoffs manually. Use when supervising a multi-agent project step by step.

56

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

The canonical home for this skill is oma-coordination in first-fluke/oh-my-agent

SKILL.md
Quality
Evals
Security

Quality

Content

63%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 delivers genuinely actionable multi-agent coordination guidance with a clear sequenced workflow and validation checkpoints. Its main weaknesses are redundancy (the same spawn/parallelism rules repeated many times) and a dangling References section that points at files not present in the bundle.

Suggestions

Consolidate the duplicated parallel-spawn guidance and command examples into one place (e.g., Step 2) and have other sections reference it, cutting significant tokens.

Fix the '## References' section: either list the actual reference files there or remove the empty heading, and inline the essential content of `../_shared/core/code-intelligence.md` or ship it as a bundle file.

Make failure-recovery steps executable (e.g., the exact command to inspect progress files or re-spawn an agent after QA finds CRITICAL issues) rather than high-level directives.

DimensionReasoningScore

Conciseness

Parallel-spawn guidance is repeated in about five places (Control-flow features, ACT scene, Canonical command path, Guardrail 2, and a duplicated command block in Step 2), and template tables ('SSL primitive', 'Resource scope') add tokens without actionable value; individual sections are terse, but the structural redundancy could be consolidated.

3 / 5

Actionability

Provides concrete, complete `oma agent spawn` command lines with flags and a dispatch-resolution procedure, plus the progress-file naming convention `progress-{agent}[-{sessionId}].md`; minor gaps remain, such as unspecified prompt-file contents and the unnamed 'memory read tool'.

4 / 5

Workflow Clarity

A clear four-step sequence (Plan, Spawn, Monitor, QA) with an explicit VERIFY checkpoint, contract-alignment validation, failure/recovery guidance, and a QA feedback loop (re-spawn on CRITICAL); recovery steps are high-level rather than executable, keeping it below the top anchor.

4 / 5

Progressive Disclosure

Section structure is present, but no bundle files exist, the trailing '## References' section is empty, and both inline citations point to `../_shared/core/code-intelligence.md` outside the skill directory, so reference navigation is broken or unverifiable.

3 / 5

Total

14

/

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.

A concise, correctly structured description with an explicit 'Use when' clause and third-person voice, but its capability list and trigger vocabulary are thin relative to what the skill actually does. It reads closer to a minimal pass than a strong exemplar.

Suggestions

Enumerate the core capabilities in the description (e.g., decompose tasks with PM, spawn agents in parallel, monitor progress files, align API/data contracts, run QA) to lift specificity and completeness.

Add natural trigger variations users would actually say, such as 'orchestrate', 'delegate to specialist agents', or 'coordinate full-stack/mobile work'.

Briefly state the boundary with the automated orchestrator skill in the description to sharpen distinctiveness.

DimensionReasoningScore

Specificity

Names the domain and roughly two concrete actions ('Coordinate assigned specialist tasks and handoffs manually', 'supervising a multi-agent project step by step'), but does not enumerate the several specific actions the skill body actually covers (spawning, monitoring, contract alignment, QA).

3 / 5

Completeness

Both a clear 'what' (coordinate specialist tasks and handoffs manually) and an explicit 'when' ('Use when supervising a multi-agent project step by step') are present, but the 'when' clause could be more specific — it omits the multi-domain complexity triggers described in the body.

4 / 5

Trigger Term Quality

Relevant natural terms are present ('multi-agent', 'supervising', 'step by step', 'handoffs') but common variations a user might say — 'orchestrate', 'delegate', 'spawn agents' — are missing, matching the 'some relevant keywords but missing variations' anchor.

3 / 5

Distinctiveness Conflict Risk

The manual step-by-step supervision niche is fairly distinct and implicitly contrasted with automated orchestration, with only minor overlap risk against a sibling orchestrator skill.

4 / 5

Total

14

/

20

Passed

Validation

100%

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
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.