coordinator-mode

Advanced multi-agent orchestration with parallel workers, synthesis protocols, and coordinator lifecycle. Use when complex tasks require multiple agents working in parallel with intelligent result synthesis.

Quality

86%

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

Quality

Content

88%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, highly actionable orchestration protocol with a clear validated lifecycle and copy-paste prompt templates. Its main weaknesses are mild redundancy across the anti-patterns/best-practices sections and no progressive disclosure into reference files for a 200-line skill.

Suggestions

Trim redundancy between the Anti-Patterns table, Best Practices list, and the earlier lifecycle/golden-rule sections to tighten token efficiency.

Move the prompt templates and/or the full Synthesis Protocol markdown block into a references/ file (e.g., references/worker-prompts.md) linked from the body, improving progressive disclosure for this 200-line skill.

Consolidate the Fork Semantics, Continue-vs-Spawn, and Best Practices decision guidance into a single navigation section to reduce scattered restatements.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's competence (fork rules, don't-peek/don't-race directives are non-obvious and earn their place), but the anti-patterns table and best-practices list restate points already made in the lifecycle and golden-rule sections, giving minor over-explanation that could be trimmed.	4 / 5
Actionability	Copy-paste-ready prompt templates for Research/Implementation/Verification workers and a fully concrete golden-rule example (file:line, exact code change) cover the common cases with executable, specific guidance.	5 / 5
Workflow Clarity	The DECOMPOSE→CLASSIFY→DISPATCH→MONITOR→SYNTHESIZE→VERIFY lifecycle is a clear sequence with an explicit VERIFY validation step, error-recovery feedback (continue vs spawn on worker failure), and checklists (anti-patterns, best practices, decision tables).	5 / 5
Progressive Disclosure	Well-organized with clear section headers and tables in a self-contained single file, but at ~200 lines with no external references, content like prompt templates or the synthesis protocol could be split into one-level-deep reference files for easier navigation.	4 / 5
	Total	18 / 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 description that clearly states both capability and trigger conditions in third-person voice. It enumerates several specific components but leans slightly conceptual, and could broaden trigger synonyms and sharpen distinctiveness.

Suggestions

Add natural trigger synonyms users would say — 'coordinate', 'dispatch agents', 'fan out', '/coordinate', '/orchestrate' — to broaden keyword coverage.

Reframe 'synthesis protocols' and 'coordinator lifecycle' as more concrete user-facing actions (e.g., 'dispatch parallel workers and merge their results') to lift specificity.

Tighten the 'when' clause with a more distinctive trigger than the broad 'complex tasks' to reduce overlap risk with general agent usage.

Dimension	Reasoning	Score
Specificity	Lists several specific capabilities — 'multi-agent orchestration', 'parallel workers', 'synthesis protocols', 'coordinator lifecycle' — but these are conceptual components rather than concrete user-facing actions like extract/fill/merge, leaving minor gaps in coverage.	4 / 5
Completeness	Explicitly answers both what ('Advanced multi-agent orchestration with parallel workers, synthesis protocols, and coordinator lifecycle') and when ('Use when complex tasks require multiple agents working in parallel with intelligent result synthesis') with a concrete trigger phrase.	5 / 5
Trigger Term Quality	Good natural keywords ('multi-agent orchestration', 'parallel workers', 'multiple agents working in parallel') that an advanced user would say, but missing common synonyms like 'coordinate', 'dispatch', or 'fan out'.	4 / 5
Distinctiveness Conflict Risk	The 'multi-agent orchestration' niche is mostly distinct with clear triggers, but 'complex tasks require multiple agents' is somewhat broad and could minor-overlap with general Agent-tool usage.	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: vudovn/ag-kit
Path: .agents/skills/coordinator-mode/SKILL.md
Commit: 211561c

Reviewed: 24 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.