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

76%

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 ./.agents/skills/coordinator-mode/SKILL.md

Quality

Content

77%

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

The content is highly actionable with a clear, validated lifecycle workflow and concrete templates. Its weaknesses are repetition across sections and a fully monolithic single-file structure with no progressive disclosure to supporting files.

Suggestions

Deduplicate the Anti-Patterns and Best Practices sections against the earlier Worker Prompt Guide and Concurrency Rules, or collapse one into a pointer to the other.

Split the detailed prompt templates and synthesis protocol into a referenced file (e.g., templates.md) so SKILL.md stays a lean overview with one-level-deep signaled references.

Dimension	Reasoning	Score
Conciseness	The body is mostly high-signal (tables, templates, rules), but the Anti-Patterns table and Best Practices list repeat guidance already given in the Worker Prompt Writing Guide and Concurrency Rules, fitting the 2-anchor (mostly efficient but could be tightened) rather than the lean 3-anchor where every token earns its place.	2 / 3
Actionability	Concrete fill-in-the-blank worker prompt templates, an explicit WRONG/RIGHT golden-rule example with a real file:line ("src/auth/jwt.ts line 45"), and copy-ready synthesis protocol and decision tables provide fully actionable guidance, matching the 3-anchor; absence of code is not penalized for this instruction-only skill per scoring_notes.	3 / 3
Workflow Clarity	The numbered DECOMPOSE→...→VERIFY lifecycle gives a clear sequence with an explicit VERIFY validation step, the Continue-vs-Spawn table supplies error-recovery feedback loops, and the Anti-Patterns/Best Practices act as checklists, matching the 3-anchor; verification is present so the destructive/batch cap at 2 does not apply.	3 / 3
Progressive Disclosure	The body is well-sectioned internally but is a single ~200-line file with everything inline and no references to separate files, matching the 2-anchor (content that could be separate is inline); it is above the disorganized 1-anchor but lacks the one-level-deep signaled references of the 3-anchor, and no bundle files exist to offset this.	2 / 3
	Total	10 / 12 Passed

Description

75%

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 an explicit trigger clause, and occupies a distinct niche. It is held back from a perfect score by abstract noun-phrase capabilities and some technical jargon in place of natural user keywords.

Suggestions

Replace abstract noun phrases ("synthesis protocols", "coordinator lifecycle") with concrete transitive actions (e.g., "decompose tasks, dispatch parallel workers, synthesize their results").

Add natural user-language trigger terms (e.g., "parallel agents", "fan out work", "orchestrate subagents") alongside the jargon so users' phrasings match.

Dimension	Reasoning	Score
Specificity	Quotes "multi-agent orchestration with parallel workers, synthesis protocols, and coordinator lifecycle" name the domain and several features, but they are abstract noun phrases rather than concrete transitive actions like the rubric's 3-anchor ("Extract text and tables... fill forms, merge documents"); it is above the vague 1-anchor ("Helps with documents").	2 / 3
Completeness	It answers both what ("Advanced multi-agent orchestration...") and when via an explicit "Use when complex tasks require multiple agents working in parallel..." clause, satisfying the 3-anchor and the guideline that an explicit trigger clause is required to exceed 2.	3 / 3
Trigger Term Quality	Phrases like "complex tasks require multiple agents working in parallel" are reasonably natural, but "synthesis protocols" and "coordinator lifecycle" are technical jargon a user would not say, matching the 2-anchor (some relevant keywords, missing common variations) rather than the broad natural-term coverage of the 3-anchor.	2 / 3
Distinctiveness Conflict Risk	Multi-agent orchestration is a clear niche with distinct triggers ("multiple agents working in parallel"), unlikely to fire for single-purpose skills, matching the 3-anchor rather than the overlapping 2-anchor.	3 / 3
	Total	10 / 12 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: 04514f0

Reviewed: about 12 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.