subagents-orchestration-guide

Guides subagent coordination through implementation workflows. Use when orchestrating multiple agents, managing workflow phases, or determining autonomous execution mode.

Quality

92%

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

Quality

Content

85%

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

A highly actionable, well-sequenced orchestration guide with explicit feedback loops and clean one-level-deep reference splitting. Its only weakness is conciseness: at 417 lines, several structured-response and table sections could be tightened without losing clarity.

Suggestions

Trim the Structured Response Specification block: several field enumerations repeat details already implied by the handoff contracts and could be condensed to the decision-relevant fields only.

Collapse the Scale Determination footnotes (※1/※2/※3) into inline cells or a single compact legend to reduce table overhead.

Move the dense per-agent Call Example prompts into a single table or a references file so the main flow stays lean.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient — tables, prompt templates, and a Mermaid diagram carry dense information without explaining concepts Claude already knows — but at 417 lines some structured-response spec blocks and the scale-table footnotes could be tightened, so it lands at the 'mostly efficient but could be tighter' level-2 anchor rather than the lean level-3 example.	2 / 3
Actionability	Copy-paste-ready guidance throughout — Agent tool call examples with literal subagent_type/description/prompt strings, a permitted-tools table, and explicit JSON handoff contracts — matching the fully-executable level-3 anchor rather than the pseudocode level-2 example.	3 / 3
Workflow Clarity	Per-scale planning chains, a Mermaid autonomous-execution diagram, an explicit stop-points table, and feedback loops (work-plan self-heal on needs_revision, re-run both verifiers after a fix cycle, stub_detected routing back to task-executor) match the clear-sequence-with-validation level-3 anchor.	3 / 3
Progressive Disclosure	The fullstack multi-layer flow is split to references/monorepo-flow.md (a real file, clearly signaled at lines 238, 383, 417, one level deep and back-referencing ../SKILL.md), while the main guide stays an organized overview — matching the well-signaled one-level-deep level-3 anchor.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 well-formed description: third-person voice, concrete actions, explicit "Use when" trigger guidance, and a clear niche that minimizes conflict risk. It hits the top anchor on every dimension with no over-claims or padding.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — "Guides subagent coordination through implementation workflows" plus "orchestrating multiple agents, managing workflow phases, or determining autonomous execution mode" — matching the level-3 anchor rather than the single-domain level-2 example.	3 / 3
Completeness	Explicitly answers both what ("Guides subagent coordination through implementation workflows") and when via a "Use when..." clause, matching the level-3 anchor rather than the what-only level-2 example.	3 / 3
Trigger Term Quality	"orchestrating multiple agents", "workflow phases", and "autonomous execution mode" are natural terms a user would actually say, giving good coverage rather than the partial level-2 set.	3 / 3
Distinctiveness Conflict Risk	The subagent-orchestration niche with distinct triggers (orchestrating agents, workflow phases, autonomous mode) is unlikely to fire for unrelated skills, matching the clear-niche level-3 anchor.	3 / 3
	Total	12 / 12 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: shinpr/claude-code-workflows
Path: skills/subagents-orchestration-guide/SKILL.md
Commit: 56ab6c1

Reviewed: 4 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.