subagents-orchestration-guide

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

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/subagents-orchestration-guide/SKILL.md

Quality

Content

73%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 a densely actionable orchestration guide with strong workflow sequencing, explicit validation feedback loops, and concrete handoff contracts. Its main weakness is verbosity from long jargon-heavy sentences that could be tightened for token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient procedural detail without explaining concepts Claude already knows, but many sections are padded with very long compound sentences and dense internal jargon (e.g., 'scopeEvidence.executionRoute.status', 'candidateDecisionPoints') that could be tightened.	3 / 5
Actionability	Concrete handoff contracts (HC-01 through HC-06) name exact fields to pass, the task execution cycle specifies branch-on-result logic, and the commit trailer format is copy-paste ready, with only minor gaps in fully executable examples.	4 / 5
Workflow Clarity	Multi-step flows are explicitly sequenced per scale in tables, a mermaid diagram shows the autonomous cycle, stop points are tabulated, and explicit feedback loops (Commit Boundary Check, Review Resolution, re-run rule) provide validation checkpoints and error recovery.	5 / 5
Progressive Disclosure	Structure is clear with section headers and two well-signaled one-level-deep references (monorepo-flow.md, review-resolution.md) that exist as real files, though the SKILL.md body itself is large with inline detail that could arguably be split further.	4 / 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 cleanly provides both a capability statement and an explicit 'Use when' trigger clause targeting a distinct orchestration niche. It would benefit from more concrete action verbs in the 'what' clause and more natural synonyms in the trigger list.

Suggestions

Replace the abstract 'Guides subagent coordination' with concrete verbs the skill performs (e.g., 'Routes work to named specialists, sequences workflow phases, and manages autonomous execution').

Add natural user-facing synonyms to the trigger clause such as 'coordinating subagents', 'running a multi-agent workflow', or 'deciding when to go autonomous'.

Tighten 'determining autonomous execution mode' to a phrase a user would actually say, e.g., 'deciding whether to run autonomously'.

Dimension	Reasoning	Score
Specificity	The description names the domain ('subagent coordination through implementation workflows') and lists several actions ('orchestrating multiple agents, managing workflow phases, or determining autonomous execution mode'), but the core 'what' ('guides coordination') remains abstract rather than enumerating concrete operations.	3 / 5
Completeness	Both a 'what' ('Guides subagent coordination through implementation workflows') and an explicit 'when' ('Use when orchestrating...') are present, but the 'what' is somewhat generic compared to the concrete trigger list, keeping it just below the top anchor.	4 / 5
Trigger Term Quality	It includes relevant phrases like 'orchestrating multiple agents' and 'managing workflow phases', but 'autonomous execution mode' leans technical and common synonyms/variations a user might naturally say are missing.	3 / 5
Distinctiveness Conflict Risk	The subagent-orchestration niche with triggers like 'autonomous execution mode' is mostly distinct with only minor overlap risk against related workflow skills.	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: shinpr/claude-code-workflows
Path: skills/subagents-orchestration-guide/SKILL.md
Commit: 83cf695

Reviewed: about 23 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.