subagents-orchestration-guide
Guides subagent coordination through implementation workflows. Use when orchestrating multiple agents, managing workflow phases, or determining autonomous execution mode.
49
53%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/subagents-orchestration-guide/SKILL.mdQuality
Discovery
67%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 has good structural completeness with an explicit 'Use when' clause covering multiple scenarios, which is its strongest aspect. However, it suffers from somewhat abstract language—terms like 'guides coordination' and 'implementation workflows' lack the concrete specificity that would make it immediately clear what this skill actually does. The trigger terms lean technical and could benefit from more natural language variations.
Suggestions
Add concrete actions that specify what the skill actually does, e.g., 'Assigns tasks to subagents, tracks phase completion, handles inter-agent dependencies, and selects between parallel vs sequential execution modes.'
Include more natural trigger term variations such as 'multi-agent', 'delegate tasks', 'parallel execution', 'agent pipeline', or 'task distribution' to improve keyword coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (subagent coordination, implementation workflows) and some actions (orchestrating, managing workflow phases, determining execution mode), but the actions are fairly abstract rather than concrete. 'Guides subagent coordination' is vague about what specific coordination actions are performed. | 2 / 3 |
Completeness | Clearly answers both what ('Guides subagent coordination through implementation workflows') and when ('Use when orchestrating multiple agents, managing workflow phases, or determining autonomous execution mode'). The explicit 'Use when' clause with multiple trigger scenarios is present. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'subagent', 'agents', 'workflow phases', and 'autonomous execution mode', but these are somewhat technical/jargon-heavy. Users might say 'multi-agent', 'parallel tasks', 'delegate', or 'orchestration' which are missing. The terms present are reasonable but not comprehensive. | 2 / 3 |
Distinctiveness Conflict Risk | The focus on subagent coordination and workflow phases is somewhat distinctive, but terms like 'workflow' and 'orchestrating' could overlap with general task management or pipeline skills. 'Implementation workflows' is broad enough to potentially conflict with build/deploy or project management skills. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
39%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill excels at workflow clarity with well-defined sequences, validation checkpoints, and escalation paths for a complex multi-agent orchestration system. However, it is severely hampered by its monolithic structure — cramming handoff contracts, response schemas, planning flows, and execution details into a single file makes it token-expensive and hard to navigate. The content would benefit enormously from splitting into focused reference files with a lean overview in SKILL.md.
Suggestions
Extract the 'Structured Response Specification' section into a separate reference file (e.g., references/response-schemas.md) and link to it from SKILL.md
Move the 'Handoff Contracts' (HC-01 through HC-06) into a dedicated reference file (e.g., references/handoff-contracts.md) since these are detailed implementation specs, not overview material
Consolidate the planning flow tables and scale determination into a single concise decision table in SKILL.md, moving detailed per-scale flow descriptions to a reference file
Remove the 'Important Constraints' recap section entirely — it explicitly states it repeats content defined above, wasting tokens
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~400+ lines. It over-explains orchestration concepts, includes extensive tables, mermaid diagrams, and detailed handoff contracts that could be split into reference files. Many sections repeat information (e.g., constraints are stated then recapped). The structured response specification section alone is a wall of detail that belongs in a reference file. | 1 / 3 |
Actionability | The skill provides concrete call examples with subagent_type/description/prompt patterns and specific JSON field names to check, but the examples use placeholders rather than fully concrete scenarios. The mermaid diagram and tables give clear structure, but much guidance remains at the 'what to do' level without executable commands beyond git commit references. | 2 / 3 |
Workflow Clarity | The multi-step workflows are exceptionally well-sequenced with explicit stop points, validation checkpoints (document-reviewer before approval, code-verifier post-implementation), feedback loops (stub_detected → re-run task-executor, needs_revision → re-review), and clear escalation paths. The mermaid diagram and per-task 4-step cycle provide unambiguous sequencing with error recovery. | 3 / 3 |
Progressive Disclosure | Despite referencing `references/monorepo-flow.md`, the skill is a monolithic wall of text with nearly all content inline. The structured response specification, handoff contracts, planning flows per scale, and autonomous execution details should be split into separate reference files. No bundle files are provided to support progressive disclosure, and the single reference mentioned is insufficient for this volume of content. | 1 / 3 |
Total | 7 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- shinpr/claude-code-workflows
- Commit
adf2e4d
- 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.