jbaruch/sub-agent-delegation
Meta-skill: how to pass skills/context to Claude sub-agents that start with fresh context, with documented SDK gotchas.
93
94%
Does it follow best practices?
Impact
92%
1.43xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
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.
This is an excellent skill description that clearly articulates specific capabilities (sub-agent orchestration, skill inheritance, echo-skills handshake), names the target platforms (Claude Code, GitHub Copilot), and provides explicit trigger guidance covering multiple natural use cases. It is concise, uses third-person voice, and occupies a distinct niche that would be easy to disambiguate from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: orchestrating sub-agents across two named platforms, covering inheritance behavior, passing skills explicitly, and the echo-skills validation handshake. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (orchestrate sub-agents, covers inheritance, passing skills, echo-skills handshake) and 'when' with an explicit 'Use when' clause listing four specific trigger scenarios including spawning, delegating, building pipelines, and troubleshooting. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'sub-agents', 'child agents', 'delegating tasks', 'multi-agent pipelines', 'Claude Code', 'GitHub Copilot', 'skills', 'context'. Also covers troubleshooting scenarios which is a natural user need. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: multi-agent orchestration specifically across Claude Code and GitHub Copilot with skill inheritance and validation handshake. The combination of platform-specific sub-agent management and the echo-skills concept makes this unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured skill that addresses a genuinely complex topic (cross-platform sub-agent delegation) with concrete, actionable guidance. Its main strength is the combination of platform-specific detail, executable code examples, and a clear validation protocol. The only weakness is minor verbosity in the Copilot section and some redundancy between prose and the comparison table.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient and covers genuinely non-obvious information (inheritance models, platform differences, validation protocol). However, some sections are slightly verbose — the VS Code Copilot section repeats the context-loss framing, and the cross-platform table partially duplicates prose already stated. The skill could be tightened by ~20% without losing information. | 2 / 3 |
Actionability | Provides fully executable Python code for both AgentDefinition usage and the echo-skills validation handler. The 'How to act' section gives concrete, numbered steps. The cross-platform table gives specific file paths and mechanisms. The #file reference syntax and settings keys are copy-paste ready. | 3 / 3 |
Workflow Clarity | The 'How to act' section provides a clear 4-step sequence with an explicit validation checkpoint (echo-skills handshake with abort-on-mismatch). The validation protocol section includes a complete feedback loop: echo → compare → fail loudly if mismatch. The critical gotcha about `context: fork` adds an important guardrail. | 3 / 3 |
Progressive Disclosure | The skill is well-structured with clear sections (per-platform models, validation protocol, how to act). It references external files appropriately — `scripts/echo_skills.py` for the validation script and `docs/SUB_AGENT_ISSUES.md` for known issues — keeping the main file focused on the core workflow. References are one level deep and clearly signaled. | 3 / 3 |
Total | 11 / 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.
Reviewed
Table of Contents