team-communication-protocols
Structured messaging protocols for agent team communication including message type selection, plan approval, shutdown procedures, and anti-patterns to avoid. Use this skill when establishing communication norms for a newly spawned team, when deciding whether to send a direct message or a broadcast, when a team-lead needs to review and approve an implementer's plan before work begins, when orchestrating a graceful team shutdown after all tasks are complete, or when debugging why teammates are not coordinating correctly at integration points.
72
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
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 defines a specific domain (agent team communication protocols), lists concrete capabilities, and provides an extensive 'Use this skill when...' clause with five distinct trigger scenarios. The description is well-structured, uses third person voice appropriately, and occupies a clear niche that would be easily distinguishable from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: message type selection, plan approval, shutdown procedures, and anti-patterns to avoid. These are clearly defined capabilities within the domain of agent team communication. | 3 / 3 |
Completeness | Clearly answers both 'what' (structured messaging protocols for agent team communication including message type selection, plan approval, shutdown procedures, anti-patterns) and 'when' with an explicit 'Use this skill when...' clause listing five distinct trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'communication norms', 'direct message', 'broadcast', 'plan approval', 'team shutdown', 'coordinating', 'integration points', 'spawned team', 'team-lead', 'implementer'. Good coverage of terms someone orchestrating agent teams would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused specifically on agent-to-agent team communication protocols. The specificity around message types, plan approval workflows, shutdown procedures, and multi-agent coordination makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured communication protocol skill with excellent actionability — every message type has a concrete JSON example and clear usage guidance. The workflow sequences for plan approval and shutdown are well-defined with proper feedback loops. The main weakness is moderate verbosity in the troubleshooting section and some redundancy in framing, plus the lack of progressive disclosure for what is a fairly lengthy document.
Suggestions
Tighten the troubleshooting section by removing explanatory phrases Claude already knows (e.g., 'This is a deadlock: both are blocked waiting for the other to finish first') and reducing each entry to the diagnostic step + fix.
Consider extracting the troubleshooting section into a separate TROUBLESHOOTING.md file and referencing it from the main skill to improve progressive disclosure and reduce the main file's length.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good use of tables and JSON examples, but the troubleshooting section is somewhat verbose with explanations Claude could infer (e.g., explaining what a deadlock is). Some sections like 'When to Use This Skill' repeat what the description already covers, and the anti-pattern explanations could be tighter. | 2 / 3 |
Actionability | Provides concrete, copy-paste-ready JSON message formats for every message type, specific file paths for teammate discovery, and clear step-by-step procedures. The anti-patterns table gives specific alternatives. All guidance is directly executable. | 3 / 3 |
Workflow Clarity | Both the plan approval workflow and shutdown protocol are clearly sequenced with numbered steps, explicit validation/feedback loops (reject with reason → wait → retry), and error recovery paths. The shutdown protocol handles rejections explicitly and includes a fallback for urgent cases. | 3 / 3 |
Progressive Disclosure | The skill references two related skills at the bottom with clear descriptions, which is good. However, the troubleshooting section is lengthy inline content that could be split into a separate file, and the overall document is fairly long (~150 lines of content) without leveraging any bundle files for detailed reference material. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- wshobson/agents
- Commit
34632bc
- 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.