agent-hierarchical-coordinator
Agent skill for hierarchical-coordinator - invoke with $agent-hierarchical-coordinator
42
13%
Does it follow best practices?
Impact
87%
9.66xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-hierarchical-coordinator/SKILL.mdQuality
Discovery
0%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 description is essentially a label and invocation command with no substantive content. It fails on every dimension: it doesn't describe what the skill does, when to use it, or provide any natural trigger terms. It would be nearly impossible for Claude to correctly select this skill from a pool of available skills.
Suggestions
Add a clear explanation of what the skill does with specific concrete actions (e.g., 'Coordinates multi-step tasks by breaking them into subtasks and delegating to specialized agents').
Add an explicit 'Use when...' clause with natural trigger terms describing the scenarios where this skill should be selected (e.g., 'Use when the user needs to orchestrate complex workflows, manage parallel subtasks, or coordinate multiple agents').
Replace the generic 'Agent skill for hierarchical-coordinator' framing with domain-specific language that distinguishes this skill from other coordination or orchestration tools.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for hierarchical-coordinator' is entirely abstract and gives no indication of what the skill actually does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. The description only states the invocation command, providing no functional or contextual information. | 1 / 3 |
Trigger Term Quality | The only keyword is 'hierarchical-coordinator', which is technical jargon unlikely to be used naturally by a user. There are no natural trigger terms that a user would say. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it could overlap with any coordination or orchestration skill. 'Hierarchical-coordinator' provides minimal distinctiveness without explaining what it coordinates or in what domain. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is excessively verbose, containing substantial generic project management content (performance metrics targets, communication patterns, best practices) that Claude already knows and doesn't need spelled out. While it provides some concrete MCP tool commands and a useful memory coordination protocol, much of the workflow guidance is abstract YAML pseudocode rather than executable instructions. The monolithic structure with no external file references makes it a poor use of context window space.
Suggestions
Reduce content by at least 60%: remove generic project management advice (best practices, communication patterns, performance metrics), worker capability descriptions Claude can infer, and the illustrative Python pseudocode algorithm.
Split into multiple files: move worker type definitions to WORKERS.md, MCP tool reference to MCP_REFERENCE.md, and escalation protocols to ESCALATION.md, with clear one-level-deep links from the main skill.
Add explicit validation checkpoints in the workflow: after spawning agents verify they're active, after task assignment confirm acknowledgment, before integration validate all worker outputs meet quality gates.
Replace YAML pseudocode workflow phases with concrete, executable MCP command sequences showing the actual commands to run at each step with expected outputs.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~250+ lines. Includes extensive explanations of concepts Claude already understands (what research workers do, what code workers do, basic delegation concepts). The architecture diagram, decision-making framework pseudocode, performance metrics targets, best practices, and communication patterns sections are largely generic project management advice that wastes tokens. Much of this could be reduced to 1/3 the size. | 1 / 3 |
Actionability | Provides concrete MCP tool commands (spawn, monitor, orchestrate) and memory coordination patterns with specific key structures, which is useful. However, much of the workflow is described in YAML pseudocode rather than executable commands, the Python decision-making algorithm is illustrative pseudocode not real code, and the escalation protocols are abstract thresholds without concrete implementation steps. | 2 / 3 |
Workflow Clarity | The three-phase workflow (Planning, Execution, Integration) provides a clear sequence, and the mandatory memory coordination protocol has numbered steps. However, there are no explicit validation checkpoints or feedback loops for error recovery. For a coordination skill involving multi-agent orchestration (a complex, potentially destructive operation), the absence of 'validate before proceeding' steps and error handling caps this at 2. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files. All content—worker type definitions, MCP tool reference, decision frameworks, escalation protocols, performance metrics, best practices—is inlined in a single massive document. Worker type details, the full MCP tool reference, and the decision-making framework could easily be split into separate referenced files. | 1 / 3 |
Total | 6 / 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
- ruvnet/claude-flow
- Commit
322b2ae
- 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.