orchestrator
Intelligent system orchestration for complex tasks using MCP and Pi Agent.
20
11%
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 ./public/skills/0xnagato/orchestrator/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 extremely vague and reads like marketing copy rather than a functional skill description. It fails to specify concrete actions, lacks natural trigger terms a user would use, provides no 'when to use' guidance, and is so generic it would conflict with many other skills.
Suggestions
Replace 'intelligent system orchestration for complex tasks' with specific concrete actions, e.g., 'Coordinates multi-step workflows across MCP servers, delegates subtasks to Pi Agent, and aggregates results.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user needs to orchestrate multiple tools, run multi-step pipelines, or mentions Pi Agent or MCP coordination.'
Define the specific scope and boundaries of this skill to distinguish it from other automation or tool-use skills, e.g., by listing the types of tasks or domains it handles.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language like 'intelligent system orchestration' and 'complex tasks' without listing any concrete actions. No specific capabilities are described. | 1 / 3 |
Completeness | The description barely addresses 'what' (vague orchestration) and completely omits 'when' — there is no 'Use when...' clause or any explicit trigger guidance. | 1 / 3 |
Trigger Term Quality | The terms 'intelligent system orchestration' and 'complex tasks' are not natural keywords a user would say. 'MCP' and 'Pi Agent' are proper nouns but overly technical without context. No common user-facing trigger terms are present. | 1 / 3 |
Distinctiveness Conflict Risk | 'Complex tasks' and 'system orchestration' are extremely generic and could overlap with virtually any skill that coordinates multiple tools or steps. Only 'Pi Agent' provides some specificity, but it's insufficient to carve out a clear niche. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a high-level description of an orchestration pattern rather than actionable guidance. It lacks concrete tool invocation syntax, executable examples, validation steps, and any specifics about how to actually use the referenced tools (mcporter, pi, exec). Claude would not gain meaningful operational knowledge from this content beyond what it could infer from the tool names alone.
Suggestions
Add concrete, executable examples showing exact tool invocation syntax for mcporter and pi (e.g., the actual function call, expected arguments, and response format).
Include validation/error-handling steps in the workflow, such as how to verify tool availability, handle failed MCP calls, or retry on errors.
Remove generic steps like 'Analyze: Understand the user's request' and 'Report: Summarize the results' — Claude already knows how to do these. Replace with specific orchestration patterns or decision trees.
Provide reference documentation or bundle files for the tools mentioned (mcporter, pi, coding-agent skill, web-search skill) so Claude can look up invocation details.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Reasonably brief but includes some unnecessary framing ('You are an Intelligent Orchestrator') and vague capability descriptions that don't add actionable value. The 'Analyze' and 'Report' steps are generic filler Claude doesn't need. | 2 / 3 |
Actionability | No executable code, no concrete commands, no specific tool invocation syntax. Everything is described abstractly ('use mcporter to call search or docs tools') without showing how to actually invoke these tools, what arguments they take, or what responses look like. | 1 / 3 |
Workflow Clarity | The workflow is a generic analyze-plan-execute-report pattern with no validation checkpoints, no error handling, and no concrete sequencing. Steps like 'Analyze: Understand the user's request' provide zero operational guidance. The example is superficial and lacks detail on actual tool invocation. | 1 / 3 |
Progressive Disclosure | The content is short and organized with clear sections, but references to 'coding-agent skill', 'web-search skill', and tools like 'mcporter' and 'pi' are mentioned without any links to documentation or supporting files. No bundle files exist to support these references. | 2 / 3 |
Total | 6 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
- Repository
- Demerzels-lab/elsamultiskillagent
- Commit
f45fcb5
- 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.