iii-agentic-backend
Creates and orchestrates multi-agent pipelines on the iii engine. Use when building AI agent collaboration, agent orchestration, research/review/synthesis chains, or any system where specialized agents hand off work through queues and shared state.
60
70%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/iii-agentic-backend/SKILL.mdQuality
Discovery
89%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 a solid description that clearly communicates both what the skill does and when to use it, with a distinctive niche around the iii engine. The trigger terms are comprehensive and natural. The main weakness is that the 'what' portion could be more specific about the concrete actions performed (e.g., defining agent roles, configuring queue topologies, managing shared state schemas).
Suggestions
Expand the capability list with more specific concrete actions, e.g., 'Creates and orchestrates multi-agent pipelines on the iii engine, including defining agent roles, configuring queue topologies, and managing shared state schemas.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (multi-agent pipelines on iii engine) and some actions (creates, orchestrates), but doesn't list multiple specific concrete actions like defining agent roles, configuring queues, setting up shared state, or managing handoffs in detail. | 2 / 3 |
Completeness | Clearly answers both what ('Creates and orchestrates multi-agent pipelines on the iii engine') and when ('Use when building AI agent collaboration, agent orchestration, research/review/synthesis chains, or any system where specialized agents hand off work through queues and shared state'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'multi-agent', 'pipelines', 'agent collaboration', 'agent orchestration', 'research/review/synthesis chains', 'queues', 'shared state', and 'hand off work'. Good coverage of variations a user might use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with the specific 'iii engine' platform reference and the niche of multi-agent pipeline orchestration with queues and shared state. Unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides a solid conceptual overview of multi-agent orchestration on the iii engine with a clear architecture diagram and useful primitive mappings. However, it lacks inline executable code examples (relying entirely on an unavailable reference file), has redundancy between the Primitives table and Common Patterns sections, and is missing error handling/validation guidance for what is inherently a complex multi-step workflow. The boilerplate 'When to Use' and 'Boundaries' sections add little value.
Suggestions
Add a minimal but complete inline code example showing at least one agent registration and one queue handoff, rather than relying entirely on the external reference file.
Remove or merge the 'Common Patterns' section with the 'iii Primitives Used' table to eliminate redundancy — they cover largely the same API surface.
Add explicit error handling and validation guidance: what happens when an approval gate rejects, when state operations fail, or when a queue message is malformed? Include a feedback loop pattern.
Remove or significantly trim the generic 'When to Use' and 'Boundaries' sections at the bottom — these are boilerplate that Claude doesn't need.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but has some redundancy — the 'Common Patterns' section largely repeats the 'iii Primitives Used' table, and the 'When to Use' and 'Boundaries' sections at the end are generic boilerplate that adds little value. The 'Adapting This Pattern' section is reasonably lean but could be tighter. | 2 / 3 |
Actionability | The skill provides concrete API signatures and a clear architecture diagram, but lacks inline executable code examples. It delegates the full working example to a reference file (agentic-backend.js) which is not provided in the bundle, so Claude cannot actually see or use the code. The 'Common Patterns' section lists API calls but doesn't show them in a runnable context. | 2 / 3 |
Workflow Clarity | The architecture diagram shows a clear multi-step sequence with an approval gate, which is good. However, there are no explicit validation checkpoints or error recovery steps — what happens if the approval check fails? What if state writes fail? For a multi-agent orchestration pattern involving queues and shared state, the absence of feedback loops and error handling guidance caps this at 2. | 2 / 3 |
Progressive Disclosure | The skill references external files (agentic-backend.js, iii-config.yaml) with clear paths and descriptions, which is good structure. However, no bundle files were provided, so these references are unverifiable. Additionally, the inline content has some redundancy between sections (Primitives table vs Common Patterns) that could be better organized — one of these should be the reference file content instead. | 2 / 3 |
Total | 8 / 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
- iii-hq/iii
- Commit
a7ebbbb
- 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.