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.
79
73%
Does it follow best practices?
Impact
Pending
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 with explicit 'Use when' triggers and a distinctive niche around multi-agent pipeline orchestration on the iii engine. Its main weakness is that the 'what' portion could be more specific about the concrete actions performed (e.g., defining agent roles, configuring queue topology, managing shared state). The trigger terms are well-chosen and cover natural user language effectively.
Suggestions
Expand the capabilities list with more concrete actions, e.g., 'Defines agent roles, configures queue topology, manages shared state, and chains specialized agents for research/review/synthesis workflows.'
| 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 specifying handoff logic. | 2 / 3 |
Completeness | Clearly answers both 'what' (creates and orchestrates multi-agent pipelines on the iii engine) and 'when' (explicit 'Use when' clause covering agent collaboration, orchestration, research/review/synthesis chains, and queue-based handoff systems). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'multi-agent pipelines', 'agent collaboration', 'agent orchestration', 'research/review/synthesis chains', 'queues', 'shared state', and 'specialized agents hand off work' — good coverage of terms a user building such systems would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — the combination of 'iii engine', 'multi-agent pipelines', 'queues and shared state' creates a clear niche that is unlikely to conflict with other skills. The specific platform reference (iii engine) further narrows the scope. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a well-structured overview of multi-agent orchestration with good progressive disclosure and a clear architecture diagram. Its main weaknesses are the lack of inline executable code (relying entirely on an external reference file) and missing error handling/validation steps in the workflow. There is also some redundancy between the primitives table and the common patterns section.
Suggestions
Add a minimal inline executable code snippet showing at least one agent registration and one queue handoff, rather than deferring all code to the reference file.
Add explicit error handling and validation guidance: what happens when an agent fails, when an approval gate rejects, or when state is missing — include retry/feedback loop steps.
Consolidate the 'Common Patterns' section with the 'iii Primitives Used' table to eliminate redundancy, or differentiate them more clearly (e.g., table = API reference, patterns = usage recipes with code).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but has some redundancy — the 'Common Patterns' section largely restates what's already in the 'iii Primitives Used' table, and the 'When to Use' and 'Boundaries' sections contain generic boilerplate that doesn't add much value. The 'Key Concepts' and 'Architecture' sections are well-written and lean. | 2 / 3 |
Actionability | Provides concrete API patterns and a primitives table, but lacks inline executable code examples. The actual implementation is deferred entirely to a reference file. The 'Common Patterns' section lists API calls but doesn't show them in a runnable context, making it closer to pseudocode-level guidance. | 2 / 3 |
Workflow Clarity | The ASCII architecture diagram shows the multi-step agent pipeline clearly, and approval gates are mentioned. However, there are no explicit validation checkpoints or error recovery steps — what happens if an agent fails? What if the approval gate rejects? Missing feedback loops for this orchestration pattern caps this at 2. | 2 / 3 |
Progressive Disclosure | Excellent structure with clear sections, a concise overview, and well-signaled one-level-deep references to the full implementation file and config file. Content is appropriately split between the skill overview and reference materials. | 3 / 3 |
Total | 9 / 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
8921efa
- 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.