iii-workflow-orchestration
Orchestrates durable multi-step workflow pipelines on the iii engine. Use when building order fulfillment, data pipelines, task orchestration, or any sequential process requiring retries, backoff, step tracking, scheduled cleanup, or dead letter queue (DLQ) handling.
80
75%
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-workflow-orchestration/SKILL.mdQuality
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 a strong skill description that clearly communicates what the skill does (orchestrate durable workflow pipelines on a specific engine) and when to use it (with an explicit 'Use when' clause covering multiple trigger scenarios). The description is concise yet comprehensive, with excellent trigger term coverage spanning both business-level concepts (order fulfillment) and technical implementation details (DLQ, backoff, retries).
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and concepts: 'durable multi-step workflow pipelines', 'retries', 'backoff', 'step tracking', 'scheduled cleanup', 'dead letter queue (DLQ) handling'. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (orchestrates durable multi-step workflow pipelines on the iii engine) and 'when' (explicit 'Use when' clause listing order fulfillment, data pipelines, task orchestration, or sequential processes requiring specific features). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'order fulfillment', 'data pipelines', 'task orchestration', 'sequential process', 'retries', 'backoff', 'step tracking', 'DLQ', 'dead letter queue', 'workflow pipelines'. Good coverage of both domain terms and technical variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific platform reference ('iii engine') and the combination of durable workflow orchestration with specific features like DLQ handling, retries, and backoff. Unlikely to conflict with generic coding or data processing skills. | 3 / 3 |
Total | 12 / 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.
This skill provides a solid architectural overview of workflow orchestration on the iii engine with clear step sequencing and well-organized primitives. However, it falls short on actionability by deferring all executable code to an unverifiable reference file, and lacks explicit validation/error-recovery checkpoints in the workflow despite dealing with durable multi-step pipelines involving retries and DLQs. Some sections ('When to Use', 'Boundaries') add meta-instructions that consume tokens without adding value.
Suggestions
Add at least one inline executable code example showing a minimal 2-step pipeline (e.g., validate → enqueue next step) rather than deferring everything to the reference file.
Add explicit validation checkpoints to the workflow — e.g., how to verify a step completed successfully before proceeding, and what to do when a step fails mid-pipeline.
Remove or consolidate the 'When to Use' and 'Boundaries' sections, which restate generic meta-instructions that don't add skill-specific value.
Consider inlining a minimal iii-config.yaml snippet showing one queue configuration rather than only referencing an external file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary sections like 'When to Use' and 'Boundaries' that restate obvious meta-instructions, and the 'Adapting This Pattern' section mixes actionable guidance with filler. The architecture diagram and primitives table are well-structured but the overall content could be tightened. | 2 / 3 |
Actionability | Provides concrete API patterns and a primitives table, but lacks inline executable code examples — the full implementation is deferred to a reference file. The 'Common Patterns' section shows API calls but as fragments rather than copy-paste-ready code blocks. Without the bundle files to verify the reference exists, actionability relies on external files. | 2 / 3 |
Workflow Clarity | The architecture diagram clearly shows the step sequence (validate → charge → ship), and the 'Adapting This Pattern' section mentions DLQ handling and retry exhaustion. However, there are no explicit validation checkpoints or error recovery feedback loops described — e.g., no guidance on what to check between steps, how to verify step completion, or how to handle partial pipeline failures. | 2 / 3 |
Progressive Disclosure | References to external files (workflow-orchestration.js, iii-config.yaml) are well-signaled and one level deep, which is good structure. However, no bundle files were provided to verify these references exist, and the SKILL.md itself contains a fair amount of content that could be split out (e.g., the full primitives table, adaptation guidance). The inline content is borderline between overview and detailed reference. | 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
d51a06d
- 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.