workflow-orchestration-patterns
Design durable workflows with Temporal for distributed systems. Covers workflow vs activity separation, saga patterns, state management, and determinism constraints. Use when building long-running processes, distributed transactions, or microservice orchestration.
72
60%
Does it follow best practices?
Impact
92%
0.98xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./tests/ext_conformance/artifacts/agents-wshobson/backend-development/skills/workflow-orchestration-patterns/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 identifies the technology (Temporal), lists specific concepts covered, and provides explicit trigger conditions. It uses proper third-person voice and includes natural keywords that users working with distributed systems would use. The description is concise yet comprehensive enough to distinguish it from general architecture or microservice skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and concepts: workflow vs activity separation, saga patterns, state management, determinism constraints, and durable workflows with Temporal. | 3 / 3 |
Completeness | Clearly answers both 'what' (design durable workflows with Temporal, covering workflow vs activity separation, saga patterns, state management, determinism constraints) and 'when' (explicit 'Use when building long-running processes, distributed transactions, or microservice orchestration'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'Temporal', 'distributed systems', 'saga patterns', 'long-running processes', 'distributed transactions', 'microservice orchestration', 'workflow', 'activity', 'determinism'. These cover a good range of how users would describe their needs. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific technology (Temporal) and domain-specific concepts (saga patterns, determinism constraints, workflow vs activity separation). Unlikely to conflict with generic coding or architecture skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
20%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a comprehensive reference guide or tutorial article about Temporal workflow orchestration than an actionable skill for Claude. It is extremely verbose, explains many concepts Claude already understands, and critically lacks any executable code examples despite being about a specific programming framework. The content would benefit enormously from being condensed to key non-obvious constraints and populated with real, runnable code snippets.
Suggestions
Add concrete, executable code examples in Python or TypeScript showing actual Temporal workflow and activity definitions, saga compensation implementation, and signal/query usage — these should be copy-paste ready, not pseudocode or prose descriptions.
Cut at least 50% of the content by removing explanations of concepts Claude already knows (what idempotency is, what fan-out/fan-in means, what saga patterns are) and focus only on Temporal-specific implementation details and gotchas.
Split detailed pattern implementations (saga, entity, fan-out) into separate reference files and keep SKILL.md as a concise overview with the critical design decision framework and determinism constraints.
Add a concrete validation/verification workflow — e.g., how to test workflow determinism, how to verify replay compatibility, or how to use Temporal's test framework to catch common violations.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~250+ lines, explaining many concepts Claude already knows (what a saga pattern is, what idempotency means, what fan-out/fan-in is). Lists of 'example use cases' and 'characteristics' are largely things Claude can infer. The 'When NOT to Use' section and extensive 'Best Practices' sections contain general software engineering knowledge that doesn't need to be spelled out. | 1 / 3 |
Actionability | Despite being about a specific technology (Temporal), there is zero executable code anywhere in the skill. Everything is described abstractly with bullet points and prose patterns rather than concrete, copy-paste-ready code examples. The 'Example: Payment Workflow' is just a numbered list of English sentences, not actual workflow code. | 1 / 3 |
Workflow Clarity | The saga pattern section provides a clear sequence (register compensation → execute → compensate in reverse on failure), and the overall structure logically progresses from design decisions to patterns to error handling. However, there are no concrete validation checkpoints or feedback loops for verifying correctness of implemented workflows, and the steps remain abstract rather than executable. | 2 / 3 |
Progressive Disclosure | The content has clear section headers and logical organization, and references external documentation URLs. However, the skill is monolithic — all content is inline in one large file with no references to supplementary skill files. Much of the detailed pattern descriptions and best practices could be split into separate reference files to keep the main skill lean. | 2 / 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
- Dicklesworthstone/pi_agent_rust
- Commit
6e3d68c
- 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.