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.

0.98x

Quality

—

Does it follow best practices?

Impact

92%

0.98x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A comprehensive, well-structured Temporal orchestration reference, but it is a verbose monolith: it re-explains familiar concepts, contains no executable code (only pseudocode), and keeps all detail inline rather than splitting it across bundle files. Workflows lack explicit validation checkpoints for risky operations.

Suggestions

Replace pseudocode/ASCII decision trees with minimal executable Temporal snippets (e.g. a real saga workflow registering compensations via workflow.get_version/activities) so guidance is copy-paste ready.

Trim conceptual explanations Claude already knows (what a saga is, retry/backoff basics, heartbeat definition) and keep only Temporal-specific constraints and decisions.

Split the detailed pattern catalog and versioning/operational sections into referenced files (e.g. PATTERNS.md, VERSIONING.md) and add explicit validation checkpoints (e.g. 'verify replay determinism before deploying changes') to multi-step workflows.

Dimension	Reasoning	Score
Conciseness	Well-organized but ~317 lines that re-explain concepts Claude already knows (saga, fan-out/fan-in, retry backoff, heartbeats) and include no executable code; it could be tightened substantially. Not a 1 because the material is structured reference rather than pure fluff, but not a 3 due to verbosity and conceptual padding.	2 / 3
Actionability	Names real APIs (workflow.get_version(), workflow.now()) and gives concrete pattern steps, but every code block is pseudocode or an ASCII decision tree rather than executable code, so guidance is incomplete. Not a 1 because specific APIs and steps are cited; not a 3 because nothing is copy-paste ready.	2 / 3
Workflow Clarity	Multi-step sequences are present (e.g. the saga compensation steps, design decision framework), but there are no validation/verification checkpoints for risky operations like distributed transactions. Per the rubric, missing feedback loops for batch/destructive operations caps this at 2.	2 / 3
Progressive Disclosure	Section structure is clear, but the skill is monolithic — the detailed pattern catalog, versioning strategies, and operational guidance that belong in separate reference files are all inline, and there are no bundle-file references at all. Not a 1 because organization is decent; not a 3 because nothing is split out.	2 / 3
	Total	8 / 12 Passed

Description

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.

A strong, third-person description that names concrete capabilities, includes an explicit 'Use when' trigger clause, and is scoped to a distinct Temporal niche. It answers both what the skill does and when to use it without padding.

Dimension	Reasoning	Score
Specificity	Names multiple concrete capabilities — 'workflow vs activity separation, saga patterns, state management, and determinism constraints' — rather than vague language.	3 / 3
Completeness	Clearly states what it does ('Design durable workflows with Temporal… Covers…') and an explicit 'Use when building long-running processes, distributed transactions, or microservice orchestration' trigger.	3 / 3
Trigger Term Quality	Natural terms users would say are well covered — 'long-running processes', 'distributed transactions', 'microservice orchestration', 'workflows' — alongside the named technology Temporal.	3 / 3
Distinctiveness Conflict Risk	Tied to a named platform (Temporal) with distinct orchestration triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Dicklesworthstone/pi_agent_rust
Commit: abece4a

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.