axiom-concurrency

Use when writing ANY async code, actors, threads, or seeing ANY concurrency error. Covers Swift 6 concurrency, @MainActor, Sendable, data races, async/await patterns.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

72%

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

An effective router skill: it gives concrete, copy-paste-ready routing to well-signaled sub-files and keeps itself a lean overview. Its weaknesses are redundant routing across five representations (hurting conciseness) and the absence of validation/feedback checkpoints in its multi-step conflict-resolution workflow (hurting workflow clarity).

Suggestions

Deduplicate routing: the same sub-files appear in the Quick Reference table, the dot decision tree, the numbered list, the Critical Patterns bullets, and the Example Invocations — keep one or two representations and drop the rest to recover tokens.

Add a validation/feedback checkpoint to the conflict-resolution workflow (e.g., 're-run the build after the concurrency fix; if data-race warnings persist, re-read skills/swift-concurrency.md') so the multi-step sequence meets the workflow-clarity bar.

Collapse the Example Invocations section into the Quick Reference table, since it repeats the same user-prompt-to-file mappings already enumerated there.

Dimension	Reasoning	Score
Conciseness	It avoids explaining concepts Claude already knows, but routes the same sub-files redundantly across the Quick Reference table, the dot decision tree, the numbered list, the Critical Patterns bullets, and the Example Invocations — material that could be tightened.	2 / 3
Actionability	Gives concrete, specific routing — exact file paths ('skills/swift-concurrency.md'), an exact slash command ('/axiom:audit concurrency'), and an exact agent name ('concurrency-auditor') — with Example Invocations mapping user prompts to precise actions.	3 / 3
Workflow Clarity	The Conflict Resolution section and numbered decision tree lay out a clear sequence ('Try concurrency FIRST', 'Only use axiom-performance if...'), but there are no validation checkpoints or feedback loops, which caps the score per the rubric.	2 / 3
Progressive Disclosure	Acts as a lean overview that pushes detail into well-signaled, one-level-deep sub-file references with easy navigation via the Quick Reference table and decision tree; content is appropriately split rather than inlined.	3 / 3
	Total	10 / 12 Passed

Description

90%

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, well-targeted description: it pairs an explicit 'Use when' trigger clause with a concrete enumeration of covered topics and natural user-facing keywords. Its only weakness is that it lists trigger conditions and covered topics rather than concrete actions the skill performs, which keeps specificity at 2.

Dimension	Reasoning	Score
Specificity	Names the concurrency domain and enumerated topics ('@MainActor, Sendable, data races, async/await patterns') but offers trigger conditions ('writing ANY async code', 'seeing ANY concurrency error') rather than concrete actions the skill performs, stopping short of the multi-action bar of 3.	2 / 3
Completeness	Explicitly answers both what ('Covers Swift 6 concurrency, @MainActor, Sendable, data races, async/await patterns') and when ('Use when writing ANY async code... or seeing ANY concurrency error'), with an explicit 'Use when' trigger clause that clears the completeness cap.	3 / 3
Trigger Term Quality	Includes natural terms users actually say — 'async code', 'actors', 'threads', 'concurrency error', 'data races', 'Sendable', 'async/await', 'Swift 6 concurrency' — giving strong coverage of real-world trigger phrasing.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear concurrency niche with distinct triggers (data races, Sendable, @MainActor, Swift 6) that are unlikely to fire for non-concurrency skills.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: CharlesWiltgen/Axiom
Path: .claude-plugin/plugins/axiom/skills/axiom-concurrency/SKILL.md
Commit: ea3be7c

Reviewed: 1 day 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.