CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

axiom-concurrency

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

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./axiom-codex/skills/axiom-concurrency/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%Weight 40%Scale 1-5

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

A well-structured router skill with concrete symptom-to-reference routing, explicit prioritization, and strong conflict-resolution guidance. Its weaknesses are redundancy (the routing table is restated four times) and one oversized inline paragraph, plus reference paths that are unverifiable against the skill's own bundle.

Suggestions

Collapse the redundancy: keep the Quick Reference symptom table and one decision structure, and fold the Critical Patterns file summaries and Example Invocations into the reference files themselves or trim them to a few lines.

Move the ~100-word 'NonisolatedNonsendingByDefault' / 'SWIFT_APPROACHABLE_CONCURRENCY' explanation out of the Anti-Rationalization table into skills/swift-concurrency.md, leaving a one-line pointer.

Explain how the 'skills/...' reference paths resolve (e.g., relative to <plugin-root>) the same way the bundled-tools note does, so navigation works when the skill is read outside its plugin context.

DimensionReasoningScore

Conciseness

The body repeats the same routing information four times (Quick Reference table, Decision Tree dot-graph plus numbered list, Critical Patterns, Example Invocations), and the final Anti-Rationalization row on 'NonisolatedNonsendingByDefault' is a ~100-word paragraph that belongs in a reference file. Mostly efficient but clearly could be tightened, matching anchor 3 rather than anchor 4's minor-trim case.

3 / 5

Actionability

Concrete symptom-to-file routing with exact crash signatures ('_dispatch_assert_queue_fail', '_swift_task_checkIsolatedSwift'), specific commands ('xcprof analyze ... --start-ms/--end-ms --user-binary'), and an explicit bundled-tool fallback path ('<plugin-root>/tools/<tool>'). This matches anchor 4; not 5 because the guidance is routing ('Read skills/...') rather than copy-paste-ready fixes inline.

4 / 5

Workflow Clarity

The numbered decision rules (1, 1a, 1b, 2, 3, 3a...) provide an explicit prioritized routing sequence, and Conflict Resolution supplies disambiguation rules ('Try concurrency FIRST... Only use axiom-performance if concurrency fixes don't help'). Matches anchor 4; not 5 because no explicit validation or feedback checkpoints exist, which anchor 5 requires.

4 / 5

Progressive Disclosure

The body is a genuine overview with one-level-deep references into six clearly signaled reference files, each with a content summary in Critical Patterns. It matches anchor 4 rather than 5 because the referenced 'skills/...' paths do not resolve within this skill's own directory — no bundle files (references/, scripts/, assets/) are present, and the plugin-root convention is only explained for tools/, not for the skills/ prefix.

4 / 5

Total

15

/

20

Passed

Description

81%Weight 40%Scale 1-5

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 description with excellent, comprehensive natural trigger terms and a clear Apple-concurrency niche. Its main weakness is the vague 'what' statement — 'Covers...' enumerates topics instead of stating what the skill concretely does.

DimensionReasoningScore

Specificity

The description names two concrete user tasks ('writing ANY async code, actors, or threads' and 'seeing ANY concurrency error') and a concrete topic list ('Swift 6 concurrency, @MainActor, Sendable, data races, async/await patterns'), but the skill's own actions are expressed only through the generic verb 'Covers', matching anchor 3 rather than anchor 4's list of several specific actions.

3 / 5

Completeness

The 'when' is explicit and concrete ('Use when writing ANY async code... or seeing ANY concurrency error'), and the 'what' is present ('Covers Swift 6 concurrency, @MainActor, Sendable, data races, async/await patterns'), but the 'what' is a topic list rather than concrete actions, so it fits anchor 4 rather than anchor 5's fully concrete example.

4 / 5

Trigger Term Quality

Comprehensive natural trigger coverage — 'async code', 'actors', 'threads', 'concurrency error', '@MainActor', 'Sendable', 'data races', 'async/await', 'Swift 6' — including the framework-specific phrasings users would naturally say, matching anchor 5's synonym-complete example.

5 / 5

Distinctiveness Conflict Risk

The 'in an Apple-platform app' qualifier plus distinctive triggers like '@MainActor', 'Sendable', and 'Swift 6' carve out a clear niche with minimal overlap risk against generic async/threading or non-Apple skills, matching anchor 5.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

CharlesWiltgen/Axiom

Path

axiom-codex/skills/axiom-concurrency/SKILL.md

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.