ax-event-runtime

Use AxEventRuntime to ingest events, explicitly wake or resume AxGen, AxAgent, and AxFlow, persist state and results, and route outputs safely.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./website/static/typescript/.well-known/agent-skills/ax-event-runtime/SKILL.md

Quality

Content

83%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.

The content is exceptionally concise and actionable with executable TypeScript and precise API rules, but the workflow lacks explicit sequenced validation checkpoints for its batch/event-redrive operations, which the rubric caps at 3. Progressive disclosure is strong with a single well-signaled external reference, though that reference file is not present in the bundle.

Suggestions

Add a short numbered workflow (build target -> declare route -> start -> publish -> verify persisted output -> redrive sink on failure) with an explicit validation/retry checkpoint to lift workflow_clarity.

Either include docs/MCP_SUBSCRIPTIONS.md in the bundle or note that it is external, so the one in-body reference is verifiable.

Consider moving the long MCP/UCP adapter paragraphs into a separate reference file to keep SKILL.md a tighter overview.

Dimension	Reasoning	Score
Conciseness	The body is lean and dense with rules and executable snippets, assumes Claude's competence, and avoids explaining what events or libraries are; nearly every token earns its place.	5 / 5
Actionability	It provides copy-paste-ready TypeScript for the minimal pattern and continuation registration, plus concrete selector/route/store APIs and exact import paths, covering the common cases fully.	5 / 5
Workflow Clarity	The skill involves batch/event-driven and destructive-ish operations (state persistence, sink redrive) and while it lists rules, it lacks an explicit numbered sequence with validate/fix/retry checkpoints; the Testing section asserts invariants but the main workflow has no explicit validation feedback loop, capping clarity at 3.	3 / 5
Progressive Disclosure	Well-organized sections (Mental Model, Minimal Pattern, Rules, Continuation, Adapters, Testing) with a single clearly-signaled one-level reference to docs/MCP_SUBSCRIPTIONS.md; however no bundle files exist to verify the reference and some adapter detail is inlined that could live separately, keeping it just below 5.	4 / 5
	Total	17 / 20 Passed

Description

71%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.

The description is specific and action-oriented with a clear technical niche, but it omits any explicit trigger/when-to-use guidance, which the rubric caps at completeness 3. Adding a 'Use when...' clause naming notifications, webhooks, timers, and queues would lift both completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when an Ax program must react to notifications, webhooks, timers, queues, or task-completion events.'

Move common user-facing trigger terms (notifications, webhooks, timers, queues) into the description rather than only the body to improve trigger-term coverage.

Keep third-person voice (currently compliant) and avoid padding the existing action list with generic verbs.

Dimension	Reasoning	Score
Specificity	Names the tool (AxEventRuntime) and lists multiple concrete actions — ingest events, wake/resume AxGen/AxAgent/AxFlow, persist state and results, route outputs safely — providing comprehensive coverage rather than vague verbs.	5 / 5
Completeness	It clearly answers 'what' (ingest/wake/resume/persist/route) but lacks any explicit 'Use when...' or 'when should Claude use it' clause, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	It includes strong natural trigger terms (events, notifications, webhooks, timers, queues, task completion) but those appear in the body, not the description; the description itself leans on technical nouns and misses everyday synonyms.	4 / 5
Distinctiveness Conflict Risk	The naming of AxEventRuntime and AxGen/AxAgent/AxFlow gives it a clear niche with minimal overlap risk; only the broad 'route outputs safely' phrasing keeps it from a 5.	4 / 5
	Total	16 / 20 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: ax-llm/ax
Path: website/static/typescript/.well-known/agent-skills/ax-event-runtime/SKILL.md
Commit: 1abea97

Reviewed: ~18 hours 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.