CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

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
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 a dense, high-signal rule set with a nearly executable minimal pattern, documented runtime-enforced validation checkpoints, and a clear testing story. Its main weaknesses are mild: missing code examples for the continuation/MCP/UCP flows, some spec-dump paragraphs that could move to reference files, and one dangling reference to docs/MCP_SUBSCRIPTIONS.md.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence throughout — no basic-concept explanations, and every rule is domain-specific ('identity from authenticated adapter state, never from event data'). A few overloaded compound sentences and spec-dense passages (cancellation semantics, store limits) could be trimmed or split out, keeping it just below the lean-everywhere anchor.

4 / 5

Actionability

A nearly copy-paste-ready TypeScript minimal pattern plus concrete API names throughout (eventPath.data(), eventInput().project(), AxSQLiteEventStore, runAxEventStoreConformance) give strongly executable guidance. Minor gaps: the continuation, MCP, and UCP sections name APIs but include no executable snippets.

4 / 5

Workflow Clarity

The Minimal Pattern gives a concrete ordered sequence (source, target, routes, start, publish) reinforced by the mental-model pipeline, and validation checkpoints are documented (envelope rejection, dead-lettering before invocation, persist-before-sink, redrive, plus an explicit Testing section with assertions and a store conformance requirement). It falls short of a 5 because no explicit validate-fix-retry feedback loop is spelled out for common failures.

4 / 5

Progressive Disclosure

Well-organized sections (Mental Model, Minimal Pattern, Rules, Continuation, Adapters, Testing) make the single-file skill easy to navigate. It misses a 5 because 'See docs/MCP_SUBSCRIPTIONS.md' points to a path not present in any bundle directory, and the generated-runtimes paragraphs carry spec-level detail (e.g. '10,000 pending deliveries, 64 MiB queued data, 1 MiB per envelope') that could live in a reference file.

4 / 5

Total

16

/

20

Passed

Description

58%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 communicates a clear, mostly concrete capability set anchored by specific Ax component names, making it highly distinctive within its ecosystem. Its weaknesses are the complete absence of 'when to use' trigger guidance and reliance on framework jargon over the natural phrases (webhooks, notifications, timers, queues) that would help a user select it.

Suggestions

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

Include natural trigger synonyms (webhooks, event-driven, subscriptions, notifications) rather than only framework terms like wake/resume/ingest.

Replace the vague 'route outputs safely' with a concrete action such as 'deliver outputs through validated sinks with redrive on failure'.

DimensionReasoningScore

Specificity

Names several concrete actions ('ingest events', 'explicitly wake or resume AxGen, AxAgent, and AxFlow', 'persist state and results') with specific targets, but 'route outputs safely' is generic filler and body-covered areas like webhooks, timers, and queues are absent, leaving minor coverage gaps.

4 / 5

Completeness

The 'what' is clear and detailed (ingest, wake/resume, persist, route), but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

'events' is a natural user term and 'ingest'/'wake'/'resume' are domain-relevant, but the description relies on framework jargon and misses common variations users would actually say — 'webhooks', 'notifications', 'timers', 'queues', 'event-driven' — all of which appear in the body but not the description.

3 / 5

Distinctiveness Conflict Risk

Naming the unique component 'AxEventRuntime' plus AxGen/AxAgent/AxFlow gives a clear niche with minimal conflict against non-Ax skills, but event handling and output routing overlap with closely related Ax skills (the body itself documents an ax-mcp boundary), leaving minor overlap risk.

4 / 5

Total

14

/

20

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 — 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

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.