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

80%

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

92%

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

The body is lean, highly actionable, and clearly sequenced with explicit safety/validation gates and a testing feedback loop. Its one real defect is progressive disclosure: it cites a docs file (MCP_SUBSCRIPTIONS.md) that is not present in the bundle, leaving the single external reference broken.

Suggestions

Create docs/MCP_SUBSCRIPTIONS.md (or remove the 'See docs/MCP_SUBSCRIPTIONS.md' reference) so the one external pointer resolves to a real file.

Consider splitting the dense MCP/UCP/generated-package adapter guidance into a reference file referenced one level deep, keeping SKILL.md as a tighter overview.

Verify there are no other inline references to files outside the bundle; ensure every 'See ...' link has a corresponding bundled artifact.

Dimension	Reasoning	Score
Conciseness	The body is lean and dense with no concept-explanation fluff - it assumes Claude's competence and jumps straight to Ax-specific behavior (mental model, rules, adapters) with every section earning its tokens. Not a 2 because there is no unnecessary explanation of known concepts or padding that could be trivially tightened.	3 / 3
Actionability	Provides two complete, copy-paste-ready TypeScript blocks (Minimal Pattern, Continuation Pattern) plus specific API calls (eventPath.data(), .project(), .field(), AxSQLiteEventStore, runAxEventStoreConformance) and concrete imperative rules. Not a 2 because the code is executable rather than pseudocode and key details are present.	3 / 3
Workflow Clarity	A clear source->inbox->route->target->stored run->sink sequence is paired with explicit validation/safety gates (dead-letter before model invocation, persist outputs before sink delivery, runAxEventStoreConformance gate) and a Testing section that functions as a feedback loop of assertions. Not a 2 because validation checkpoints and error-recovery guidance (separate sink redrive, retrySafety) are explicit rather than implicit.	3 / 3
Progressive Disclosure	Sections are clearly organized (Mental Model, Minimal Pattern, Rules, adapters, Testing) but the only external reference, 'See docs/MCP_SUBSCRIPTIONS.md', points to a file that does not exist, and no bundle files are present. Not a 3 because the referenced detail file is missing; not a 1 because the inline content is sectioned rather than a monolithic wall.	2 / 3
	Total	11 / 12 Passed

Description

67%

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 distinct, clearly naming concrete capabilities and product-scoped identifiers, but it omits any 'when to use' trigger guidance and leans on product jargon over the natural keywords (webhooks, timers, notifications) a user would actually say.

Suggestions

Append an explicit 'Use when...' clause naming natural trigger terms - e.g. notifications, webhooks, timers, queues, task-completion, or application events - so the description answers 'when' as well as 'what'.

Soften product jargon by pairing each Ax identifier with a plain-language equivalent (e.g. 'AxEventRuntime ... to ingest events from notifications, webhooks, and timers') to improve trigger-term quality.

Keep the concrete action list but reorder so the natural trigger scenario leads, improving the chance a user's phrasing matches the description.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions - 'ingest events', 'wake or resume', 'persist state and results', 'route outputs safely' - matching the anchor for listing several specific concrete actions. Not a 2 because it goes beyond naming a domain and some actions to enumerating four distinct operations.	3 / 3
Completeness	Clearly answers 'what' (ingest, wake/resume, persist, route) but provides no 'when to use it' guidance - no 'Use when...' clause or equivalent trigger. Per the guideline, a missing explicit trigger clause caps completeness at 2, so it cannot reach 3; not a 1 because the 'what' is explicit and concrete.	2 / 3
Trigger Term Quality	Trigger terms are product-specific jargon (AxEventRuntime, AxGen, AxAgent, AxFlow) rather than natural user keywords; 'events' is a relevant keyword but common variations a user would actually say (webhooks, notifications, timers, queues - which appear in the body) are absent. Not a 1 because 'events', 'persist', and 'route' are genuine domain keywords rather than fully generic terms.	2 / 3
Distinctiveness Conflict Risk	The Ax-namespaced product identifiers (AxEventRuntime, AxGen, AxAgent, AxFlow) carve out a clear niche unlikely to trigger for the wrong skill. Not a 2 because the product-specific framing makes overlap with generic skills improbable rather than 'could still overlap'.	3 / 3
	Total	10 / 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: ax-llm/ax
Path: website/static/typescript/.well-known/agent-skills/ax-event-runtime/SKILL.md
Commit: 7911e27

Reviewed: 5 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.