CtrlK
BlogDocsLog inGet started
Tessl Logo

ax-gen

This skill helps an LLM generate correct AxGen code using @ax-llm/ax. Use when the user asks about ax(), AxGen, generators, forward(), streamingForward(), validation, assertions, streaming assertions, field processors, step hooks, self-tuning, or structured outputs. For MCP clients, transports, prompts, resources, tasks, subscriptions, or authentication use ax-mcp alongside this skill.

67

Quality

82%

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

SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

A highly actionable, well-organized AxGen reference with extensive executable code, but it is a monolithic wall of inline API detail with some redundancy and no progressive disclosure into local bundle files. Splitting the reference/examples into referenced files and de-duplicating repeated rules would lift the weaker dimensions.

Suggestions

Move the per-feature API reference and the examples list into local reference files (e.g. REFERENCE.md, EXAMPLES.md) and keep SKILL.md as a concise overview that links to them one level deep.

De-duplicate rules repeated across sections — e.g. the multi-step stop conditions appear in both 'Use These Defaults' and 'Function Calling', and 'Do Not Generate' restates earlier rules.

For any genuinely multi-step or risky flows (e.g. step-hook mutation pending-boundary, streaming-assert retry behavior), add an explicit validate-then-retry sequence so workflow_clarity can reach the checkpoint anchor.

DimensionReasoningScore

Conciseness

The body is dense and mostly free of concept-explaining fluff, but it is a long monolithic API reference (~540 lines) with repeated rules (e.g. multi-step stop conditions appear in both 'Use These Defaults' and 'Function Calling', and the 'Do Not Generate' list restates earlier rules), so it could be tightened.

2 / 3

Actionability

Every section ships copy-paste-ready, executable TypeScript with concrete options (e.g. gen.forward(llm, {...}, { maxRetries, modelConfig, debug }), addAssert, bestOfN), fully matching the executable-and-complete anchor.

3 / 3

Workflow Clarity

Content is well-organized by topic with per-section 'Rules' lists, but this is a reference rather than a sequenced multi-step process, and there are no validation/feedback checkpoints — which is acceptable for codegen but does not reach the explicit-checklist anchor.

2 / 3

Progressive Disclosure

No bundle files exist (references/scripts/assets absent); the body is a single large doc whose API reference and examples could be split into local reference files, and examples are only linked as external GitHub URLs rather than clearly-signaled one-level-deep local references.

2 / 3

Total

9

/

12

Passed

Description

100%

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: third-person voice, explicit what-and-when triggers, broad natural trigger terms, and a clear handoff to ax-mcp to avoid scope overlap. It would not reasonably fire for the wrong skill.

DimensionReasoningScore

Specificity

Names the concrete action ('generate correct AxGen code using @ax-llm/ax') and enumerates specific concrete capabilities (ax(), forward(), streamingForward(), assertions, field processors, step hooks, self-tuning, structured outputs), matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

It explicitly answers both what ('helps an LLM generate correct AxGen code using @ax-llm/ax') and when ('Use when the user asks about ...'), matching the clearly-answers-both anchor.

3 / 3

Trigger Term Quality

The 'Use when the user asks about ...' clause gives broad coverage of natural terms a user of this library would say (ax(), AxGen, generators, validation, assertions, structured outputs), matching the good-coverage anchor.

3 / 3

Distinctiveness Conflict Risk

It carves a clear AxGen-codegen niche and explicitly redirects overlapping MCP concerns to the separate ax-mcp skill, making conflicts unlikely.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (544 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
ax-llm/ax
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.