Name: ax-flow
Rating: 68 (1 reviews)
Author: ax-llm

ax-flow

This skill helps an LLM generate correct AxFlow workflow code using @ax-llm/ax. Use when the user asks about flow(), AxFlow, workflow orchestration, parallel execution, DAG workflows, conditional routing, map/reduce patterns, or multi-node AI pipelines.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%

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-structured codegen reference with clear rules and error feedback. Its weaknesses are length/conciseness and progressive disclosure: a large amount of reference-grade content is packed into SKILL.md instead of being split into clearly signaled reference files.

Suggestions

Move the Mermaid Flow Gallery and dialect reference into a dedicated reference file (e.g. references/mermaid.md) and summarize it in SKILL.md with a one-level-deep link, reducing the inline token load.

Extract the instrumentation/tracing and event-triggered flow sections into reference files, keeping only a concise pattern and a pointer in SKILL.md.

Tighten the inline API sections (Factory Options, Node Definition, Execute, Map, Returns) by consolidating near-duplicate examples so the body stays lean while remaining copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows and stays code-dense, but at ~680 lines with a large inline Mermaid Flow Gallery and extensive API reference it is voluminous; material that could live in reference files is kept inline, so it does not fully earn the lean anchor 3.	2 / 3
Actionability	Abundant executable, copy-paste-ready TypeScript patterns (canonical flow, branching, while/feedback loops, derive, tracing) plus concrete aliases and error strings give fully actionable, specific guidance.	3 / 3
Workflow Clarity	This is a single-action codegen skill with an unambiguous canonical pattern, reinforced by 'Use These Defaults', 'Critical Rules', a 'Do Not Generate' checklist, and a common-errors error-handling section that functions as feedback for recovery.	3 / 3
Progressive Disclosure	Sections are well organized, but the file is monolithic: the Mermaid gallery, dialect reference, instrumentation, and event-triggered flow material are inline rather than offloaded to one-level-deep reference files, and no bundle files are present.	2 / 3
	Total	10 / 12 Passed

Description

90%

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, third-person description with explicit what-and-when triggers and good keyword coverage. Its only weakness is specificity: it names essentially one action (generate workflow code) rather than enumerating several concrete capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ('generate correct AxFlow workflow code using @ax-llm/ax'), but the remaining terms are trigger keywords rather than multiple distinct concrete actions, so it stops short of the comprehensive anchor 3.	2 / 3
Completeness	Clearly states what the skill does and provides an explicit 'Use when the user asks about...' trigger clause, satisfying both what and when in third person.	3 / 3
Trigger Term Quality	Broad, natural developer phrasing is covered ('flow()', 'AxFlow', 'workflow orchestration', 'parallel execution', 'DAG workflows', 'conditional routing', 'map/reduce patterns', 'multi-node AI pipelines'), matching the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	The '@ax-llm/ax' / 'AxFlow' niche is specific with distinctive triggers, making conflict with unrelated skills unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (683 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
Path: website/static/typescript/.well-known/agent-skills/ax-flow/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.