Name: ax-playbook
Rating: 72 (1 reviews)
Author: ax-llm

ax-playbook

This skill helps an LLM generate correct playbook code using @ax-llm/ax. Use when the user asks about playbook(), AxPlaybook, context playbooks, evolving context, ACE / Agentic Context Engineering, agent.playbook(), or growing/applying task knowledge offline and online with evolve() and update().

Quality

88%

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

82%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 body is highly actionable with complete executable examples and a well-sectioned structure. It is largely concise, with only minor verbose passages and no explicit validation checkpoints on the evolve/update flow.

Suggestions

Tighten the prose distinguishing program-level vs agent-level evolve and the playbook-vs-optimize section, which repeats concepts already conveyed by the code and tables.

Add a brief validation/checkpoint note for evolve() results (e.g., inspect bestScore or render() before applyTo) to strengthen workflow clarity.

Consider moving the multi-language agent-evolve table into a reference file once bundle support is added, keeping the body focused on the canonical TypeScript patterns.

Dimension	Reasoning	Score
Conciseness	Mostly lean with dense defaults/rules and minimal code, but a few explanatory paragraphs (the agent vs program evolve distinction, playbook-vs-optimize) could be tightened.	4 / 5
Actionability	Provides fully executable, copy-paste-ready TypeScript snippets across offline, online, persist, and agent patterns, plus a multi-language table covering the common agent-bound evolve call.	5 / 5
Workflow Clarity	Sections clearly sequence offline→online→persist→agents with a troubleshooting feedback section, though evolve/update lack explicit validation checkpoints; these are not destructive batch ops requiring the cap.	4 / 5
Progressive Disclosure	Well-organized with clear headers and a See Also section providing one-level-deep navigation; no bundle files exist, but the self-contained body is appropriately structured for its scope.	4 / 5
	Total	17 / 20 Passed

Description

95%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 highly specific and trigger-rich, clearly answering both what the skill does and when to use it with concrete API terms. It is concise, third-person, and well-distinguished from sibling skills.

Dimension	Reasoning	Score
Specificity	Names the domain (@ax-llm/ax playbook codegen) and several concrete actions (evolve(), update(), growing/applying task knowledge offline and online), with only minor coverage gaps.	4 / 5
Completeness	Explicitly states what the skill does (generate correct playbook code using @ax-llm/ax) and provides a concrete 'Use when...' clause with multiple trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural and technical trigger terms including playbook(), AxPlaybook, context playbooks, evolving context, ACE / Agentic Context Engineering, agent.playbook(), and the evolve()/update() method synonyms.	5 / 5
Distinctiveness Conflict Risk	Tightly scoped to the @ax-llm/ax playbook API with distinct method-name triggers, making overlap with unrelated skills minimal.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: ax-llm/ax
Path: website/static/typescript/.well-known/agent-skills/ax-playbook/SKILL.md
Commit: 1abea97

Reviewed: ~19 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.