Name: ax-playbook
Rating: 74.4 (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

92%

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

85%

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

Highly actionable and token-efficient reference with executable code and tight rules. Weaker on workflow clarity (lacks explicit validation checkpoints as ordered steps) and progressive disclosure (no bundle files to offload the inline reference).

Suggestions

Frame the offline evolve pattern as numbered steps with an explicit validation checkpoint, e.g. 1) build program + metric, 2) await evolve, 3) inspect bestScore/playbook, 4) applyTo only when satisfied, 5) persist.

Move the generated multi-language API table and the detailed agent-bound evolve semantics into a separate reference file (e.g. references/agent-evolve.md) and link to it one level deep, keeping SKILL.md as an overview.

Add a short validate→fix→retry feedback loop note for the agent evolve verify gate so batch tuning failure recovery is explicit.

Dimension	Reasoning	Score
Conciseness	Lean rule lists and executable code assume Claude's competence without explaining what a playbook or library is; every section earns its tokens, including the compact multi-language table and See Also.	3 / 3
Actionability	Offline, online, persist/restore, and agent patterns are all given as fully executable TypeScript with concrete method calls and option shapes, copy-paste ready.	3 / 3
Workflow Clarity	Patterns are sequenced and troubleshooting gives error cues, but the main workflows are framed as reference snippets rather than ordered steps with explicit validate→fix→retry checkpoints; the agent evolve verify gate is described but not as a user-facing feedback loop.	2 / 3
Progressive Disclosure	Sections are well organized and See Also points to sibling skills, but no bundle files exist and the body is a fairly long inline reference with no one-level-deep file references to offload detail.	2 / 3
	Total	10 / 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, third-person description that clearly states the capability and provides an explicit 'Use when' clause with natural trigger terms. It is concise yet comprehensive and unlikely to misfire.

Dimension	Reasoning	Score
Specificity	Lists concrete actions and named API surfaces ('generate correct playbook code', 'evolve()', 'update()', offline and online growth), matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers what ('helps an LLM generate correct playbook code using @ax-llm/ax') and when ('Use when the user asks about...'), with an explicit 'Use when' trigger clause.	3 / 3
Trigger Term Quality	Natural trigger terms a user would say are well covered ('playbook()', 'context playbooks', 'evolving context', 'evolve() and update()', 'growing/applying task knowledge offline and online').	3 / 3
Distinctiveness Conflict Risk	Niche is specific to @ax-llm/ax playbook codegen with distinctive API-name triggers (AxPlaybook, ACE, agent.playbook()), making conflict with other skills unlikely.	3 / 3
	Total	12 / 12 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: 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.