Name: ax-agent-memory-skills
Rating: 69.6 (1 reviews)
Author: ax-llm

ax-agent-memory-skills

This skill helps an LLM generate correct AxAgent memory retrieval, context-map, and dynamic skill-loading code using @ax-llm/ax. Use when the user asks about contextMap, AxAgentContextMap, onMemoriesSearch, memoriesCatalog, recall(...), inputs.memories, onLoadedMemories, onUsedMemories, onSkillsSearch, skillsCatalog, AxAgentCatalogSkill, discover({ skills }), onLoadedSkills, onUsedSkills, preloaded skills, preloading memories at forward time, relevanceRanking hints, loaded memory/skill IDs, or carrying memories across forward() calls.

Quality

85%

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

Quality

Content

71%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 a thorough, executable reference with strong guardrails, but it is a single monolithic file carrying API-reference bulk that could be split into reference files, and it repeats several rules across sections. Splitting types/examples into separate files and de-duplicating the Rules lists would tighten it materially.

Suggestions

Move the consolidated type definitions and full API reference into separate reference files (e.g. TYPES.md, EXAMPLES.md) and link to them one level deep, keeping SKILL.md as a concise overview plus a quick-start snippet.

De-duplicate the per-section Rules lists against the consolidated Types and 'Do Not Generate' sections so each rule appears once; the 'return void' and dedup-by-id rules are currently restated several times.

Add an explicit validate→fix→retry checkpoint for mutating paths such as contextMap onUpdate snapshot persistence so workflow_clarity can reach the top anchor.

Dimension	Reasoning	Score
Conciseness	The body is dense and high-signal with no over-explanation of concepts Claude already knows, but rules and the 'return void' contract are repeated across the per-section Rules lists and again in the consolidated Types and Do Not Generate sections, which is more than the 'minor' trimming the 4 anchor implies.	3 / 5
Actionability	Complete, copy-paste-ready TypeScript examples and full type definitions cover the common cases — enabling a callback, static catalog, preloading, and used-tracking — matching the fully-executable top anchor.	5 / 5
Workflow Clarity	Actor usage is clearly sequenced (Turn 1 recall → Turn 2+ read inputs.memories) with explicit do/don't guardrails, but there are no formal validate→fix→retry feedback loops for the few mutating operations (e.g. onUpdate snapshot persistence), leaving it just below the 5 anchor.	4 / 5
Progressive Disclosure	No bundle files exist and the full API reference — complete type definitions, per-section Rules, and bulk examples — is inlined into a single ~440-line SKILL.md with only external GitHub URLs as one-level references, fitting the 'content that should be separate is inline' anchor rather than a well-split structure.	3 / 5
	Total	15 / 20 Passed

Description

100%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 third-person, concrete, and tightly scoped, answering both what the skill does and when to use it with an extensive list of natural trigger terms and API identifiers. It is a strong, low-conflict description with no padding.

Dimension	Reasoning	Score
Specificity	Lists many concrete capabilities and API surfaces — 'memory retrieval, context-map, and dynamic skill-loading code' plus named APIs (contextMap, onMemoriesSearch, recall(...), discover({ skills }), memoriesCatalog) — matching the 'multiple specific concrete actions; comprehensive coverage' anchor.	5 / 5
Completeness	Explicit 'what' ('generate correct AxAgent memory retrieval, context-map, and dynamic skill-loading code') and an explicit 'Use when the user asks about...' clause with concrete trigger phrases, satisfying the top anchor.	5 / 5
Trigger Term Quality	Exhaustive natural/identifier trigger coverage including synonyms and specific symbols ('recall(...)', 'discover({ skills })', 'preloading memories at forward time', 'carrying memories across forward() calls'), matching the comprehensive-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	Narrow niche scoped to AxAgent memory/skills APIs with many distinct triggers, and the body explicitly distinguishes sibling skills (ax-agent, ax-agent-rlm, ax-agent-observability), giving minimal conflict risk.	5 / 5
	Total	20 / 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-agent-memory-skills/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.