CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

The content is highly actionable with complete executable code and clear sequenced workflows plus observability checkpoints. Its main weaknesses are length/redundancy across sections and a monolithic inline structure that lacks the reference-file split progressive disclosure favors for a skill this size.

Suggestions

Deduplicate cross-section restatements: define 'recall()/discover() return void' and 'built-in catalog search is lexical' once in a shared section and reference it from Memory Search and Skills Search.

Extract the inline type definitions and the full callback-signature reference into a reference file (e.g. REFERENCE.md) and link to it, so SKILL.md stays an overview and progressive disclosure improves.

Move the long 'Do Not Generate' list closer to each relevant section or condense it, since several entries restate rules already covered inline.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence (no padding with basics), but at ~440 lines it restates some points across sections — e.g. 'built-in search is lexical' and 'recall()/discover() return void' each appear multiple times — so it could be tightened.

2 / 3

Actionability

Provides fully executable, import-complete TypeScript examples with real type definitions, signatures, and copy-paste-ready code for context maps, memory search, skills search, carrying memories, and usage tracking.

3 / 3

Workflow Clarity

Actor-usage sequences are clearly staged ('Turn 1: kick off one batched lookup... Turn 2+: matched entries visible') with observability checkpoints (onLoadedMemories/onUsedSkills, relevance_ranking events) and explicit 'Do Not Generate' guardrails.

3 / 3

Progressive Disclosure

Sections are clearly labeled and external examples are one-level-deep, well-signaled links, but no bundle/reference files exist and the ~440-line body keeps substantial inline API reference and type definitions that could be split into separate reference files.

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.

The description is specific, trigger-rich, and complete, clearly stating what the skill does and exactly when to use it via concrete API symbol names. It is clearly distinguishable from sibling Ax skills and written in third person.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities ('memory retrieval', 'context-map', 'dynamic skill-loading code') plus many specific API symbols, matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both 'what' ('helps an LLM generate correct AxAgent memory retrieval, context-map, and dynamic skill-loading code') and 'when' via an explicit 'Use when the user asks about...' trigger clause.

3 / 3

Trigger Term Quality

The 'Use when the user asks about...' clause enumerates the full surface of API symbol names (onMemoriesSearch, recall(...), skillsCatalog, discover({ skills }), relevanceRanking, etc.) that a developer using @ax-llm/ax would naturally mention, giving good coverage of natural terms.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (AxAgent memory/skills/context-map APIs in @ax-llm/ax) with highly specific trigger terms keyed to exact API names, making wrong-skill triggering unlikely; sibling skills are disambiguated in the body.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

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.