ax-python-agent-memory-skills

Use when writing Python code with `axllm` for agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking.

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./packages/python/skills/ax-python-agent-memory-skills/SKILL.md

Quality

Content

67%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.

A well-organized, information-dense reference for a generated package, with clear routing to package docs and examples and no wasted tokens on concepts Claude already knows. The main weakness is actionability: the one code example is incomplete and the core memory/skill/observer features are described but never shown in executable form.

Suggestions

Complete the 'Core Pattern' snippet by showing how `llm` is obtained (or a no-key transport variant) so it is copy-paste runnable.

Add one short executable example for the skill's headline features, e.g., passing `skills`/`memories` at forward time and registering `onUsedSkills`/`onLoadedMemories` observers.

Move the detailed `contextMap` version-migration prose into a reference file (or an 'old patterns' section) and keep a one-line summary in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is dense with package-specific, non-inferable facts (e.g., 'Forward-time `skills` override constructor entries by normalized ID', 'observer errors are ignored') with no generic-concept padding. A few long bullets (the `contextMap` and `relevanceRanking` entries) pack multiple behaviors into single sentences and could be split or trimmed.	4 / 5
Actionability	The 'Core Pattern' block is nearly executable but leaves `llm` undefined, and the skill's headline features — memory seeding, catalog search, observer registration — get prose behavior descriptions with no code at all. Guidance leans on pointing to external example files ('skills-and-memory-assistant.py') rather than inline executable snippets, which is a concrete gap.	3 / 5
Workflow Clarity	The entry-point workflow is unambiguous ('Start from package examples for exact native syntax before inventing a new call shape') and the 'Package Facts' section clearly routes to API docs, manifests, and examples. No destructive or batch operations are involved, so missing validation checkpoints are not penalized; however, the path from core pattern to the memory/skill/observer features is implicit rather than sequenced.	4 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent), and the body is well-organized with clearly signaled pointers to package-side materials (API.md, axir-api.json, examples/). Minor gap: dense reference-style bullets like the `contextMap` migration details could live in a separate reference file to keep SKILL.md a leaner overview.	4 / 5
	Total	15 / 20 Passed

Description

78%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.

A strong, niche-specific description with an explicit 'Use when...' trigger and a concrete feature list. Its main weakness is that the feature list names capabilities rather than actions, leaving the 'what does this skill do' side implicit.

Suggestions

Lead with a verb-driven 'what' clause (e.g., 'Guides writing Python code that loads memories, registers recall callbacks, and tracks used skills with the axllm package') so the capability nouns become concrete actions.

Add one or two natural user synonyms (e.g., 'remembering', 'skill catalog') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete capability areas ('agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking') anchored to a named package, but these are capability nouns rather than concrete actions, and coverage of what the skill actually helps do is implicit.	4 / 5
Completeness	The 'when' is explicit and concrete ('Use when writing Python code with `axllm` for agent memory, recall callbacks...'), but the 'what' is only implied by the feature list — no verb-led statement of what the skill does (e.g., 'Guides writing Python code that loads memories and registers skill observers').	4 / 5
Trigger Term Quality	Good natural keyword coverage: 'writing Python code', 'agent memory', 'dynamic skill discovery', plus the package name 'axllm'. A few natural user phrasings (e.g., 'remember', 'skill catalog', 'recall') are present but common synonyms and variations are not comprehensive.	4 / 5
Distinctiveness Conflict Risk	Clear niche: Python code for a specific generated package ('axllm') with agent-memory/skill-discovery triggers. Minimal overlap risk with other skills; the package name alone disambiguates.	5 / 5
	Total	17 / 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: packages/python/skills/ax-python-agent-memory-skills/SKILL.md
Commit: 3f630a0

Reviewed: 3 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.