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

78%

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

72%

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

A well-structured, concise reference skill that assumes competence and defers detail to the package's own docs, but its single code example is incomplete and it offers no validation-gated workflow for the lifecycle operations it describes.

Suggestions

Complete the Core Pattern example by showing how `llm` is constructed (e.g. a provider/no-key transport setup) so the snippet is copy-paste executable.

Add a short sequenced workflow with a validation checkpoint for at least one lifecycle operation (e.g. preload skills -> verify IDs merged -> forward -> inspect onUsedSkills), since the skill covers memory/skill loading and tracking.

Clarify which referenced files (API.md, axir-api.json, axir-capabilities.json, examples/) ship inside the skill bundle versus inside the axllm package, so navigation targets are unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is lean and information-dense — sections like 'Package Facts' and 'Lifecycle And State' pack concrete API facts Claude would not know without explaining basic concepts (e.g. what Python is), so every token earns its place.	3 / 3
Actionability	A concrete Core Pattern snippet and named API surface are present, but the example is incomplete (`llm` is referenced yet never defined) and most guidance is descriptive behavior notes rather than copy-paste executable code, so key details are missing.	2 / 3
Workflow Clarity	The 'When To Use' scenarios and Guardrails give some ordering, but this multi-faceted lifecycle skill lacks an explicit sequenced workflow with validation checkpoints or a validate-fix-retry feedback loop for its operations.	2 / 3
Progressive Disclosure	SKILL.md stays a well-organized overview with clear sections and one-level-deep signaled references to detail materials (API.md, axir-api.json, axir-capabilities.json, examples/), with no deep nesting; the skill's own bundle is empty because detail lives in the target axllm package.	3 / 3
	Total	10 / 12 Passed

Description

85%

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 specific, distinctive, well-triggered description that answers both what and when, weakened only by several implementation-jargon trigger terms that a user would be unlikely to say naturally.

Suggestions

Soften jargon trigger terms: pair 'recall callbacks' / 'loaded-skill state' / 'used-skill tracking' with plainer phrasings a user might actually say (e.g. 'remembering and tracking which skills and memories an agent used').

Add a couple of common natural variations (e.g. 'agent memory', 'skill discovery', 'Python agent skills') to broaden natural-keyword coverage.

Dimension	Reasoning	Score
Specificity	It lists multiple concrete capability areas — 'agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking' — tied to a specific package, matching the multiple-specific-actions anchor rather than the single-domain anchor at 2.	3 / 3
Completeness	It explicitly states both what ('writing Python code with axllm for [capabilities]') and when ('Use when writing Python code with axllm...'), satisfying the explicit what-AND-when-with-trigger anchor rather than the what-only anchor at 2.	3 / 3
Trigger Term Quality	Some natural terms appear ('writing Python code', 'agent memory', 'skill discovery'), but 'recall callbacks', 'loaded-skill state', and 'used-skill tracking' are internal implementation jargon a user would not naturally say, and common variations are missing.	2 / 3
Distinctiveness Conflict Risk	The narrow tie to the `axllm` package and its specific memory/skill-tracking niche makes it highly distinguishable and unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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: packages/python/skills/ax-python-agent-memory-skills/SKILL.md
Commit: fe8baf8

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.