CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

1.63x
Quality

80%

Does it follow best practices?

Impact

90%

1.63x

1 of 3 eval scenarios. Add 2 more for a full score.

SecuritybySnyk

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
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 tight, information-dense skill body that consistently provides package-specific facts Claude could not know, with executable syntax and clear guardrails. It falls just short of top marks due to a minor gap in the code sample (undefined 'llm'), version-history detail outside a deprecated section, and lifecycle detail that could be split into a reference file.

Suggestions

Make the Core Pattern code sample fully copy-paste ready by defining or importing 'llm' (e.g., show a no-key or scripted transport setup so the snippet runs as written).

Move the 24.x/25.0.0 context-map migration detail into an 'Old patterns' or 'Deprecated' section so version-sensitive history does not consume the core token budget.

Consider splitting the Lifecycle And State bullets into a separate reference file (e.g., references/lifecycle.md) and keeping a one-line summary in SKILL.md to improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body is lean and fact-dense with no padding or explanation of concepts Claude already knows — every line conveys package-specific behavior. However, the version-history detail ('Since 25.0.0 the text and item ids follow... a map saved by a 24.x port loads with its items') is time-sensitive migration information placed outside any 'old patterns' or 'deprecated' section, which the guidelines penalize, matching anchor 4 rather than 5.

4 / 5

Actionability

The Core Pattern provides real executable syntax and the Lifecycle section gives concrete behavioral rules (override precedence, state-shape warnings, ID merging semantics), plus pointers to runnable example files. But the code sample has a minor gap — 'llm' is never defined or imported — so it is not fully copy-paste ready, matching anchor 4 ('minor gaps') rather than 5.

4 / 5

Workflow Clarity

This is a reference-style skill with no destructive or batch operations, so no validation checkpoints are required; guidance is unambiguous and Guardrails direct the agent to start from package examples. There is no explicit step sequencing for common flows (e.g., choosing between get_state and export_runtime_state beyond the 'do not interchange' warning), which keeps it at anchor 4 rather than a fully sequenced 5.

4 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/ directories), and the body is well-organized into clear sections with external artifacts ('API.md', 'axir-api.json', 'examples/') clearly signaled one level deep under Package Facts and Runnable Examples. The dense Lifecycle And State section packs substantial behavioral detail inline that could live in a separate reference file, a minor organization gap matching anchor 4.

4 / 5

Total

16

/

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 good domain keyword coverage. Its main limitation is that capabilities are listed as feature nouns inside the trigger clause rather than as distinct concrete actions, keeping it just below the top anchors.

DimensionReasoningScore

Specificity

Names the domain ('writing Python code with `axllm`') and several concrete capability areas ('agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking'). These are feature nouns under a single verb rather than multiple distinct concrete actions, so it falls short of the anchor-5 comprehensive example like 'Extract text and tables from PDF files, fill forms, merge documents'.

4 / 5

Completeness

The explicit 'Use when writing Python code with `axllm` for...' clause answers 'when' clearly (avoiding the cap at 3), and the capability list implies the 'what'. However, the 'what' is embedded in the trigger clause rather than stated as its own capability statement, matching anchor 4 ('when' could be more explicit or specific) rather than the anchor-5 pattern of separate what and when statements.

4 / 5

Trigger Term Quality

Good natural keyword coverage for the domain ('Python', 'axllm', 'agent memory', 'skill discovery') that users of this package would plausibly say, but no synonyms or variations (e.g., 'memories catalog', 'skills catalog', 'recall') are included, matching anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The description is pinned to a specific generated package ('axllm') with niche triggers (agent memory, recall callbacks, skill discovery) that no general-purpose skill would share, giving a clear niche with minimal conflict risk as in anchor 5.

5 / 5

Total

17

/

20

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.

Validation — 15 / 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

Path

packages/python/skills/ax-python-agent-memory-skills/SKILL.md

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.