CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ax-rust-agent-memory-skills

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

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 lean, well-structured reference skill: dense factual bullets, an executable core pattern, specific example paths, and useful guardrails. The main deductions are version-number-laden detail in the contextMap bullet and limited executable code beyond the single core snippet.

DimensionReasoningScore

Conciseness

The body is dense and factual with no explanations of concepts Claude already knows ('Language: Rust. Package: `axllm`.' style throughout), but the `contextMap` bullet carries version-history detail ('Since 25.0.0... a map saved by a 24.x port...') that is time-sensitive information outside any 'old patterns'/'deprecated' section, incurring the guideline penalty and keeping it at anchor 4 rather than 5.

4 / 5

Actionability

A concrete, executable core-pattern snippet ('axllm::agent("question:string -> answer:string")?; helper.forward(&llm, inputs, None)?'), specific runnable example paths, and a named API surface provide mostly executable guidance with minor gaps — only one small code snippet is included and several sections describe behavior without code, matching anchor 4 rather than the copy-paste-ready coverage of anchor 5.

4 / 5

Workflow Clarity

As a reference-style skill there is no multi-step sequence to validate, and the well-organized 'When To Use', lifecycle semantics, and guardrails make the usage unambiguous; the guardrail 'Use no-key examples for deterministic local checks' provides a checkpoint-style feedback path, but explicit validation steps are thin, matching anchor 4's 'clear sequence with most checkpoints present; minor validation gaps'.

4 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/), the ~60-line body is well-organized into clearly signaled sections, and external pointers (API.md, axir-capabilities.json, examples/) are one level deep into the target package rather than nested skill files, so per the simple-skill scoring note this matches anchor 5's clear, easy-to-navigate structure.

5 / 5

Total

17

/

20

Passed

Description

87%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 description: explicit 'Use when' trigger guidance, a named package and language, and five concrete capability areas. Its only weaknesses are terse noun-phrase capabilities and missing synonym variations, which cap specificity and trigger-term quality at 4 rather than 5.

DimensionReasoningScore

Specificity

The description enumerates five concrete capability areas ("agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking") tied to a named package, going beyond the 1-2 actions of anchor 3, but they are noun phrases rather than fully stated actions and coverage has minor gaps, so anchor 4 fits best.

4 / 5

Completeness

It explicitly answers both questions with concrete trigger phrasing: the 'what' is 'writing Rust code with axllm for agent memory, recall callbacks...' and the 'when' is the explicit 'Use when writing Rust code with `axllm` for...' clause listing the same concrete triggers, matching the anchor 5 example structure.

5 / 5

Trigger Term Quality

Natural terms a user of this domain would say are present ("Rust", "axllm", "agent memory", "skill discovery", "tracking"), matching anchor 4's 'good keyword coverage; a few natural terms missing' — synonyms like 'remember', 'recall', or 'skills catalog' are absent, keeping it below anchor 5.

4 / 5

Distinctiveness Conflict Risk

The named package (`axllm`), language (Rust), and niche functionality (agent memory/skill lifecycle for that package) create a clear niche with distinct triggers and minimal conflict risk with generic skills, matching anchor 5.

5 / 5

Total

18

/

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/rust/skills/ax-rust-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.