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

73%

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/rust/skills/ax-rust-agent-memory-skills/SKILL.md

Quality

Content

61%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-organized reference for the axllm memory/skills subsystem with real code, concrete example paths, and clear pointer navigation. Its weaknesses are the absence of any sequenced implementation workflow with a verification checkpoint, and a long version-history-laden contextMap bullet that inflates the main body.

Suggestions

Add a short numbered workflow (consult `API.md`/examples, adapt the example for the target callbacks, verify with a `no-key` example run) with an explicit validation checkpoint so the implementation sequence is not implicit.

Move the contextMap format and 24.x-to-25.0.0 migration detail into a dedicated old-patterns/deprecated subsection or reference file, keeping only the current behavior in the main body.

Include one complete inline example that wires skills/memories inputs and observers end-to-end so the core pattern graduates from a snippet to copy-paste-ready guidance.

Dimension	Reasoning	Score
Conciseness	The body is fact-dense with essentially no conceptual padding, but the `contextMap` bullet carries format minutiae and version-sensitive migration detail ("Since 25.0.0 ... a map saved by a 24.x port loads with its items") inline rather than in an old-patterns/deprecated section, which is a explicit penalty trigger and a noticeable tightening candidate.	3 / 5
Actionability	It gives a real core-pattern code snippet, concrete example file paths (e.g., `src/examples/rust/long-agents/skills_and_memory_assistant.rs`), and specific API semantics (observer precedence, state-shape separation). It stops short of anchor 5 because no complete end-to-end inline example wiring inputs and observers is provided.	4 / 5
Workflow Clarity	Guidance is organized topically rather than as a workflow: the sequence for actually implementing something (consult API docs, adapt the example, verify with the no-key transport) is only implicit in Guardrails, and no explicit validation checkpoint or error-recovery loop is shown. This is not a single-action simple skill, so the simple-skill exception does not apply.	3 / 5
Progressive Disclosure	No bundle files exist, and external materials are clearly signaled at one level deep ("Package API docs: `API.md` and `axir-api.json`", "Runnable examples: `examples/`") with well-organized sections. The dense Lifecycle And State section, including the version-history material, is inline content that could live in a reference file, keeping it at anchor 4 rather than 5.	4 / 5
	Total	14 / 20 Passed

Description

75%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 solid, well-scoped description with an explicit "Use when..." trigger, a named niche package, and several concrete capability areas. It falls short of top marks only on breadth: it does not enumerate all subsystems it covers, and the what-vs-when split is compressed into a single clause.

Suggestions

State what the skill provides up front (e.g., "Documents the axllm API and examples for...") before the "Use when..." clause so the what is explicit, not implied.

Add the remaining capability areas users would mention (relevance ranking, context map, agent state export/restore) and natural synonyms such as "skills catalog" to broaden trigger coverage.

Include a phrase or synonym that distinguishes this skill from sibling axllm skills (e.g., naming the memory/skills subsystem explicitly versus other axllm subsystems) to further reduce overlap risk.

Dimension	Reasoning	Score
Specificity	The description names the domain (Rust with `axllm`) and five concrete capability areas ("agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking"), but omits other features the body covers (relevanceRanking, contextMap, state export/restore), leaving minor coverage gaps rather than comprehensive coverage.	4 / 5
Completeness	The "Use when..." trigger clause is explicit and concrete, and the topic list implies the what, but the description never separately states what the skill provides (API guidance and examples for these subsystems); both what and when are present with one less explicit, matching anchor 4 rather than 5.	4 / 5
Trigger Term Quality	Terms a user of this package would naturally say — "Rust", "axllm", "agent memory", "skill discovery" — are present and distinctive, but common synonyms and variations (e.g., "skills catalog", "relevance hints", "context map") are missing, so keyword coverage is good rather than comprehensive.	4 / 5
Distinctiveness Conflict Risk	The trigger is gated on the niche package name `axllm`, which avoids conflicts with generic skills, but that same gate would be shared with sibling axllm-Rust skills, leaving minor overlap risk with closely related skills rather than the minimal risk of anchor 5.	4 / 5
	Total	16 / 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/rust/skills/ax-rust-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.