ax-cpp-agent-memory-skills

Use when writing C++ 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 ./website/static/cpp/.well-known/agent-skills/ax-cpp-agent-memory-skills/SKILL.md

Quality

Content

68%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, information-dense reference skill: package facts, lifecycle semantics, concrete API names, example paths, and useful guardrails, with almost no wasted tokens. Its weaknesses are the absence of an explicit step-by-step workflow with validation checkpoints and inline version-sensitive details that belong in a compatibility/deprecated section.

Suggestions

Add a short ordered workflow (e.g., 1. check axir-capabilities.json, 2. adapt the matching example from examples/, 3. run the no-key transport for a local check) with an explicit validation checkpoint to raise workflow clarity.

Move the 24.x/25.0.0 contextMap compatibility details into a dedicated 'Legacy / compatibility' or 'Old patterns' section so version-sensitive facts do not penalize the main content.

Include a minimal complete snippet showing how `llm` is obtained and a one-line catalog search example so the core pattern is copy-paste runnable without consulting external docs.

Dimension	Reasoning	Score
Conciseness	The body is dense and factual with no padding of concepts Claude already knows, and every line carries package-specific information. It falls short of 5 due to version-sensitive details inline ("Since 25.0.0 the text and item ids follow TypeScript's format...") rather than in a dedicated old-patterns/deprecated section, plus a few overlong sentences in the contextMap bullet.	4 / 5
Actionability	Concrete guidance throughout: an executable core pattern ("axllm::agent(\"question:string -> answer:string\")"), named API symbols, real example file paths, and specific guardrails. Minor gaps remain — the code snippet omits how `llm` is constructed and the catalog search flow shows no call example.	4 / 5
Workflow Clarity	The body is organized by topic (lifecycle, state, API surface, guardrails) rather than as a sequenced workflow; there is no explicit step order or validation checkpoint for tasks like using the no-key examples for local checks. Guardrails partially compensate, so it stays at the "sequence implicit / checkpoints missing" anchor rather than dropping to 2.	3 / 5
Progressive Disclosure	Sections are clearly headed and detailed material (API.md, axir-api.json, runnable examples, website gallery) is pointed to one level deep instead of being inlined, which is appropriate. It does not reach 5 because the body is slightly above the simple-skill threshold, no in-bundle reference files exist to verify navigation, and the API-surface section is a bare list without links.	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 description with an explicit trigger clause, a named niche domain, and several concrete capability areas. Its main weakness is that the "what" is expressed as jargon-adjacent capability nouns rather than crisp concrete actions, and it lacks synonym-level trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ("writing C++ code with `axllm`") and lists several concrete capability areas ("agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking"), with only minor coverage gaps. It falls short of 5 because these are capability nouns rather than a comprehensive set of concrete actions, and above 3 because it names far more than 1-2 actions.	4 / 5
Completeness	Both parts are present: an explicit "Use when writing C++ code with `axllm`" trigger and a what (the listed memory/skill features). The "when" is explicit but the "what" is stated as capability areas rather than concrete actions, keeping it below the fully explicit 5 anchor.	4 / 5
Trigger Term Quality	Natural phrases a user would say are present ("writing C++ code", "agent memory", "skill discovery", "axllm"), giving good keyword coverage. A few natural variations are missing and some terms lean technical ("loaded-skill state", "used-skill tracking"), so it is not the comprehensive synonym-level coverage of a 5.	4 / 5
Distinctiveness Conflict Risk	The description is tightly bound to the niche `axllm` C++ package and its specific feature set, giving it a clear trigger niche with minimal risk of firing for unrelated skills.	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: website/static/cpp/.well-known/agent-skills/ax-cpp-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.