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

80%

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

Quality

Content

82%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 dense, well-organized reference skill that respects the reader's intelligence and points to real package artifacts for detail. Its main gaps are the absence of any shown code beyond the two-line core pattern and no explicit validation checkpoint for verifying a call shape.

Suggestions

Add a short end-to-end snippet showing one observer or catalog callback wiring, since the Core Pattern only demonstrates forward() and the lifecycle behaviors are otherwise prose-only.

Add an explicit validation step in Guardrails (e.g., 'run the no-key example to confirm the call shape compiles and maps provider requests before extending it').

Trim the 'Relevant API Surface' symbol list to a few entry points and defer the full surface to API.md, which is already referenced under Package Facts.

Dimension	Reasoning	Score
Conciseness	Every bullet is package-specific fact (e.g., "Forward-time `skills` override constructor entries by normalized ID and remain loaded for later calls", "observer errors are ignored") with no padding and no explanation of concepts Claude already knows. All ~55 lines earn their place.	5 / 5
Actionability	The Core Pattern is copy-paste-ready (`axllm::agent("question:string -> answer:string")` plus `forward`), and concrete example paths like `src/examples/cpp/long-agents/skills_and_memory_assistant.cpp` are given. However, key flows such as observer registration and catalog callbacks are described but never shown in code.	4 / 5
Workflow Clarity	The guardrail "Start from package examples for exact native syntax before inventing a new call shape" gives an unambiguous primary action, and "Use `no-key` examples for deterministic local checks" serves as an implicit verification step. No explicit compile/run validation checkpoint exists, so it falls short of anchor 5.	4 / 5
Progressive Disclosure	The body is a lean overview with clearly signaled one-level-deep references (`API.md`, `axir-api.json`, `axir-capabilities.json`, `examples/`). The "Relevant API Surface" section inlines symbol lists that arguably belong in the API reference, a minor organization gap.	4 / 5
	Total	17 / 20 Passed

Description

70%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 specific, distinctive trigger description with good natural keywords that correctly uses third person. Its one structural weakness is that it is entirely a 'Use when' clause — the actual capability statement ('what this skill does') is only implied by the enumerated topics.

Suggestions

Lead with an explicit capability statement using action verbs (e.g., 'Guides writing C++ agent code with `axllm` for...') before the 'Use when' clause so both what and when are stated.

Add a few natural trigger synonyms that appear in the body, such as 'skills catalog', 'memories catalog', or 'AxAgent', to broaden keyword coverage.

Dimension	Reasoning	Score
Specificity	"agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking" lists five concrete capability areas, matching anchor 4's several-specific-items level. It stops short of anchor 5 because these are domain nouns with no action verbs stating what the skill does with them.	4 / 5
Completeness	"Use when writing C++ code with `axllm` for..." provides an explicit and detailed 'when', but the 'what' is only weakly implied by the topic list — the description never states what the skill does. This mirrors anchor 3's one-clear-one-weak pattern rather than anchor 4's both-present.	3 / 5
Trigger Term Quality	Terms like "writing C++ code", "axllm", "agent memory", and "dynamic skill discovery" are natural phrasings a user would plausibly say, giving good keyword coverage. A few natural variations used in the body (skills catalog, memories catalog, AxAgent) are missing, so it is not anchor 5.	4 / 5
Distinctiveness Conflict Risk	The `axllm` C++ package combined with the agent-memory/skills niche is a clear, highly specific trigger space with minimal overlap risk against other skills, matching anchor 5.	5 / 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/cpp/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.