ax-cpp-agent-context

Use when writing C++ code with `axllm` for deciding between context maps, trajectory context policy, offline optimization (ACE/GEPA), and memory recall for long-context agents.

Quality

81%

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

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized, token-efficient overview that points cleanly to package references, but its inline code example is not fully runnable and the routing guidance lacks a concrete decision rule.

Suggestions

Make the Core Pattern fully runnable: show the required includes and how `llm` is constructed, or explicitly note that provider setup lives in `examples/`, so the snippet is copy-paste ready.

Replace the generic 'route to the right feature' with a concrete decision rule in 'When To Use' (e.g., 'use contextMap when …, contextPolicy when …, optimization/ACE-GEPA when …, recall when …').

Expand the Relevant API Surface beyond bare symbol names with minimal signatures or one-line usage so Claude can call them without first opening API.md.

Dimension	Reasoning	Score
Conciseness	The body is lean and dense with useful facts (Package Facts, a code pattern, an API surface list, guardrails) and avoids explaining concepts Claude already knows; nearly every token earns its place.	3 / 3
Actionability	The Core Pattern gives concrete C++ but is not copy-paste ready — `llm` is undefined and no includes/setup are shown — and the Relevant API Surface lists bare symbol names without signatures, leaving key details missing per the level-2 anchor.	2 / 3
Workflow Clarity	'When To Use' offers routing guidance but no concrete decision procedure for choosing among contextMap, contextPolicy, optimization, and recall (the directive 'route to the right feature' is vague), and there is no explicit sequence or checkpoints.	2 / 3
Progressive Disclosure	The body is a concise overview organized into well-labeled sections with one-level-deep, clearly signaled references to package artifacts (API.md, axir-capabilities.json, examples/), matching the level-3 anchor; no bundle files are present so it is scored on organization and signaled references.	3 / 3
	Total	10 / 12 Passed

Description

90%

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-targeted description with an explicit 'Use when' trigger and concrete feature keywords; its only weakness is that the core action ('deciding between') is abstract rather than a set of concrete operations.

Dimension	Reasoning	Score
Specificity	It names the domain (C++ with axllm, long-context agents) and lists four feature areas (context maps, trajectory context policy, offline optimization ACE/GEPA, memory recall), but the action verb 'deciding between' is abstract rather than concrete operations like extract/fill/merge, so it stops short of the level-3 anchor.	2 / 3
Completeness	It has an explicit 'Use when ...' trigger (the when) and states what it helps with ('deciding between ... for long-context agents'), explicitly answering both what and when as the level-3 anchor requires.	3 / 3
Trigger Term Quality	The clean entry trigger 'Use when writing C++ code with `axllm`' plus the feature keywords (context maps, optimization ACE/GEPA, memory recall, long-context agents) give good coverage of the natural terms a user of this niche package would say.	3 / 3
Distinctiveness Conflict Risk	The combination of C++ + axllm + long-context agents + the named features is a narrow, clearly-bounded niche with distinct triggers that is unlikely to fire for an unrelated skill.	3 / 3
	Total	11 / 12 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-context/SKILL.md
Commit: 9087a01

Reviewed: 5 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.