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

70%

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-context/SKILL.md

Quality

Content

65%Weight 40%Scale 1-3

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

The body is admirably concise and well-organized with a useful API surface and guardrails, but the core code example is incomplete and the referenced bundle files do not exist in the skill directory. Adding a runnable example and providing the referenced files would lift the weaker dimensions.

Suggestions

Provide a complete, runnable Core Pattern example that defines `llm` (e.g. a `no-key` scripted transport) so the snippet is copy-paste ready and lifts actionability.

Add the referenced bundle files (API.md, axir-api.json, axir-capabilities.json, examples/) under references/ or assets/, or remove the references if they are not shipped, so progressive-disclosure navigation resolves to real files.

Add a short explicit decision sequence with a validation checkpoint (e.g. 'pick the feature, verify against axir-capabilities.json, then proceed') to improve workflow clarity for the routing task.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence with no padded explanations of basic concepts; every section ('Package Facts', 'Core Pattern', 'Relevant API Surface', 'Guardrails') earns its place, matching anchor 3.	3 / 3
Actionability	Provides an executable Core Pattern snippet and a concrete API surface list, but the example is illustrative (`helper.forward(llm, ...)` uses an undefined `llm`) and there are no concrete commands beyond it, matching anchor 2 rather than the copy-paste-ready anchor 3.	2 / 3
Workflow Clarity	'When To Use' gives routing guidance and Guardrails list safety rules, but there is no explicit sequenced process with validation checkpoints for the routing decision, matching anchor 2; not 1 because the routing guidance is present.	2 / 3
Progressive Disclosure	The body signals references to API.md, axir-api.json, axir-capabilities.json, and examples/, but no references/scripts/assets bundle files actually exist, so the signaled one-level-deep navigation is not realizable in the actual bundle structure, matching anchor 2.	2 / 3
	Total	9 / 12 Passed

Description

75%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise and clearly states both what it does and when to use it, with a distinct, low-conflict niche. It is slightly held back by naming decision topics rather than concrete actions and by SDK-internal trigger terms.

Dimension	Reasoning	Score
Specificity	Names the domain (C++ with `axllm`) and several concrete decision areas ('context maps, trajectory context policy, offline optimization (ACE/GEPA), and memory recall'), but these are noun-phrases naming topics rather than concrete actions, matching anchor 2.	2 / 3
Completeness	Explicitly answers what ('deciding between context maps, trajectory context policy, offline optimization (ACE/GEPA), and memory recall') and when ('Use when writing C++ code with `axllm`') with an explicit trigger clause, matching anchor 3; not 2 because the when is explicit rather than implied.	3 / 3
Trigger Term Quality	Includes the natural-ish trigger 'Use when writing C++ code with `axllm`' and relevant terms ('offline optimization (ACE/GEPA)', 'memory recall', 'long-context agents'), but the keywords are SDK-specific and miss common user-facing variations, matching anchor 2.	2 / 3
Distinctiveness Conflict Risk	Targets a clear niche (C++ codegen with `axllm` for context-selection decisions) with distinct triggers, making it unlikely to fire for unrelated skills, matching anchor 3.	3 / 3
	Total	10 / 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: 9 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.