CtrlK
BlogDocsLog inGet started
Tessl Logo

ax-cpp-gen

Use when writing C++ code with `axllm` for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.

65

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./packages/cpp/skills/ax-cpp-gen/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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 well-organized, reasonably concise API-reference skill body with a solid core code pattern and useful guardrails. Its main gaps are the lack of an explicit sequenced workflow and references to bundle files (API.md, examples/, etc.) that are not present in the bundle.

Suggestions

Ship the referenced bundle files (API.md, axir-api.json, axir-capabilities.json, examples/) referenced in Package Facts, or remove the dangling references — currently the navigation points to files that do not exist.

Add one short runnable example each for the common cases (multi-sampling with a result picker, tool attachment) so the API surface sections are executable rather than only descriptive.

Frame a short explicit workflow (start from examples → core pattern → select options → validate against guardrails) so the operating sequence is unambiguous.

DimensionReasoningScore

Conciseness

The body is lean and avoids explaining concepts Claude already knows, but the dense 'Provider Forward Options' and 'Multi-Sampling' prose paragraphs pack in jargon that could be tightened.

4 / 5

Actionability

A concrete, copy-paste-ready core pattern is provided, and the API surface lists exact symbol names; however only one runnable example is given and the option/mode sections describe behavior in prose rather than executable snippets.

4 / 5

Workflow Clarity

A loose sequence is implied (start from examples, apply core pattern, choose options, respect guardrails) but it is not framed as an explicit sequenced workflow with validation checkpoints.

3 / 5

Progressive Disclosure

Sections are well organized and references (API.md, axir-api.json, examples/) are clearly signaled in a Package Facts block, but the referenced bundle files do not actually exist in the skill directory, leaving the navigation dangling.

3 / 5

Total

14

/

20

Passed

Description

92%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, concrete description that clearly states both what the skill does and when to use it, scoped to a distinct C++/AxGen niche. The only weakness is a slight reliance on technical jargon over natural user phrasing in its trigger vocabulary.

DimensionReasoningScore

Specificity

Enumerates many concrete actions — 'forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing' — giving comprehensive coverage of the skill's capabilities rather than vague abstraction.

5 / 5

Completeness

An explicit 'Use when ...' trigger clause answers 'when', and the enumerated capability list answers 'what', both concretely and explicitly.

5 / 5

Trigger Term Quality

'writing C++ code' and 'AxGen' are natural user terms, and the list includes several relevant capability keywords, though much of the remainder ('indexed multi-sampling', 'result pickers', 'assertions') is technical jargon a user would be less likely to say verbatim.

4 / 5

Distinctiveness Conflict Risk

Scoped tightly to 'C++ code with axllm for AxGen programs', a clear niche with distinct triggers and minimal overlap with other skills.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
ax-llm/ax
Reviewed

Table of Contents

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.