CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ax-cpp-llm

Use when writing C++ code with `axllm` for using the generated Ax package, factory functions, package docs, examples, and API reference.

Quality

76%

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-llm/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

The body is an exemplary router-style entry point: a lean task-indexed table pointing to 16 real, one-level-deep reference files, followed by a short list of essential conventions including an explicit version-check checkpoint. The only minor improvements are trimming one vague bullet and optionally inlining a minimal code snippet.

DimensionReasoningScore

Conciseness

The ~35-line body is lean and assumes Claude's competence — a routing table plus short conventions with no concept explanations — but minor filler like 'Specialist skills remain optional when separate skill entries are useful' could be trimmed, keeping it just below anchor 5.

4 / 5

Actionability

Concrete routing guidance with exact file paths per task and specific artifacts to consult ('API.md', 'axir-api.json', 'axir-capabilities.json'); for an instruction-only router skill the absence of code is not penalized, though a minimal inline usage snippet would close the remaining gap to anchor 5.

4 / 5

Workflow Clarity

A clear sequence is present — pick a guide from the table, read it before writing code, check the installed package version against the guide version, then use the native API — with an explicit version-check checkpoint; no error-recovery feedback loop is needed or provided, matching anchor 4.

4 / 5

Progressive Disclosure

Verified against the actual bundle: all 16 referenced paths exist in references/, no reference links deeper into other references (one level deep), the task-to-file table clearly signals navigation, and the body is a concise overview — a clean match to anchor 5.

5 / 5

Total

17

/

20

Passed

Description

65%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.

The description has a clear niche and an explicit trigger clause, but its phrasing is grammatically convoluted ('with `axllm` for using the generated Ax package') and it lists resources instead of stating concrete capabilities. It reads as a 'when' clause with an appended artifact list rather than a what+when statement.

Suggestions

Lead with a concrete capability statement in third person (e.g., 'Write C++ code with the generated `axllm` package: native factory functions, signatures, generators, agents, and flows.'), then follow with the 'Use when' clause.

Replace the generic resource list ('package docs, examples, and API reference') with the concrete functional areas the skill covers (providers, structured generation, agents, flows, optimizers) so the 'what' is explicit.

Add a few natural trigger synonyms users might say, such as 'Ax for C++', 'axllm', or 'Ax LLM in C++', to broaden keyword coverage.

DimensionReasoningScore

Specificity

Names the domain ('writing C++ code with `axllm`') and one concrete action, but the remainder ('for using the generated Ax package, factory functions, package docs, examples, and API reference') is a list of resources rather than concrete actions, so coverage is not comprehensive as anchor 4 requires.

3 / 5

Completeness

The 'when' is explicit ('Use when writing C++ code with `axllm`'), but the 'what' is only weakly articulated through a muddled artifact list rather than a clear capability statement, placing it just below anchor 4's 'both what and when' standard.

3 / 5

Trigger Term Quality

Good natural-term coverage — 'C++', 'axllm', 'Ax package', 'factory functions', 'API reference' are terms a user of this package would naturally say — but common synonyms and broader domain terms (e.g., 'Ax LLM', 'agents', 'signatures', 'prompts') are missing, short of anchor 5.

4 / 5

Distinctiveness Conflict Risk

Tightly scoped to C++ code using the specific `axllm` package, giving a clear niche with distinct triggers and minimal conflict risk with other skills.

5 / 5

Total

15

/

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.

Validation — 15 / 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

Path

packages/cpp/skills/ax-cpp-llm/SKILL.md

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.