CtrlK
BlogDocsLog inGet started
Tessl Logo

ax-cpp-agent-rlm

Use when writing C++ code with `axllm` for RLM executor loops, AxCodeRuntime sessions, runtime envelopes, process runtimes, and optional runtime profiles.

64

Quality

80%

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 ./website/static/cpp/.well-known/agent-skills/ax-cpp-agent-rlm/SKILL.md
SKILL.md
Quality
Evals
Security

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 lean, well-structured overview for a niche C++ package API: excellent token efficiency, real code in the core pattern, and clearly signaled external docs. Weaknesses are minor — an incomplete code snippet (undefined llm), one misplaced bullet in When To Use, and bare-name references without paths.

Suggestions

Make the Core Pattern executable: show the includes and how `llm` is constructed (e.g. with the no-key transport), or explicitly point to the specific example file that shows a complete runnable program.

Move "Explain that generated packages are not TypeScript transpilers" out of When To Use into Guardrails where it belongs as a behavioral rule.

Give referenced files explicit paths relative to the package root (e.g. `axllm/API.md`, `axllm/examples/`) so navigation is unambiguous.

DimensionReasoningScore

Conciseness

The ~40-line body is lean and entirely package facts: "Language: C++", "Real network support: yes", "Runtime profiles: `javascript-quickjs`, `python-pyodide`". No concept Claude already knows is explained, no padding, and every token carries package-specific information. It clearly matches the anchor 5 example of lean, efficient content.

5 / 5

Actionability

The Core Pattern gives real C++ syntax ("axllm::agent("question:string -> answer:string")", "helper.forward(llm, {...})") plus concrete symbol names in the API Surface section and directives like "Use `no-key` examples for deterministic local checks". It is not a 5 because the snippet is not copy-paste ready — `llm` is undefined, no includes or setup are shown — which is only partially mitigated by the pointer to start from package examples.

4 / 5

Workflow Clarity

As a single-purpose reference skill under 50 lines with well-organized sections it would qualify for 5 under the simple-skill exception, but there are minor clarity gaps: the "When To Use" bullet "Explain that generated packages are not TypeScript transpilers; they adapt the Ax runtime contract" is a behavioral instruction misplaced in a trigger list, and no first concrete step (which example to open, which manifest to check) is sequenced.

4 / 5

Progressive Disclosure

Structure is good: the body stays an overview (core pattern, compact API list) and the Package Facts section clearly signals where the deep material lives ("API.md and axir-api.json", "axir-capabilities.json", "examples/"). It falls short of 5 because those references are bare backtick names with no resolvable path or link — relative to the package is only implied — leaving minor navigation ambiguity.

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 distinctive, well-targeted trigger description for a niche package, with good keyword coverage of its API names. Its main weakness is that it is entirely a "Use when..." clause — the skill's actual action is never stated, leaving completeness as the weakest dimension.

Suggestions

Lead with a what-clause before the trigger, e.g. "Provides API usage, capability-manifest guidance, and runnable examples for writing C++ code with the generated package `axllm`. Use when...".

Add body-only trigger terms to the description (ProcessCodeRuntime, actor-code sessions) so users naming those also match.

Name one concrete skill action (e.g. wiring an AxCodeRuntime session or using a runtime profile) so the what is explicit, not just implied.

DimensionReasoningScore

Specificity

The description names the domain ("writing C++ code with `axllm`") and lists several concrete capability areas ("RLM executor loops, AxCodeRuntime sessions, runtime envelopes, process runtimes, and optional runtime profiles"), giving broad but not fully action-oriented coverage. It does not reach a 5 because the only action verb is "writing" — the items are topics rather than specific actions the skill performs, and it fits anchor 4 (several specific items, minor gaps) better than anchor 3 (only 1-2 concrete actions).

4 / 5

Completeness

The "when" is fully explicit ("Use when writing C++ code with `axllm` for..."), but the "what" is never directly stated — the description opens with the trigger clause and only implies the skill's purpose through the enumerated topics. This sits between anchor 2 (only 'when' present) and anchor 4 (both explicit); the enumerated areas partially convey the what, warranting the midpoint.

3 / 5

Trigger Term Quality

Key natural terms for this niche are present: "C++", "axllm", "AxCodeRuntime", "runtime profiles", "process runtimes", "RLM executor loops". It stays at 4 rather than 5 because a few related trigger terms (e.g. ProcessCodeRuntime, actor-code sessions) appear only in the body, and no synonyms or extensions are covered.

4 / 5

Distinctiveness Conflict Risk

The description is anchored to highly specific identifiers (`axllm`, AxCodeRuntime, RLM) that only apply to this package, giving it a clear niche with distinct triggers and minimal conflict risk with any other skill.

5 / 5

Total

16

/

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
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.