CtrlK
BlogDocsLog inGet started
Tessl Logo

ax-python-agent-rlm

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

66

Quality

83%

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

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 reference skill: token-efficient facts, a concrete core pattern, and crisp guardrails with explicit decision rules, all under 50 lines. The gaps are executable completeness (the `llm` object in the Core Pattern is never shown how to be created) and unverifiable references — API.md, axir-api.json, axir-capabilities.json, and examples/ are cited but no bundle files exist to confirm them.

Suggestions

Show how to construct the `llm` argument in the Core Pattern (e.g., a `no-key` scripted transport setup) so the snippet is copy-paste executable, lifting actionability to the top anchor.

Add one line of ordering guidance (e.g., '1. Check `axir-capabilities.json` for the target runtime, 2. Copy the closest `examples/` example, 3. Adapt using `API.md`') to make the single workflow explicit.

Confirm the referenced files (`API.md`, `axir-api.json`, `axir-capabilities.json`, `examples/`) ship alongside the skill, or add a dedicated 'References' section pointing to them so navigation does not depend on the Package Facts list.

DimensionReasoningScore

Conciseness

Every section earns its tokens: "Package Facts" is a terse fact list, "Core Pattern" is a 4-line snippet, "Relevant API Surface" is bare symbol names, and "Guardrails" are single-line directives. No concept Claude already knows is explained (no 'what a runtime is' padding), matching anchor 5's 'lean and efficient; every token earns its place'.

5 / 5

Actionability

The Core Pattern is real, runnable-looking syntax ("helper = agent(...)" / "helper.forward(llm, {...})") and the Guardrails give executable directives ("Use `no-key` examples for deterministic local checks"). It is not anchor 5 because the snippet is not copy-paste ready — `llm` is used but never constructed or imported, so a key setup detail is missing; and "Relevant API Surface" lists symbols without any usage hint.

4 / 5

Workflow Clarity

As a reference-style skill it is not a multi-step process, and its single action is made largely unambiguous by the Core Pattern plus explicit decision rules ("Use `provider-api` examples only when the user explicitly has provider credentials" and "Start from package examples ... before inventing a new call shape"). It falls short of anchor 5 because there is no explicit ordering of how to proceed (e.g., check the capabilities manifest, then copy an example, then adapt) and no verification step for the code the agent produces.

4 / 5

Progressive Disclosure

The body is a well-organized overview that delegates detail via clearly signaled, flat, one-level-deep references ("Package API docs: `API.md` and `axir-api.json`", "Capability manifest: `axir-capabilities.json`", "Runnable examples: `examples/`"), matching the good-structure pattern of anchor 4. It does not reach 5 because no bundle files (references/, scripts/, assets/) are present to verify those paths resolve, and the reference list lives inside 'Package Facts' rather than a dedicated navigation section.

4 / 5

Total

17

/

20

Passed

Description

78%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, lean description: explicit 'Use when' trigger guidance plus five concrete, domain-specific capability areas that make it highly distinct. Its main weakness is that the 'what' is only implied — it never says what the skill provides (API guidance, runnable examples, manifests) — and it offers only one action verb, which keeps specificity and completeness just below the top anchors.

DimensionReasoningScore

Specificity

"Use when writing Python code with `axllm` for RLM executor loops, AxCodeRuntime sessions, runtime envelopes, process runtimes, and optional runtime profiles" names the domain (Python, `axllm`) and enumerates five concrete capability areas. It stops short of anchor 5 because only one action verb is offered ("writing") — there is no list of distinct actions like create/wire/explain — but it is well above anchor 3's '1-2 concrete actions', since the five named constructs give specific, non-generic coverage.

4 / 5

Completeness

An explicit "Use when ..." clause clearly answers 'when', and the enumerated areas ("RLM executor loops, AxCodeRuntime sessions, runtime envelopes, process runtimes, and optional runtime profiles") convey the 'what' substantially. It does not score 5 because the 'what' is implicit — the description never states what the skill itself provides (API guidance, examples, manifests) in the way anchor 5's 'Extract text and tables from PDF files, fill forms, merge documents' does; but it is clearly above the midpoint, well beyond anchor 2's 'only when without what'.

4 / 5

Trigger Term Quality

Trigger terms include "Python code", "axllm", "RLM executor loops", "AxCodeRuntime sessions", "runtime envelopes", "process runtimes", and "runtime profiles" — natural phrasing for a user working in this package's niche, and far above anchor 3's 'some relevant keywords' baseline. A few natural terms are missing (e.g., "AxCodeSession", "streaming", "QuickJS"/"Pyodide" profiles named in the body), so it does not reach anchor 5's comprehensive synonym/variation coverage.

4 / 5

Distinctiveness Conflict Risk

The terms "axllm", "RLM executor loops", "AxCodeRuntime", and "runtime envelopes" carve out a clear niche with distinct triggers; no generic phrasing ("helps with code") that would collide with other skills. This matches anchor 5's 'clear niche with distinct triggers; minimal conflict risk'.

5 / 5

Total

17

/

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.