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.

Quality

71%

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 ./website/static/python/.well-known/agent-skills/ax-python-agent-rlm/SKILL.md

Quality

Content

61%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 tightly written, well-sectioned reference sheet with excellent token efficiency, but it functions as a stub: its code example is not runnable, and its entire detail layer (API docs, capability manifest, examples) points to files missing from the bundle. The structure is good; the substance behind the pointers is not there.

Suggestions

Ship the referenced bundle files (`API.md`, `axir-api.json`, `axir-capabilities.json`, `examples/`) or rewrite the body to be self-contained; dangling pointers make the detail layer unusable.

Make the Core Pattern runnable: show how `llm` is constructed/imported, or label the snippet as a shape to adapt from `examples/`.

Add a short sequenced workflow (e.g., 1. check `axir-capabilities.json` for the target runtime, 2. start from the matching `examples/` entry, 3. verify with a no-key transport) so the guardrails become an ordered path rather than scattered rules.

Dimension	Reasoning	Score
Conciseness	The body is lean fact-lists and a minimal code snippet with zero padding — no explanations of concepts Claude already knows (no 'what is a runtime' prose), matching the anchor 'every token earns its place'. Minor duplication of the profile names between Package Facts and Relevant API Surface is not enough to drop it to 4.	5 / 5
Actionability	The Core Pattern is incomplete: `out = helper.forward(llm, ...)` references an undefined `llm` with no setup shown, so it is not executable as written. The 'Relevant API Surface' only names symbols without usage, and every pointer to concrete guidance (`API.md`, `axir-api.json`, `axir-capabilities.json`, `examples/`) references files that do not exist in the skill bundle, matching anchor 3's 'missing key details'.	3 / 5
Workflow Clarity	There is no sequenced flow for the skill's core use case — e.g., pick a runtime profile, consult the capabilities manifest, construct the runtime, build the envelope — the guidance is scattered across When To Use, Package Facts, and Guardrails. Validation appears only implicitly as guardrails ('Use no-key examples for deterministic local checks'), matching anchor 3's 'sequence present but checkpoints missing or implicit'.	3 / 5
Progressive Disclosure	The body cites `API.md`, `axir-api.json`, `axir-capabilities.json`, and `examples/` as its detail layer, but none of these files exist in the bundle — all references are dangling, making navigation to deeper detail impossible. This matches anchor 2 ('references are buried' / minimal usable structure); the short-skill exception does not apply because external references are claimed but absent.	2 / 5
	Total	13 / 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 distinct, trigger-rich description for a narrow niche, with an explicit 'Use when' clause. Its main weakness is that it enumerates target contexts rather than concrete actions, leaving the 'what' somewhat under-specified. Overall solid but not exemplary.

Dimension	Reasoning	Score
Specificity	Names the domain ("writing Python code with `axllm`") and several specific targets ("RLM executor loops, AxCodeRuntime sessions, runtime envelopes, process runtimes"), but offers only a single action — writing code — whereas anchor 4 requires several distinct concrete actions like 'extracts', 'fills', 'converts'.	3 / 5
Completeness	Both 'what' and 'when' are present — "writing Python code with `axllm` for RLM executor loops..." states the what and the explicit "Use when..." clause provides concrete triggers. However, the 'what' is thin (one generic action verb) and the 'when' enumerates contexts rather than user-request trigger phrases, so it sits between anchors 4 and 5, closer to 4.	4 / 5
Trigger Term Quality	Good natural keyword coverage: "Python code", "axllm", "RLM executor loops", "AxCodeRuntime sessions", "runtime envelopes", "process runtimes", "runtime profiles" are terms a user of this niche would say. A few natural terms are missing (e.g., AxCodeSession, actor-code sessions, streaming), keeping it below the comprehensive-synonym anchor 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche with distinct triggers (axllm, AxCodeRuntime, runtime envelopes) that are unlikely to collide with other skills, but the broad opening "Use when writing Python code" carries minor overlap risk with general Python-development skills, matching anchor 4 rather than the minimal-conflict anchor 5.	4 / 5
	Total	15 / 20 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: website/static/python/.well-known/agent-skills/ax-python-agent-rlm/SKILL.md
Commit: 3f630a0

Reviewed: 3 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.