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

75%

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 ./packages/python/skills/ax-python-agent-rlm/SKILL.md

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is concise and well-organized but falls short on actionability and workflow clarity: the core code example is incomplete and the API surface lacks signatures, while there is no explicit sequence or validation for choosing between runtime profiles and transports.

Suggestions

Make the Core Pattern example complete and copy-paste ready by showing how `llm` is obtained (or pointing to the exact examples/ file), so the code runs as written.

Add signatures or one-line usage for each item in the Relevant API Surface (e.g., `agent`, `AxAgent`, `ProcessCodeRuntime`, `RuntimeEnvelope`) instead of listing bare names.

Provide a short decision sequence for choosing a runtime profile and transport (e.g., no-key for local checks vs provider-api when credentials exist) with a validation step to test the chosen runtime, which would raise workflow clarity.

Either bundle the referenced files (`API.md`, `axir-api.json`, `axir-capabilities.json`, `examples/`) in references/ and link to them, or remove the dangling references so progressive disclosure is not undermined by missing files.

Dimension	Reasoning	Score
Conciseness	The body is lean — short bullets, a single compact code pattern, and terse facts like "Real network support: yes" with no padding or explanation of concepts Claude already knows, matching the anchor for lean, efficient content where every token earns its place.	3 / 3
Actionability	It gives concrete code (`from axllm import agent` ... `helper.forward(...)`) and specific package facts, but the example is incomplete — `llm` is undefined and the Relevant API Surface lists names with no signatures or usage — matching the anchor for concrete guidance that is incomplete and missing key details rather than copy-paste-ready code.	2 / 3
Workflow Clarity	It lists when-to-use bullets and guardrails but does not sequence the multi-part decisions implied by runtime profiles and transports, and has no validation/checkpoint guidance, matching the anchor for steps present but checkpoints missing or implicit rather than a clear sequence with explicit validation.	2 / 3
Progressive Disclosure	The body is organized into clear sections, but it names referenced files (`API.md`, `axir-api.json`, `axir-capabilities.json`, `examples/`) that are not present in any bundle directory and are not signaled as navigable links, matching the anchor for some structure with references that are not clearly signaled rather than well-signaled one-level-deep references.	2 / 3
	Total	9 / 12 Passed

Description

85%

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 is specific, complete, and well-distinguished with an explicit 'Use when' trigger. Its main weakness is trigger-term naturalness: the jargon-heavy phrasing would rarely match what a user actually says, capping trigger quality at 2.

Suggestions

Add natural-language trigger phrases a user would actually say (e.g., 'write a Python Ax agent', 'set up a process code runtime', 'use the axllm package') alongside the current technical terms to improve trigger-term quality.

Consider leading with the plain-language task before the internal jargon so the most natural trigger comes first.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — "writing Python code with `axllm`", "RLM executor loops", "AxCodeRuntime sessions", "runtime envelopes", "process runtimes", and "runtime profiles" — matching the anchor for listing multiple specific capabilities rather than naming only a domain and some actions.	3 / 3
Completeness	It explicitly states what ("writing Python code with `axllm` for [tasks]") and an explicit when trigger ("Use when..."), matching the anchor that clearly answers both what and when with explicit triggers rather than having when missing or implied.	3 / 3
Trigger Term Quality	It has relevant keywords ("writing Python code", "axllm", "runtime") but leans heavily on internal jargon ("RLM executor loops", "runtime envelopes") that a user would not naturally say, so it matches the anchor for some relevant keywords missing common variations rather than full natural coverage.	2 / 3
Distinctiveness Conflict Risk	The named runtime terms (`axllm`, AxCodeRuntime, RLM executor loops) form a clear niche unlikely to fire for unrelated skills, matching the anchor for a clear niche with distinct triggers rather than being generic or overlapping.	3 / 3
	Total	11 / 12 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: packages/python/skills/ax-python-agent-rlm/SKILL.md
Commit: fe8baf8

Reviewed: 5 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.