CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ax-go-agent-rlm

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for RLM executor loops, AxCodeRuntime sessions, runtime envelopes, process runtimes, and optional runtime profiles.

Quality

82%

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

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.

A lean, well-organized body that supplies only non-obvious package facts and clear guardrails, weakened mainly by an incomplete core code example. Fixing the snippet's undefined `llm`, missing imports, and the ax/axllm prefix inconsistency would make the guidance copy-paste ready.

Suggestions

Make the Core Pattern snippet fully executable: show the import statement, define or parameterize `llm`, and wrap it in a complete function.

Reconcile the package prefix inconsistency between the code example (`ax.NewAgent`, `ax.Forward`) and the Relevant API Surface list (`axllm.NewAgent`, `axllm.AxAgent`).

Add a brief ordering for the 'When To Use' tasks (e.g., pick transport via no-key vs provider-api, then adapt the closest example) so multi-step wiring work has an explicit sequence.

DimensionReasoningScore

Conciseness

The body contains only package-specific facts Claude cannot know ("Real network support: yes", "Runtime profiles: `javascript-goja`", the TypeScript-API warning) with no padding or explanation of known concepts; every token earns its place.

5 / 5

Actionability

The Core Pattern snippet is concrete Go but not executable — `llm` is undefined, imports are absent, and the package prefix is inconsistent (`ax.NewAgent` in the snippet vs `axllm.NewAgent` in the API surface) — and most guidance directs the reader to look at package examples rather than giving complete steps.

3 / 5

Workflow Clarity

As a simple single-purpose skill under 50 lines with no destructive or batch operations it avoids the validation cap, and the Guardrails act as decision rules (no-key vs provider-api), but the multi-construct tasks in 'When To Use' (wire a runtime, use a profile) lack any explicit ordering or checkpoints.

4 / 5

Progressive Disclosure

No bundle files exist, and under the under-50-lines exception well-organized sections suffice; sections are clear, the referenced package artifacts (API.md, axir-api.json, examples/) are clearly signaled external facts, and there are no nested references.

5 / 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, tightly-scoped description that names the exact package and five concrete capability areas with an explicit 'Use when' trigger. Its main limitation is that the 'what' is only implied inside the when-clause and a few natural synonym terms (e.g., "Ax", "agent framework") are absent.

DimensionReasoningScore

Specificity

The description names one action ("writing Go code") but backs it with five concrete capability objects ("RLM executor loops, AxCodeRuntime sessions, runtime envelopes, process runtimes, and optional runtime profiles"), matching the anchor for several specific items with minor gaps rather than comprehensive multiple distinct actions.

4 / 5

Completeness

The 'when' is explicit ("Use when writing Go code with `github.com/ax-llm/ax/packages/go`...") and the 'what' (writing Go code for the five listed constructs) is present, but the what is folded into the when-clause instead of being stated as its own capability sentence with distinct concrete triggers.

4 / 5

Trigger Term Quality

Terms like "Go code", "AxCodeRuntime", "RLM", "runtime profiles", and the full package path are exactly what a user of this package would naturally say, but common variations such as "Ax" or "agent framework" are missing, so coverage is good rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

The exact package path and niche construct names (AxCodeRuntime, runtime envelopes, javascript-goja profiles) form a clear, distinct trigger with minimal conflict risk against any other skill.

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

Path

packages/go/skills/ax-go-agent-rlm/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.