CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

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/go/.well-known/agent-skills/ax-go-agent-rlm/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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 reference skill with sensible guardrails and appropriate deferral of detail to package docs, but its executable guidance has gaps: the core snippet is not copy-paste ready (undefined `llm`, inconsistent `ax`/`axllm` qualifiers) and there is no sequenced workflow or validation checkpoint for the runtime-wiring tasks it targets.

Suggestions

Make the Core Pattern example complete and copy-paste ready: include the import path, construct the `llm` argument it references, and resolve the `ax.NewAgent` vs `axllm.NewAgent` qualifier inconsistency with the 'Relevant API Surface' section.

Add a short numbered workflow for the main task, e.g. wiring an AxCodeRuntime session: consult `axir-capabilities.json` -> pick a matching example from `examples/` -> choose provider-api or no-key transport -> run and verify locally, so the sequence and validation checkpoint are explicit rather than implied by guardrails.

Trim tokens that duplicate the frontmatter, such as 'Language: Go' and the repeated package path in 'Package Facts', to push conciseness toward the top anchor.

DimensionReasoningScore

Conciseness

The body is efficient and assumes competence (no explaining what Go or RLM is; facts like 'Real network support: yes' are genuinely additive), but 'Language: Go' and 'Package: `github.com/ax-llm/ax/packages/go`' duplicate the title and description, and the intro paragraph restates the description — minor instances that could be trimmed, so not the every-token-earns-its-place anchor 5.

4 / 5

Actionability

'Core Pattern' provides concrete Go code, but it references an undefined `llm` variable, uses `ax.NewAgent` while 'Relevant API Surface' lists `axllm.NewAgent` (a package-qualifier inconsistency), and there is no code for the sessions, envelopes, or process runtimes the skill says it covers — key details are missing and execution is deferred to package examples/, matching the 'incomplete / missing key details' anchor rather than the 'minor gaps' anchor 4.

3 / 5

Workflow Clarity

Guardrails give useful decision rules ('Start from package examples', 'Use no-key examples for deterministic local checks') but the skill covers multiple tasks (wiring runtimes, sessions, envelopes) without any sequenced workflow or explicit validation checkpoint; the sequence is implicit at best, fitting anchor 3 rather than the clear-sequence anchor 4, and the simple-skill 5 exception does not apply since this is not a single-action skill.

3 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files and no need for external reference files; sections are well-organized (When To Use, Package Facts, Core Pattern, Relevant API Surface, Guardrails) and bulk detail is appropriately left in package-side docs (API.md, axir-capabilities.json, examples/), so the simple-skill condition for a top score is met.

5 / 5

Total

15

/

20

Passed

Description

87%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 description: third-person, explicit 'Use when' trigger clause tied to an exact package path, and a concrete enumeration of the constructs it covers. Its only weaknesses are minor missing synonyms/variations in trigger terms and coverage gaps relative to the full skill scope.

DimensionReasoningScore

Specificity

The description names the domain ('writing Go code with `github.com/ax-llm/ax/packages/go`') and enumerates five concrete areas ('RLM executor loops, AxCodeRuntime sessions, runtime envelopes, process runtimes, and optional runtime profiles'), going beyond the 1-2 actions of anchor 3 but omitting parts of the skill's actual scope (transports, examples, manifests), so it is not the comprehensive coverage of anchor 5.

4 / 5

Completeness

It explicitly answers both questions: the 'what' is concrete (writing Go code with the package for the five enumerated constructs) and the 'when' is an explicit trigger clause ('Use when writing Go code with `github.com/ax-llm/ax/packages/go` for ...') with concrete trigger phrases, matching the anchor-5 pattern; it is not the anchor-4 case because the 'when' is already explicit and specific.

5 / 5

Trigger Term Quality

Trigger terms are the natural vocabulary of this niche ('writing Go code', 'AxCodeRuntime sessions', 'runtime envelopes', 'RLM executor loops', 'runtime profiles'), giving good keyword coverage; a few natural terms users might say are missing (e.g. 'AxCode', 'goja', 'JavaScript runtime', 'Ax agent'), which keeps it below the comprehensive-with-synonyms anchor 5.

4 / 5

Distinctiveness Conflict Risk

The description is anchored to one exact package path and its specific class names (AxCodeRuntime, RuntimeEnvelope, ProcessCodeRuntime), creating a clear niche with distinct triggers and minimal conflict risk with any other skill.

5 / 5

Total

18

/

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.