CtrlK
BlogDocsLog inGet started
Tessl Logo

ax-go-refine

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for reward-scored generation, iterative candidate improvement, evaluator feedback, and optimizer-backed refinement patterns.

62

Quality

78%

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 ./packages/go/skills/ax-go-refine/SKILL.md
SKILL.md
Quality
Evals
Security

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 concise, well-structured overview whose main weakness is actionable correctness: the single code example contradicts the listed API surface (ax.NewGEPA vs axllm.AxGEPA) and lacks a complete, copy-paste-ready workflow. Structure and token efficiency are solid.

Suggestions

Reconcile the Core Pattern snippet with the Relevant API Surface: either use the axllm-prefixed identifiers (axllm.AxGEPA, axllm.Optimize) in the code example or explain the ax vs axllm aliasing.

Add one complete, runnable example (imports, client setup, request, evaluator, engine construction, Optimize call) so the core pattern is copy-paste ready instead of schematic.

Add a short sequenced workflow section (pick optimizer → construct engine → wire evaluator → run → inspect result) with a verification checkpoint such as checking result artifacts or falling back to package examples on failure.

DimensionReasoningScore

Conciseness

The body is lean and sectioned with no concept explanations, but the opening line repeats the frontmatter description and 'Language: Go' duplicates information already in the header and import path — minor trimmable instances.

4 / 5

Actionability

The Core Pattern snippet uses 'ax.NewGEPA' while the API Surface lists 'axllm.AxGEPA' and 'axllm.Optimize', an inconsistency that makes the example non-executable as written; inputs like reflectionClient and evaluator are undefined and no complete runnable example is shown inline.

3 / 5

Workflow Clarity

The skill lists use cases and guardrails but never sequences the steps of an actual refinement loop (choose optimizer, construct engine, wire evaluator, run, inspect result), so the reader gets orientation without an executable path; no validation checkpoints appear either.

3 / 5

Progressive Disclosure

Sections are short and well-organized with clearly signaled references ('API.md', 'axir-api.json', 'axir-capabilities.json', 'examples/'), but those paths are package-relative rather than skill-bundle paths, leaving minor navigation ambiguity about where the files live.

4 / 5

Total

14

/

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: it pairs an explicit 'Use when' trigger with the exact Go package path and a list of concrete capabilities. Its only weaknesses are mild abstraction in 'refinement patterns' and a few missing natural synonyms.

DimensionReasoningScore

Specificity

The description names the domain and several concrete capabilities ('reward-scored generation, iterative candidate improvement, evaluator feedback, and optimizer-backed refinement patterns'), but 'refinement patterns' is somewhat abstract, leaving minor coverage gaps.

4 / 5

Completeness

It explicitly answers 'when' via 'Use when writing Go code with github.com/ax-llm/ax/packages/go' and 'what' via the enumerated capability list, both with concrete trigger phrases. Both elements are explicit rather than implied, matching the top anchor.

5 / 5

Trigger Term Quality

Natural phrases like 'writing Go code', 'evaluator feedback', 'optimizer', and 'refinement' would plausibly appear in user requests, and the 'Use when' construction is a natural trigger. A few common synonyms (e.g., 'improve output', 'optimize prompts') are missing, so it falls just short of comprehensive.

4 / 5

Distinctiveness Conflict Risk

The full import path 'github.com/ax-llm/ax/packages/go' carves out a clear niche tied to one specific package, making accidental triggering for unrelated skills very unlikely.

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.