CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ax-go-gepa

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for GEPA, Pareto tradeoffs, reflection clients, metric budgets, optimizer state, and artifacts.

Quality

71%

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-gepa/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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.

The body is dense with genuinely non-obvious domain knowledge and stays concise, but it is more of a fact sheet than an operational guide: the only code snippet is non-executable and internally inconsistent with the API listing, and no ordered workflow with validation checkpoints is given for what are budget-consuming batch optimizer runs. Referenced bundle files are also absent from the skill directory.

Suggestions

Make the Core Pattern snippet executable and consistent: show construction of a real reflection client, request, and evaluator (or point to a specific examples/ file), and reconcile the `ax.NewGEPA` vs `axllm.AxGEPA` prefix mismatch.

Add a short numbered workflow (e.g., 1. seed with BootstrapFewShot if demos needed, 2. run Optimize, 3. validate by comparing metadata.bestScore against baselineScore, 4. inspect artifact) with the comparison step as an explicit checkpoint.

Ship the referenced files (API.md, axir-api.json, axir-capabilities.json, examples/) in the bundle or remove/deweight the Package Facts pointers so no navigation path dangles.

DimensionReasoningScore

Conciseness

The body is mostly lean bullets and code — "Package: `github.com/ax-llm/ax/packages/go`", "Real network support: yes" — and nearly all of it is non-obvious domain knowledge (baseline score semantics, metric-call accounting, demo provenance) that Claude cannot already know. It stops short of anchor 5 because the opening paragraph and "When To Use" partially restate the frontmatter description, and "Relevant API Surface" is a bare name-list whose relevance is unexplained.

4 / 5

Actionability

The "Core Pattern" snippet (`engine := ax.NewGEPA(reflectionClient, nil)` / `result := engine.Optimize(request, evaluator)`) is structurally concrete but not executable — the variables are undefined placeholders — and it conflicts with the "Relevant API Surface" section, which uses the `axllm.` prefix (`axllm.AxGEPA`) while the snippet uses `ax.`. This matches anchor 3 ('some concrete guidance but incomplete ... missing key details') rather than anchor 4's mostly-executable guidance; the guardrails are behaviorally concrete but give no runnable entry point.

3 / 5

Workflow Clarity

Sequencing exists only implicitly: "Use BootstrapFewShot before GEPA when demonstrations should seed optimization" and "Compare metadata.bestScore with baselineScore" hint at order and verification, but no numbered workflow (bootstrap → optimize → inspect artifact → compare scores) is laid out. Optimizer runs are batch operations consuming capped metric budgets, so per the rubric's cap, missing explicit validation checkpoints holds this at anchor 3 ('sequence present but checkpoints missing or implicit') rather than 4.

3 / 5

Progressive Disclosure

Sections are well-organized for a short skill, and references are clearly signaled in a dedicated "Package Facts" section, but the referenced files — `API.md`, `axir-api.json`, `axir-capabilities.json`, `examples/` — are not present in the bundle (no references/, scripts/, or assets/ directories exist), so the navigation paths dangle. This lands at anchor 3 ('structure present, references present but not resolvable/well-placed') rather than 4, since a reader following the pointers finds nothing.

3 / 5

Total

13

/

20

Passed

Description

73%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.

The description is a strong, niche-scoped trigger: it names the exact package and the domain vocabulary a user would naturally say, with an explicit "Use when" clause. Its main weakness is that capabilities are expressed as topic areas rather than distinct concrete actions, leaving the 'what' implicit inside the 'when' phrasing.

Suggestions

State the skill's capabilities as concrete actions before the trigger clause, e.g., "Provides API patterns, package facts, and optimizer guardrails for the generated Ax Go package. Use when..."

Add one or two more natural trigger variations such as "ax", "prompt optimization", or "BootstrapFewShot" to broaden keyword coverage.

DimensionReasoningScore

Specificity

"Use when writing Go code with `github.com/ax-llm/ax/packages/go` for GEPA, Pareto tradeoffs, reflection clients, metric budgets, optimizer state, and artifacts" names the domain (Go code against a specific package) and a single generic action ("writing Go code") plus a list of topic areas rather than multiple distinct concrete actions. It exceeds anchor 2 ('names the domain but actions are minimal') because the enumerated topics narrow the scope, but it never reaches anchor 4's 'several specific actions' such as 'run the optimizer' or 'inspect artifacts'.

3 / 5

Completeness

Both what and when are present and explicit — "Use when writing Go code with [package] for GEPA, ..." — but the 'what' is merged into the 'when' clause rather than stated as the skill's own capabilities (e.g., 'Provides API patterns and guardrails for...'). This matches anchor 4 (both present, 'when'/'what' could be more explicit) rather than anchor 5's fully separated and concretely phrased what-and-when; the "Use when" clause keeps it above anchor 3's 'when missing or only weakly implied'.

4 / 5

Trigger Term Quality

Trigger terms like "Go code", "GEPA", "Pareto tradeoffs", "metric budgets", and "optimizer state" are exactly the words a user of this package would naturally say, and the explicit "Use when" phrasing is a natural trigger. It falls short of anchor 5 because common variations and looser synonyms (e.g., "ax", "prompt optimization", "demonstrations/bootstrapping") are absent.

4 / 5

Distinctiveness Conflict Risk

The trigger is scoped to one specific package path (`github.com/ax-llm/ax/packages/go`) and the niche GEPA/Pareto optimizer vocabulary, giving a clear niche with distinct triggers and minimal conflict risk with any other skill. It does not fall to anchor 4 because no closely related skill would realistically collide with a package-path-qualified trigger.

5 / 5

Total

16

/

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-gepa/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.