CtrlK
BlogDocsLog inGet started
Tessl Logo

ax-agent-optimize

This skill helps an LLM generate correct AxAgent tuning and evaluation code using @ax-llm/ax. Use when the user asks about agent.optimize(...), judgeOptions, eval datasets, optimization targets, saved optimizedProgram artifacts, or agent optimization guidance.

67

Quality

81%

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

75%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 highly actionable skill body with multiple executable patterns and a clear goal-to-shape decision guide, weakened mainly by recurring overlapping rules across sections that hurt token efficiency. Structure is good for a single-file skill.

Suggestions

Consolidate the overlapping decision rules spread across 'Use These Defaults', 'Metric vs Judge', and 'Dataset And Judge Rules' into a single decision table to reduce redundancy and token cost.

Add an explicit validate->fix->retry feedback loop for artifact replay (e.g. restore, run held-out task, compare baseline vs optimized, re-tune if regression) to strengthen workflow clarity.

Consider moving the dense 'Eval Semantics' and 'Delegation Optimization Notes' rule lists into a separate reference file referenced one level deep from the body.

DimensionReasoningScore

Conciseness

Largely lean directive bullets with no concept-explanation padding, but decision guidance recurs across 'Use These Defaults', 'Decision Guide', 'Metric vs Judge', and 'Dataset And Judge Rules' with overlapping rules that could be consolidated; some tightening possible.

3 / 5

Actionability

Provides multiple complete, copy-paste-ready TypeScript patterns (Canonical, Minimal, Deterministic Metric, Built-In Judge, plain AxGen) covering the common cases with specific imports and runnable code.

5 / 5

Workflow Clarity

A clear decision guide maps user goals to optimization shapes, and artifact save/load plus eval-safe replay are sequenced; however explicit validate->fix->retry feedback loops are only implied rather than spelled out as checkpoints.

4 / 5

Progressive Disclosure

Well-organized into clearly headed sections (Decision Guide, Canonical Pattern, Minimal Pattern, etc.) with external example links; as a single-file skill with no bundle files it is appropriately structured, though a few dense rule sections could be split into reference files.

4 / 5

Total

16

/

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, specific description that clearly states what the skill does and when to use it, with concrete API trigger terms and good boundary discipline against a sibling skill. Minor synonym coverage is the only gap.

DimensionReasoningScore

Specificity

Names the concrete domain ('AxAgent tuning and evaluation code using @ax-llm/ax') and enumerates specific API surfaces (agent.optimize, judgeOptions, eval datasets, optimizedProgram artifacts), listing several specific actions with only minor coverage gaps.

4 / 5

Completeness

Explicitly answers both 'what' ('helps an LLM generate correct AxAgent tuning and evaluation code') and 'when' ('Use when the user asks about...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural trigger phrases a user would say ('agent.optimize(...)', 'judgeOptions', 'eval datasets', 'optimization targets', 'agent optimization guidance'); good keyword coverage with a few synonyms missing.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (AxAgent agent.optimize workflow) with distinct triggers and explicit boundary guidance (defers generic optimize() to the ax-gepa skill), minimizing conflict risk.

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.

Validation15 / 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.