CtrlK
BlogDocsLog inGet started
Tessl Logo

ax-python-agent-optimize

Use when writing Python code with `axllm` for agent optimization, verified agent-playbook evolution, evaluators, judges, optimizer artifacts, BootstrapFewShot, and GEPA.

65

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/python/skills/ax-python-agent-optimize/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A concise, well-organized overview that assumes competence and points cleanly to deeper materials. It is weakest in actionability and workflow clarity, where the core example is illustrative rather than executable and the optimization workflow lacks explicit sequenced validation steps.

Suggestions

Make the Core Pattern example self-contained by showing how reflection_client, request, and evaluator are constructed, or explicitly mark the snippet as illustrative and link the runnable example to follow.

Add a short numbered optimization workflow with an explicit verification gate checkpoint (e.g. run -> evaluate -> drop proposals failing the gate -> re-run within budget) to improve workflow_clarity for batch optimization.

DimensionReasoningScore

Conciseness

Lean bullet-driven body that assumes Claude's competence — no padded concept explanations, and concrete package facts (runtime profiles, transport support) that Claude would not already know.

3 / 3

Actionability

Provides a code skeleton and a symbol list, but the Core Pattern uses undefined placeholders ('reflection_client', 'request', 'evaluator') rather than complete, copy-paste-ready code, deferring full detail to external examples.

2 / 3

Workflow Clarity

Tasks and a 'verification gate' are named, but the optimization process is not laid out as an explicit sequence with validation checkpoints, and batch optimization runs lack a documented validate-fix-retry feedback loop.

2 / 3

Progressive Disclosure

Well-organized overview under 50 lines that signals one-level-deep references (API.md, axir-api.json, examples/) without nesting or inlining large reference material.

3 / 3

Total

10

/

12

Passed

Description

85%Weight 40%Scale 1-3

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 specific, well-triggered description that answers both what and when for a distinct niche. Its main weakness is reliance on domain jargon over broadly natural user phrasing in the trigger terms.

Suggestions

Add a few natural-language variations users might say (e.g. 'few-shot examples', 'prompt optimization') alongside the technical terms to improve trigger_term_quality.

Consider spelling out one or two jargon terms (e.g. 'GEPA (genetic prompt optimization)') so the trigger is recognizable to users who know the concept but not the acronym.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — 'agent optimization, verified agent-playbook evolution, evaluators, judges, optimizer artifacts, BootstrapFewShot, and GEPA' — rather than vague language.

3 / 3

Completeness

Starts with an explicit 'Use when writing Python code with `axllm`' trigger (the when) and enumerates the concrete capabilities (the what), clearly answering both.

3 / 3

Trigger Term Quality

Includes some natural terms ('agent optimization', 'evaluators', 'judges') but is heavy on package jargon ('axllm', 'BootstrapFewShot', 'GEPA', 'agent-playbook evolution') and misses common variations like 'few-shot' or 'prompt optimization'.

2 / 3

Distinctiveness Conflict Risk

Scoped tightly to the `axllm` agent-optimization niche with distinctive triggers (GEPA, BootstrapFewShot, playbook evolution), making it unlikely to fire for the wrong skill.

3 / 3

Total

11

/

12

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.