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%

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

The body is concise and well-structured with clearly signaled references to deeper package materials. Its weaker dimensions are actionability (the inline code is a sketch, not copy-paste ready) and workflow clarity (no explicit sequenced validation checkpoints for a batch optimization process).

Suggestions

Make the Core Pattern copy-paste ready by showing how to construct the request, evaluator, and reflection_client, or label it explicitly as a sketch and point to a specific example file with a runnable command.

Add an explicit numbered optimization workflow with a validation checkpoint (e.g. run evaluator -> review failures -> keep only proposals passing the verification gate -> re-run within budget) so the batch process has a clear feedback loop.

Show one concrete evaluator-callback snippet since "Create evaluator callbacks and persist optimizer artifacts" is a listed task but has no executable example.

DimensionReasoningScore

Conciseness

Lean bullet/section structure that assumes Claude's competence and explains no concepts Claude already knows; every section earns its place, matching the level-3 anchor.

3 / 3

Actionability

The Core Pattern is real Python but uses undefined variables (reflection_client, request, evaluator) and defers full syntax to examples/, so it is concrete yet not copy-paste ready; this fits level 2 rather than the fully-executable level 3.

2 / 3

Workflow Clarity

"When To Use" lists tasks but provides no numbered sequence, and the verification gate and budgets are mentioned without explicit validation checkpoints; since optimization is a batch operation, missing feedback loops cap this at 2.

2 / 3

Progressive Disclosure

Under 50 lines with well-organized sections and clearly signaled one-level-deep references to detailed package materials (API.md, axir-api.json, examples/) listed in Package Facts, satisfying the simple-skill rule for level 3.

3 / 3

Total

10

/

12

Passed

Description

85%

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 specific and complete with an explicit trigger, and occupies a clearly distinct niche. Its main weakness is jargon-heavy trigger terms that may not match natural user phrasing.

Suggestions

Add plain-language trigger variations a user would naturally say (e.g. "optimize an agent", "improve agent prompts", "tune agent performance") alongside the technical terms like GEPA and BootstrapFewShot.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities ("agent optimization, verified agent-playbook evolution, evaluators, judges, optimizer artifacts, BootstrapFewShot, and GEPA") rather than abstract language; it is comprehensive, not the partial coverage of a 2.

3 / 3

Completeness

Explicit "Use when writing Python code with `axllm` for agent optimization..." trigger answers when, and the enumerated capabilities answer what; both are explicit, matching the level-3 anchor rather than the when-only-implied level 2.

3 / 3

Trigger Term Quality

Includes some natural terms ("agent optimization", "evaluators", "judges") but leans heavily on technical jargon ("BootstrapFewShot", "GEPA", "agent-playbook evolution") and misses common user-phrasing variations, so it stops at 2 rather than 3.

2 / 3

Distinctiveness Conflict Risk

Tightly scoped to `axllm`-based agent optimization with distinctive terms (GEPA, BootstrapFewShot), making it unlikely to trigger for unrelated skills.

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.