CtrlK
BlogDocsLog inGet started
Tessl Logo

ax-cpp-agent-optimize

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

68

Quality

82%

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

65%

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

The content is concise and well-organized with a useful API surface and guardrails, but the core code example is a placeholder shape rather than executable code and the optimization workflow lacks an explicit sequenced process with validation checkpoints. Additionally, every referenced bundle file (API.md, examples/, manifests) is missing, breaking progressive disclosure.

Suggestions

Replace the Core Pattern placeholder snippet with a complete, executable example that shows how reflection_client, options, request, and evaluator are constructed, ideally drawn from a real example file.

Add an explicit numbered workflow for optimization (e.g., mine failed-task weaknesses -> propose playbook changes -> run the verification gate -> persist passing artifacts) with a validation/retry checkpoint.

Either add the referenced bundle files (API.md, axir-api.json, axir-capabilities.json, examples/) or remove the references so navigation resolves and progressive disclosure is not broken.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: it never explains what C++, agents, or GEPA are, and each section (Package Facts, Core Pattern, Relevant API Surface, Guardrails) earns its place without padding, matching the 'every token earns its place' anchor.

3 / 3

Actionability

It gives concrete symbol names and a 2-line Core Pattern, but the snippet uses undefined placeholders (reflection_client, options, request, evaluator) rather than executable code, and the referenced runnable examples (examples/) and API.md are not present, leaving guidance incomplete.

2 / 3

Workflow Clarity

The When To Use bullets imply a sequence (mine weaknesses, propose playbook, pass the verification gate) but it is never laid out as an explicit ordered workflow with validation checkpoints, and the optimize call hides the iteration/gating steps; sequence is only implicit.

2 / 3

Progressive Disclosure

The body is cleanly sectioned and signals one-level-deep references (API.md, axir-api.json, axir-capabilities.json, examples/), but none of these referenced bundle files actually exist in the skill, so the advertised navigation does not resolve.

2 / 3

Total

9

/

12

Passed

Description

100%

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, well-triggered, and distinctive: it states a clear 'Use when' condition tied to a concrete package and enumerates concrete capabilities a user of this niche would actually name. It concisely answers both what the skill does and when to invoke it.

DimensionReasoningScore

Specificity

The description names the concrete domain ('writing C++ code with axllm') and lists multiple specific capabilities ('agent optimization', 'evaluators, judges, 'optimizer artifacts', 'BootstrapFewShot, and GEPA'), matching the anchor that lists several concrete actions.

3 / 3

Completeness

It explicitly answers both 'what' (agent optimization, playbook evolution, evaluators, etc.) and 'when' via an explicit 'Use when...' clause, satisfying the top anchor for completeness.

3 / 3

Trigger Term Quality

It opens with a natural 'Use when writing C++ code with axllm for agent optimization' trigger and surfaces the exact vocabulary a user of this niche would say (agent optimization, evaluators, judges, playbook, BootstrapFewShot, GEPA), giving good coverage of natural trigger terms.

3 / 3

Distinctiveness Conflict Risk

The trigger is tightly scoped to C++ with the specific axllm package and named optimizer techniques (BootstrapFewShot, GEPA), forming a clear niche unlikely to fire for unrelated skills.

3 / 3

Total

12

/

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.