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.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./packages/cpp/skills/ax-cpp-agent-optimize/SKILL.md

Quality

Content

61%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 well-organized, token-efficient reference-style skill body with clear sections and one-level references. It is held back by an illustrative rather than executable core pattern and the absence of an explicit sequenced workflow with validation checkpoints for the optimization process.

Suggestions

Make the Core Pattern copy-paste ready by showing how reflection_client, options, request, and evaluator are constructed, or point to a specific example file that is.

Add an explicit numbered optimization workflow with a validation/verification checkpoint (e.g., run evaluator -> keep only proposals passing the verification gate -> persist artifacts) rather than leaving it implied.

Either trim the inlined Relevant API Surface to a few key symbols and defer the rest to API.md, or drop the separate API.md/axir-api.json reference to avoid redundancy.

Dimension	Reasoning	Score
Conciseness	Lean bullet-driven sections (Package Facts, API Surface, Guardrails) with no concept over-explanation; minor redundancy where the inlined API Surface overlaps the separately referenced API.md/axir-api.json.	4 / 5
Actionability	The Core Pattern gives real symbols but uses undefined variables ('reflection_client', 'options', 'request', 'evaluator') and is illustrative rather than copy-paste executable; key setup details are missing.	3 / 5
Workflow Clarity	No explicit multi-step sequence with validation checkpoints; 'When To Use' is a task list, not a workflow, and the 'verification gate' is only implied in the description rather than sequenced in the body.	3 / 5
Progressive Disclosure	Well-sectioned overview with one-level-deep, clearly signaled references (API.md, axir-api.json, axir-capabilities.json, examples/) and no nesting; the short inlined API Surface is the only minor organization gap.	4 / 5
	Total	14 / 20 Passed

Description

78%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 specific, well-triggered description that names a distinct niche and concrete capabilities with an explicit 'Use when' clause. Its main weakness is that 'what' and 'when' are fused into one sentence and capabilities are listed as nouns rather than crisp actions.

Dimension	Reasoning	Score
Specificity	Lists several concrete domain items — 'agent optimization, verified agent-playbook evolution, evaluators, judges, optimizer artifacts, BootstrapFewShot, and GEPA' — but these are noun phrases naming capabilities rather than verb-driven actions, leaving minor gaps versus a fully comprehensive action list.	4 / 5
Completeness	Explicit 'Use when writing C++ code with `axllm`' trigger plus an implicit 'what' through the capability list; both what and when are present, but they are blended into a single clause rather than cleanly separated as in the top anchor.	4 / 5
Trigger Term Quality	Good coverage of natural terms a practitioner would say ('writing C++ code', 'agent optimization', 'evaluators', 'judges') plus specialized domain terms, though common synonyms or file-extension-style variations are missing.	4 / 5
Distinctiveness Conflict Risk	A clear niche — C++ code with the `axllm` package for agent optimization using BootstrapFewShot/GEPA — with distinct, specialized triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
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/cpp/skills/ax-cpp-agent-optimize/SKILL.md
Commit: 781623e

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.