ax-cpp-agent

Use when writing C++ code with `axllm` for agents, child delegation, tools, MCP, citations, persistent playbook learning, stage instructions, runtime state, final typed responses, and direct-respond executor skipping.

Quality

75%

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/SKILL.md

Quality

Content

65%

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

A concise, well-structured overview with a concrete core pattern, but it stops short of fully executable guidance for most capabilities and lacks sequenced workflows with validation. References to detail files are present but not clearly signaled as navigation.

Suggestions

Add one short executable example each for the high-value capabilities (MCP client setup, runtime state save/restore) so guidance is copy-paste ready beyond the core pattern.

Turn the Package Facts file references into clearly signaled links (e.g. a dedicated "## Reference" section with "See [API.md](API.md) for full method docs") and move the inline API surface there.

For runtime-state save/restore and playbook harvesting, add an explicit validate-then-proceed checkpoint so the workflow has a feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is lean and dense — tight bullet lists in Package Facts and When To Use, a minimal core snippet, and no explanation of concepts Claude already knows (no "what is C++/MCP" padding); every section earns its place.	3 / 3
Actionability	It provides one concrete executable core pattern and a precise map of API symbols, but the broader capabilities (MCP, runtime profiles, citations, playbook) are given only as symbol inventories rather than executable examples, and the snippet leaves `llm` undefined.	2 / 3
Workflow Clarity	The content is clearly organized into sections but presents no sequenced multi-step workflow, and potentially fragile operations like "Save and restore agent runtime state around long-running tasks" and playbook harvesting lack any validation checkpoints or feedback loops, capping the score at 2.	2 / 3
Progressive Disclosure	Sections are well-organized, but the referenced detail files (API.md, axir-api.json, examples/) are only mentioned inline in Package Facts rather than clearly signaled as navigable links, and the inline Relevant API Surface could be delegated to the referenced API.md.	2 / 3
	Total	9 / 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.

A specific, well-triggered description with an explicit "Use when" clause and a clear axllm/C++ niche. Its main weakness is heavy reliance on framework-specific jargon that dampens natural trigger-term quality.

Suggestions

Soften framework jargon (e.g. "direct-respond executor skipping", "persistent playbook learning") with more natural phrasings a user would actually say, or pair each jargon term with a plain-language equivalent.

Add a couple of common user-facing variations (e.g. "C++ LLM agent", "C++ agent with tools") to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	The description lists multiple specific concrete capabilities — "agents, child delegation, tools, MCP, citations, persistent playbook learning, stage instructions, runtime state, final typed responses, and direct-respond executor skipping" — rather than vague language, matching the multiple-concrete-actions anchor.	3 / 3
Completeness	It opens with an explicit "Use when..." trigger clause and pairs it with a clear statement of what the skill does (writing C++ code with axllm for the listed capabilities), explicitly answering both what and when.	3 / 3
Trigger Term Quality	It includes some natural terms a developer would say ("C++ code", "agents", "tools", "MCP", "citations"), but a large portion is framework jargon ("persistent playbook learning", "stage instructions", "direct-respond executor skipping", "final typed responses") that users would not naturally utter, so it is not a full 3.	2 / 3
Distinctiveness Conflict Risk	The niche is tightly scoped to the `axllm` C++ package with distinctive framework-specific triggers (playbook learning, executor skipping, stage instructions), making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 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/SKILL.md
Commit: 9087a01

Reviewed: 5 days 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.