ax-cpp-playbook

Use when writing C++ code with `axllm` for the playbook() context-engineering surface, agent-bound verified evolution, run-end learning, online updates, and rendering a playbook into a program.

Quality

66%

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-playbook/SKILL.md

Quality

Content

62%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.

The body is concise and offers a concrete core pattern plus a clear API surface, but it lacks a sequenced workflow with validation checkpoints, and its progressive-disclosure references point to bundle files that are not present.

Suggestions

Add a short numbered workflow (e.g. start from example -> build playbook -> evolve with metric -> validate -> render) with an explicit validation/rollback checkpoint before rendering.

Either provide the referenced bundle files (API.md, axir-api.json, examples/) or inline the minimum needed detail so references resolve.

Flesh out the `pb.evolve(examples, metric_fn)` call with concrete argument shapes so the core pattern is copy-paste runnable.

Dimension	Reasoning	Score
Conciseness	Lean and well-sectioned with no padding or explanation of basics; only minor trim opportunities such as 'When To Use' echoing the description's capabilities.	4 / 5
Actionability	Provides an executable Core Pattern snippet and a concrete API surface list; minor gaps include the omitted `examples/` contents and underspecified `pb.evolve(examples, metric_fn)` arguments.	4 / 5
Workflow Clarity	Capabilities are enumerated but not sequenced into a multi-step workflow, and no explicit validation checkpoints or feedback loops are given for the evolve/rollback operations.	3 / 5
Progressive Disclosure	Sections are clean and reference paths are signaled, but the referenced bundle files (API.md, axir-api.json, axir-capabilities.json, examples/) do not exist in the bundle, so navigation does not resolve.	3 / 5
	Total	14 / 20 Passed

Description

70%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.

The description is specific and clearly scoped to a distinct niche, with explicit 'what' and 'when' guidance. Its main weakness is trigger-term naturalness, leaning on domain jargon over phrases a user would actually say.

Suggestions

Add natural-language trigger phrases users would say (e.g. 'optimize a C++ Ax program', 'evolve a playbook from failures') alongside the technical terms.

Consider listing concrete entry points or file types a user might mention to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists several specific capabilities ('writing C++ code with `axllm`', 'playbook() context-engineering surface', 'agent-bound verified evolution', 'run-end learning', 'online updates', 'rendering a playbook into a program') with only minor coverage gaps; not quite the comprehensive level-5 enumeration.	4 / 5
Completeness	Explicitly answers both 'what' (write C++ with axllm for the listed capabilities) and 'when' ('Use when writing C++ code with `axllm` for...'), with the 'when' slightly abstract rather than fully concrete user triggers.	4 / 5
Trigger Term Quality	Includes a 'Use when' clause and 'writing C++ code', but the remaining triggers are domain jargon ('context-engineering surface', 'run-end learning') rather than natural user phrases, and lacks synonyms or file extensions.	3 / 5
Distinctiveness Conflict Risk	A clear niche (C++ axllm playbook/evolution) with distinct triggers and minimal risk of firing for an unrelated skill.	5 / 5
	Total	16 / 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-playbook/SKILL.md
Commit: 781623e

Reviewed: 3 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.