ax-python-playbook

Use when writing Python 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

73%

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/python/skills/ax-python-playbook/SKILL.md

Quality

Content

76%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 content is concise, well-structured, and points clearly to deeper materials, with a concrete core code example. The main gap is the absence of an explicit evolve/rollback workflow with validation checkpoints.

Suggestions

Add a short sequenced workflow for the evolve loop (e.g., prepare examples -> run evolve -> review verified weaknesses -> rollback on failure) with an explicit validation checkpoint.

Make the deferred references navigable (e.g., `[API.md](API.md)`) so the overview links cleanly to detail files.

Provide at least one copy-paste-ready snippet where placeholders (`llm`, `examples`, `metric_fn`) are bound to concrete values, or note where they come from.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-sectioned (Package Facts, Core Pattern, API Surface, Guardrails) with no over-explanation of concepts Claude already knows; every section earns its place.	5 / 5
Actionability	The Core Pattern gives concrete, runnable code (`ax(...)`, `playbook(...)`, `pb.evolve(...)`), but it relies on undefined placeholders (`llm`, `examples`, `metric_fn`) and only covers one of the several advertised capabilities, leaving minor gaps.	4 / 5
Workflow Clarity	The Core Pattern shows a short sequence (ax -> playbook -> evolve) and When-To-Use lists use cases, but there are no validation/verification checkpoints for an evolution flow that explicitly involves verification and rollback; per the rubric this caps the score at 3.	3 / 5
Progressive Disclosure	The body is a compact overview that defers detail to referenced files (`API.md`, `axir-api.json`, `examples/`) signaled under Package Facts; not a 5 because those references are plain text rather than navigable links and a small API-name list is inlined.	4 / 5
	Total	16 / 20 Passed

Description

71%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 distinct, with an explicit 'Use when' trigger and a niche focus. Its main weakness is heavy domain jargon that few users would naturally voice, slightly weakening trigger-term quality.

Suggestions

Add plain-language trigger phrases users would actually say (e.g., 'evolve a playbook', 'optimize a program with examples') alongside the technical terms.

Soften or gloss jargon like 'context-engineering surface' and 'agent-bound verified evolution' so the 'when' clause reads as natural user intent.

Optionally include a synonym or two (e.g., 'playbook optimization') to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('writing Python code with `axllm`') and lists several specific capabilities ('agent-bound verified evolution', 'run-end learning', 'online updates', 'rendering a playbook into a program'); falls short of 5 because the actions lean on domain jargon rather than plainly concrete verbs.	4 / 5
Completeness	Has both a 'what' (the listed capabilities) and an explicit 'when' ('Use when writing Python code with `axllm`'); not a 5 because the 'when' is a single broad clause rather than multiple concrete trigger phrases.	4 / 5
Trigger Term Quality	'writing Python code with `axllm`' and 'playbook' are natural triggers, but most of the phrase ('context-engineering surface', 'agent-bound verified evolution', 'run-end learning') is internal jargon users would not naturally say; missing common synonyms, so it sits at 3 rather than 4.	3 / 5
Distinctiveness Conflict Risk	Targets a very specific niche (the `axllm` playbook() surface) with distinct triggers, so conflict with other skills is minimal.	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/python/skills/ax-python-playbook/SKILL.md
Commit: e690b48

Reviewed: 1 hour 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.