CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

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

80%

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 body with a real executable core pattern and a concrete API surface list. It loses points because the evolve batch workflow lacks validation checkpoints and because the referenced bundle files (API.md, axir-api.json, examples/) are not actually present.

Suggestions

Add an explicit validation/verification checkpoint to the evolve workflow (e.g., 'after pb.evolve(...), inspect the metric delta and roll back via the exact-rollback path if the metric regresses') to lift workflow_clarity above 2.

Bundle or remove the dangling references: either include API.md, axir-api.json, axir-capabilities.json, and examples/ alongside the skill, or drop them from Package Facts so progressive disclosure resolves to real files.

Fill in the Core Pattern's placeholders (llm, examples, metric_fn) or point to a specific runnable example in examples/ so the snippet is copy-paste complete.

DimensionReasoningScore

Conciseness

Lean, sectioned body with no padding and no explanations of concepts Claude already knows — every section (When To Use, Package Facts, Core Pattern, Guardrails) earns its tokens. There is no unnecessary explanation to tighten, clearing the score-3 bar over a 'mostly efficient but could be tightened' score-2.

3 / 3

Actionability

Provides a concrete Core Pattern with real imports and real API calls (`ax`, `playbook`, `pb.evolve`) plus a specific Relevant API Surface symbol list and directive Guardrails. This is closer to fully executable guidance than to the 'pseudocode / incomplete' score-2 anchor; the undefined `llm`/`examples`/`metric_fn` placeholders are minor and the skill directs to package examples for exact syntax.

3 / 3

Workflow Clarity

The Core Pattern gives a minimal sequence (ax → playbook → evolve) but there are no validation/feedback checkpoints, and evolve is a batch optimization operation where the rubric caps clarity at 2 without verification steps. It is above score-1 (a sequence is present) but the missing checkpoints hold it at 2.

2 / 3

Progressive Disclosure

Sections are well-organized and references are explicitly signaled in Package Facts ('API.md and axir-api.json', 'examples/'), but none of those referenced files exist in the bundle (no references/scripts/assets dirs). Good signaling and one-level-deep intent pull it above score-1, but dangling references that resolve to nothing keep it at 2 rather than 3.

2 / 3

Total

10

/

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 strong, specific description with an explicit Use-when trigger and a clear package-bound niche. Its main weakness is trigger-term quality: beyond 'writing Python code with axllm', the activating language is internal jargon rather than terms users naturally say.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — 'verified evolution', 'run-end learning', 'online updates', 'rendering a playbook into a program' — rather than vague domain naming. It clears the score-3 bar (multiple distinct actions) rather than stopping at naming the domain and a few actions (score 2).

3 / 3

Completeness

Explicitly answers both: what it does (evolution, run-end learning, online updates, rendering) and when to use it via an explicit 'Use when writing Python code with `axllm`' trigger. The presence of an explicit 'Use when' clause keeps it off the score-2 cap.

3 / 3

Trigger Term Quality

Includes one natural keyword ('Use when writing Python code with `axllm`'), but the distinctive triggers are product-internal jargon ('agent-bound verified evolution', 'run-end learning', 'context-engineering surface') that users would rarely say aloud. It is above a pure score-1 (no natural keywords) thanks to 'writing Python code', but lacks common natural-term coverage, so it lands at 2.

2 / 3

Distinctiveness Conflict Risk

Scoped tightly to the `axllm` package and the playbook() surface, giving it a clear niche with distinct triggers unlikely to fire for generic Python skills. Matches the score-3 'clear niche with distinct triggers; unlikely to conflict' anchor.

3 / 3

Total

11

/

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.