Name: ax-go-playbook
Rating: 61.6 (1 reviews)
Author: ax-llm

ax-go-playbook

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for the playbook() context-engineering surface, agent-bound verified evolution, run-end learning, online updates, and rendering a playbook into a program.

Quality

77%

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

Quality

Content

65%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 concise, reasonably actionable reference-style skill body with good section organization. Its main weaknesses are a placeholder-laden core example, no sequenced workflow with validation checkpoints, and references to API/examples files that are missing from the bundle.

Suggestions

Include the referenced files (API.md, axir-api.json, axir-capabilities.json, examples/) in the bundle, or remove/inline the mentions so no navigation path is broken.

Make the Core Pattern copy-paste ready: show imports and concrete values (a real metric function signature and an examples slice) instead of bare `examples`, `metricFn`, and `llm` placeholders.

Add a short ordered workflow with a checkpoint, e.g. 1) copy the closest example from examples/, 2) adapt the call shape, 3) verify deterministically with the no-key transport before using provider credentials.

Dimension	Reasoning	Score
Conciseness	The body is lean with well-chosen terse facts ('Real network support: yes', 'Scripted no-key transport support: yes') and no explanation of concepts Claude already knows. It falls short of the 5 anchor only through minor duplication: 'Language: Go.' and the package path restate what the frontmatter description already establishes.	4 / 5
Actionability	The Core Pattern gives concrete Go syntax ('program := ax.NewAx(...)', 'pb := ax.Playbook(...)', 'pb.Evolve(ctx, examples, metricFn, nil)') plus a named API surface and pointers to runnable examples. It is not a 5 because the snippet is not copy-paste ready: `llm`, `examples`, and `metricFn` are undefined placeholders and imports are omitted.	4 / 5
Workflow Clarity	'When To Use' routes tasks and the Guardrails include check-style hints ('Use no-key examples for deterministic local checks'), but there is no sequenced workflow with validation checkpoints — nothing tells the agent to start from an example, adapt it, and verify against the no-key transport before touching live providers. This matches the 'steps listed but validation gaps; checkpoints missing or implicit' anchor.	3 / 5
Progressive Disclosure	Sections are clearly organized for a short skill, but every referenced artifact — 'API.md', 'axir-api.json', 'axir-capabilities.json', and 'examples/' — is absent from the bundle (no references/, scripts/, or assets/ directories exist). The references are signaled but dangling, so navigation to deeper detail is impossible in practice, matching the 'references present but not clearly usable' level rather than the good-structure 4 anchor.	3 / 5
	Total	14 / 20 Passed

Description

80%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 strong description with explicit what/when structure, a concrete package-scoped trigger, and low conflict risk. Its main weakness is jargon-heavy phrasing that may not match the natural language users actually say when they need playbook evolution or learning.

Suggestions

Add natural-language synonyms alongside the technical terms, e.g. 'Use when optimizing prompts or evolving an agent playbook for a Go program' so users who say 'optimize', 'evolve', or 'learn from failures' match the trigger.

Include the offline-refinement capability (refining from labeled examples) to close the small coverage gap between the description and the body's 'When To Use' list.

Dimension	Reasoning	Score
Specificity	The description names several concrete capabilities — 'playbook() context-engineering surface', 'agent-bound verified evolution', 'run-end learning', 'online updates', and 'rendering a playbook into a program' — which matches the 'several specific actions; minor gaps in coverage' anchor. It is not a 5 because coverage is slightly incomplete (e.g., offline refinement from labeled examples and playbook persistence appear in the body but not the description).	4 / 5
Completeness	It explicitly answers both what (playbook creation, verified evolution, run-end learning, online updates, rendering) and when ('Use when writing Go code with `github.com/ax-llm/ax/packages/go`') with a concrete trigger phrase. This clearly matches the 5 anchor rather than the 4 anchor, whose 'when' is weaker or less specific than the package-scoped trigger given here.	5 / 5
Trigger Term Quality	Natural terms like 'Go code' and 'playbook' are present, but the majority of the phrasing is internal jargon ('context-engineering surface', 'run-end learning', 'agent-bound verified evolution') rather than words a user would naturally say. Common variations such as 'optimize', 'evolve', or 'learn from agent failures' are missing, matching the 'some relevant keywords but missing common variations or synonyms' anchor.	3 / 5
Distinctiveness Conflict Risk	The description is pinned to a specific import path (`github.com/ax-llm/ax/packages/go`) and a niche capability set (playbook evolution and learning), giving it a clear niche with distinct triggers and minimal conflict risk with generic Go or optimization 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/go/skills/ax-go-playbook/SKILL.md
Commit: 3f630a0

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.