CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./packages/go/skills/ax-go-playbook/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 a compact, well-sectioned overview with genuinely useful package facts and guardrails, and it mostly respects token budget. However, the core code snippet is not executable (undefined identifiers, inconsistent ax./axllm. qualifiers), the evolve/verify/rollback workflow is named but never sequenced, and every referenced file (API.md, examples/, manifests) is missing from the bundle.

Suggestions

Make the Core Pattern runnable: add the import line, define or annotate the free variables (ctx, llm, examples, metricFn), and reconcile the ax. vs axllm. package qualifier with the 'Relevant API Surface' list.

Add a numbered evolve-verify-rollback workflow with an explicit validation checkpoint (e.g., how to check verification output and trigger the 'exact rollback' the description promises).

Resolve the dangling references: either include API.md, the manifests, and examples/ in the bundle (under references/) and link them as paths, or state where they live relative to the generated package.

DimensionReasoningScore

Conciseness

The body is lean — terse bullet sections ("Real network support: yes", "Runtime profiles: javascript-goja") that assume competence and add facts Claude could not know about a generated package. Not 5 because the opening sentence ("This skill helps an agent write Go code with the generated Ax package...") restates the description, and the 'When To Use' bullets partially duplicate it.

4 / 5

Actionability

The Core Pattern code block is concrete Go but not executable as-is: identifiers (llm, examples, metricFn, ctx) are undefined, there is no import statement, and the package qualifier is inconsistent — the snippet uses "ax." while 'Relevant API Surface' lists "axllm.Optimize" etc., leaving the actual import path unclear. This matches 'some concrete guidance but incomplete; missing key details'; the guardrail to defer to examples/ partly compensates but the gap remains.

3 / 5

Workflow Clarity

A rough sequence exists (create program → construct Playbook → Evolve in the Core Pattern), and guardrails like 'Use no-key examples for deterministic local checks' act as implicit checkpoints. But the headline workflows — verified evolution with 'verification and exact rollback', online refinement, rendering/persisting — are named without any sequenced steps or explicit validation checkpoints, matching 'steps listed but checkpoints missing or implicit'.

3 / 5

Progressive Disclosure

Sections are well-organized for a short skill, but the body points to "API.md", "axir-api.json", "axir-capabilities.json", and "examples/" and no such files exist anywhere in the skill bundle (references/, scripts/, assets/ are all absent). The references are also plain inline code mentions rather than clearly signaled links or paths, so navigation cannot be verified — 'references present but not clearly signaled'.

3 / 5

Total

13

/

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 highly distinctive thanks to the pinned package path and covers several concrete capabilities, with an explicit 'Use when' trigger. Its main weakness is trigger-term quality: dense proprietary jargon ("agent-bound verified evolution", "run-end learning") crowds out the natural phrases a user would actually say.

Suggestions

Add natural trigger synonyms users would plausibly say, such as 'ax framework', 'Go agent', or 'context engineering', alongside the package path.

Translate at least one jargon capability into plain language (e.g., 'agent-bound verified evolution' → 'evolve an agent's playbook from failures with verification and rollback').

Split the single run-on sentence into a what-clause and a when-clause so both halves read clearly.

DimensionReasoningScore

Specificity

Lists several concrete capabilities — "playbook() context-engineering surface", "agent-bound verified evolution", "run-end learning", "online updates", "rendering a playbook into a program" — but the jargon-dense phrasing leaves minor gaps in what a reader can concretely grasp. Not 5 because the actions are named in proprietary terminology rather than fully unpacked concrete actions; not 3 because coverage goes well beyond 1-2 actions.

4 / 5

Completeness

Explicitly answers both: what ("playbook() context-engineering surface, agent-bound verified evolution, run-end learning, online updates, and rendering a playbook") and when ("Use when writing Go code with github.com/ax-llm/ax/packages/go"). Not 5 because the 'what' is packed into a single jargon-heavy clause whose concrete meaning is hard to parse; the 'when' is explicit but narrow.

4 / 5

Trigger Term Quality

Relevant keywords like "writing Go code", "playbook", and the package path are present, but natural user phrases and synonyms (e.g., "ax framework", "Go agent", "context engineering") are missing. Phrases like "agent-bound verified evolution" and "run-end learning" are technical jargon users would not naturally say, matching the anchor for some relevant keywords but missing common variations.

3 / 5

Distinctiveness Conflict Risk

Pinned to the specific package "github.com/ax-llm/ax/packages/go" with a distinct niche (playbook context engineering in Go), giving it a clear trigger with minimal conflict risk against other skills. A user working with this package would unambiguously match this description.

5 / 5

Total

16

/

20

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.

Validation — 15 / 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

Path

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

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.