CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

65

Quality

78%

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

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

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized, token-efficient reference skill with good progressive disclosure and concrete API pointers. It loses points on actionability (illustrative snippet with undefined variables) and workflow clarity (no sequenced, validated multi-step process for the evolve/learn operations).

Suggestions

Make the Core Pattern snippet self-contained by showing how examples, metricFn, llm, and ctx are constructed, or label it explicitly as a shape template and point to examples/ for a runnable version.

Add a short sequenced workflow with a validation checkpoint for the evolve-then-verify cycle (e.g. evolve -> check metric -> rollback if worse), since agent-bound verified evolution is a risky multi-step operation.

DimensionReasoningScore

Conciseness

The body is lean — terse Package Facts, a compact Core Pattern, a symbol list, and directive Guardrails — with no padding explaining concepts Claude already knows; every section earns its tokens.

3 / 3

Actionability

The Core Pattern gives a real call shape (ax.NewAx, ax.Playbook, pb.Evolve) and the API surface lists exact symbols, but the snippet references undefined variables (examples, metricFn, llm, ctx) so it is not copy-paste ready.

2 / 3

Workflow Clarity

"When To Use" lists capability triggers and Guardrails offer soft checks ("Start from package examples", "if package docs disagree ... update the compiler"), but there is no sequenced multi-step workflow with explicit validation checkpoints for the evolve/learn/refine operations.

2 / 3

Progressive Disclosure

The body is a concise overview that clearly signals one-level-deep references ("Package API docs: API.md and axir-api.json", "Capability manifest: axir-capabilities.json", "Runnable examples: examples/"), matching the well-signaled single-level reference anchor. (No bundle files were present in the review directory to verify against.)

3 / 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 specific, well-scoped description with an explicit use-trigger and concrete capabilities. Its main weakness is trigger-term naturalness: the action vocabulary is technical and unlikely to match how a user would phrase a request.

Suggestions

Add user-natural phrasings alongside the technical terms (e.g. "evolve/optimize a prompt playbook", "learn from failed runs") so the description matches how users actually ask.

Consider including a plain-language synonym for "context-engineering surface" to broaden trigger coverage without losing specificity.

DimensionReasoningScore

Specificity

Quotes several concrete actions — "playbook() context-engineering surface", "agent-bound verified evolution", "run-end learning", "online updates", and "rendering a playbook into a program" — matching the multiple-specific-actions anchor.

3 / 3

Completeness

Explicitly states both what it does (the listed playbook operations) and when to use it via the "Use when writing Go code with ..." clause, satisfying the what-AND-when anchor.

3 / 3

Trigger Term Quality

Opens with the natural trigger "Use when writing Go code with ...", but the remainder is jargon-heavy ("context-engineering surface", "agent-bound verified evolution") that users would rarely say verbatim, so coverage of natural terms is partial.

2 / 3

Distinctiveness Conflict Risk

Tied to a specific package path `github.com/ax-llm/ax/packages/go` and a narrow playbook niche, making it unlikely to trigger for unrelated skills.

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.