CtrlK
BlogDocsLog inGet started
Tessl Logo

ax-go-agent-context

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for deciding between context maps, trajectory context policy, offline optimization (ACE/GEPA), and memory recall for long-context agents.

63

Quality

75%

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-agent-context/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

A concise, well-organized skill that correctly assumes Claude's competence, but it under-delivers on its own purpose: it lists the four features to choose between without executable examples or a concrete decision rule, and it cites bundle files that do not exist.

Suggestions

Add a concrete decision rule or small executable example for each of contextMap, contextPolicy, optimization, and recall so the routing is actionable rather than just named.

Provide an explicit if/then routing sequence (e.g., "If the corpus is persistent across runs, use contextMap; if within-run token budget matters, use contextPolicy") so the workflow is unambiguous.

Either ship the referenced bundle files (API.md, axir-api.json, axir-capabilities.json, examples/) or remove/conditionalize the references so they are not broken.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence: it states package facts, a tight code block, and an API symbol list without explaining concepts Claude already knows, so every token earns its place.

3 / 3

Actionability

The Core Pattern code block is executable and the API surface lists real symbols, but the skill's core purpose — choosing between contextMap, contextPolicy, optimization, and recall — gives only symbol names and no executable example or concrete decision guidance for each path.

2 / 3

Workflow Clarity

The When-To-Use bullets and Guardrails list conditional guidance, but the routing decision itself is implicit (no explicit if/then sequence mapping task traits to a feature), so the sequence and checkpoints are missing or implicit.

2 / 3

Progressive Disclosure

Sections are well-organized, but the body references files ("API.md", "axir-api.json", "axir-capabilities.json", "examples/") that are not present in any bundle directory, so the references are broken rather than cleanly signaled and one level deep.

2 / 3

Total

9

/

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 explicit "Use when" triggers and a clear niche tied to a single package. Its main weakness is trigger-term quality: it favors technical jargon over the natural phrasings a user would actually say.

Suggestions

Add plain-language trigger variations a user might actually say (e.g., "Go agents", "managing context for long-context LLM agents", "context window", "agent memory") alongside the technical terms.

Soften or briefly gloss jargon like "trajectory context policy" and "ACE/GEPA" so the trigger reads naturally rather than as an internal API name list.

DimensionReasoningScore

Specificity

The description names the concrete package and lists four specific capabilities ("context maps, trajectory context policy, offline optimization (ACE/GEPA), and memory recall"), matching the anchor for multiple specific concrete actions.

3 / 3

Completeness

It explicitly answers both what it does (the four named capabilities) and when to use it ("Use when writing Go code with ... for ..."), matching the anchor for clear what-and-when with explicit triggers.

3 / 3

Trigger Term Quality

"Use when writing Go code" and "long-context agents" are natural user terms, but the description leans heavily on technical jargon ("trajectory context policy", "ACE/GEPA", the package path) and misses common variations, matching the anchor for some relevant keywords with gaps.

2 / 3

Distinctiveness Conflict Risk

It is scoped to a single generated Go package and a specific feature set, giving it a clear niche that is unlikely to conflict with other 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.