Name: ax-go-agent-context
Rating: 59.2 (1 reviews)
Author: ax-llm

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.

Quality

74%

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 ./website/static/go/.well-known/agent-skills/ax-go-agent-context/SKILL.md

Quality

Content

58%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 compact, well-organized overview that delegates detail appropriately to package artifacts, but it under-delivers on its own promise: the routing decision it exists for has no procedure, and the sole code example is not copy-paste runnable due to an undefined variable and inconsistent package qualifiers.

Suggestions

Add a short decision table or criteria list mapping task characteristics to each feature (e.g. persistent corpus orientation → contextMap; within-run compaction → contextPolicy; prompt/program tuning offline → optimization; retrieving from long-context memory → recall) so the central routing decision is actually actionable.

Make the Core Pattern compile-ready: use one consistent package qualifier (ax vs axllm) and show how the llm argument is constructed, or reference the specific examples/ file to copy from.

Trim the duplicated 'javascript-goja' runtime-profile mention (Package Facts vs Relevant API Surface) and the redundant 'Language: Go.' line that repeats the package path.

Dimension	Reasoning	Score
Conciseness	The body is lean and fact-dense with no explanations of concepts Claude already knows, but minor redundancy remains: 'Language: Go.' duplicates the package path, and 'javascript-goja' appears in both Package Facts and Relevant API Surface. These trimmable extras keep it below anchor 5's 'every token earns its place'.	4 / 5
Actionability	The Core Pattern is real Go rather than pseudocode, but it is not executable as shown: 'llm' is never defined or constructed, and the example uses the 'ax.' qualifier while the API surface lists 'axllm.*' names — an inconsistency in key details that fits anchor 3 (concrete but incomplete) better than anchor 4's 'minor gaps'.	3 / 5
Workflow Clarity	The skill's central purpose is 'deciding between contextMap, contextPolicy, optimization, and recall', yet no decision criteria, task-to-feature mapping, or sequence is provided — 'When To Use' names the choice dimensions but never says how to route, and there are no validation checkpoints. The simple-skill exception does not apply because the core action is a multi-branch decision, not a single unambiguous step.	2 / 5
Progressive Disclosure	Under 50 lines with clean section headers and clearly listed one-level-deep pointers to the package's detailed artifacts (API.md, axir-api.json, axir-capabilities.json, examples/); no bundle files exist, so the simple-skill organization exception applies — the body serves purely as an overview.	5 / 5
	Total	14 / 20 Passed

Description

78%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: explicit trigger, concrete domain, niche-specific terms, and low conflict risk. Its main weakness is that the capability statement ('what') is implied inside the 'Use when' clause rather than declared directly, and action coverage stops at 'deciding between' the four features without saying what the skill provides for each.

Dimension	Reasoning	Score
Specificity	Names the domain (Go, 'github.com/ax-llm/ax/packages/go') and several concrete feature areas ('context maps, trajectory context policy, offline optimization (ACE/GEPA), and memory recall'), but the actions themselves reduce to 'writing Go code' and 'deciding between' — more concrete than anchor 3's 1-2 actions, short of anchor 5's comprehensive action coverage.	4 / 5
Completeness	An explicit 'Use when...' clause answers 'when' clearly, and the 'what' (deciding between the four context/optimization features) is present, but it is folded into the trigger sentence rather than stated as standalone capabilities — anchor 5 requires both explicitly and concretely.	4 / 5
Trigger Term Quality	Good keyword coverage including 'Go code', 'context maps', 'ACE/GEPA', 'memory recall', 'long-context agents', and the full package path — natural terms for this framework's users — but common variations and synonyms (e.g. 'Ax', 'ax-go', 'prompt optimization') are missing, so it falls short of anchor 5.	4 / 5
Distinctiveness Conflict Risk	The package-specific import path and niche feature names ('trajectory context policy', 'ACE/GEPA') give it a clear trigger niche with minimal overlap risk against generic Go or context-management 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: website/static/go/.well-known/agent-skills/ax-go-agent-context/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.