Name: ax-go-agent-context
Rating: 55.2 (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

69%

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-agent-context/SKILL.md

Quality

Content

51%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 compact and well-sectioned with a concrete code pattern and useful guardrails, but it never delivers its promised core value: no guidance on when to prefer contextMap over contextPolicy, optimization, or recall. The code example's `ax.` vs `axllm.` prefix inconsistency and references to files absent from the bundle further weaken executability and navigation.

Suggestions

Add a short decision table or bullet criteria under "When To Use" mapping task characteristics to each feature (e.g., persistent corpus vs within-run compaction → contextMap vs contextPolicy; offline eval data available → ACE/GEPA), since the skill's stated purpose is choosing between them.

Fix the Core Pattern code block to use the same package prefix and include the import statement (e.g., `import axllm "github.com/ax-llm/ax/packages/go"`) so it is copy-paste executable and consistent with the "Relevant API Surface" listing.

Clarify the location of the cited files ("API.md", "axir-api.json", "examples/") with explicit paths, or move that content into a references/ directory in the bundle so the pointers resolve.

Dimension	Reasoning	Score
Conciseness	The body is lean — terse fact bullets, one small code block, no explanation of concepts Claude already knows. Minor trimmable redundancy remains: "Language: Go." duplicates the package path and title, and the "When To Use" bullets largely restate the frontmatter description, so it sits just below anchor 5's "every token earns its place".	4 / 5
Actionability	Concrete elements exist (the "Core Pattern" code block and specific API symbols like `axllm.NewAgent`, `axllm.AxGEPA`), but the code block uses `ax.NewAgent`/`ax.Value` while the API surface section uses the `axllm.` prefix — an inconsistency that breaks copy-paste readiness — and the import statement is missing. Key details for the skill's central task (criteria for choosing between contextMap/contextPolicy/optimization/recall) are absent, matching anchor 3's "concrete guidance but incomplete".	3 / 5
Workflow Clarity	"Choose between contextMap, contextPolicy, optimization, and recall for a task" merely restates the skill's name with no selection criteria, and no sequenced decision flow exists anywhere in the body — the core routing task is undefined. The only checkpoint-like guidance is implicit ("Start from package examples for exact native syntax before inventing a new call shape"), fitting anchor 2's rough/poorly-defined sequence with validation absent.	2 / 5
Progressive Disclosure	Sections are well-organized for a sub-50-line skill, but the cited materials — "API.md and axir-api.json", "axir-capabilities.json", "examples/" — do not exist in the skill bundle (no references/, scripts/, or assets/ directories) and no path or location is given for them. References are present in name but not clearly signaled, matching anchor 3 rather than anchor 4's "references mostly clear".	3 / 5
	Total	12 / 20 Passed

Description

73%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, tightly-scoped description: it names the exact package, includes an explicit "Use when…" trigger, and lists concrete feature areas with good technical keywords. Its main weakness is that the capability side rests on a single verb ("deciding between") rather than stating what the skill actually provides, leaving the what half slightly implicit.

Dimension	Reasoning	Score
Specificity	The description names the domain precisely ("writing Go code with `github.com/ax-llm/ax/packages/go`") and enumerates concrete feature areas ("context maps, trajectory context policy, offline optimization (ACE/GEPA), and memory recall"), but the only action verb is "deciding between" — a single action over four objects, not several distinct actions as anchor 4 requires (cf. "Extracts text…, fills forms, converts pages").	3 / 5
Completeness	The when-clause is explicit and specific ("Use when writing Go code with `github.com/ax-llm/ax/packages/go`"), and a what is present ("deciding between context maps, trajectory context policy, offline optimization…, and memory recall"), but the what is embedded as a purpose clause rather than a leading capability statement, and what the skill provides (API usage guidance, examples, manifests) is left implicit — one of the two halves could be more explicit, matching anchor 4 rather than anchor 5.	4 / 5
Trigger Term Quality	Good natural keyword coverage: "Go code", "context maps", "offline optimization (ACE/GEPA)", "memory recall", "long-context agents", plus the exact package import path. A few natural terms and synonyms are missing (e.g., "Ax", "prompt optimization", "context window", "compaction"), so it does not reach anchor 5's comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	The description is pinned to a single specific package ("github.com/ax-llm/ax/packages/go") and niche features ("trajectory context policy", "ACE/GEPA", "memory recall for long-context agents"), giving it a clear niche with distinct triggers and minimal overlap with any generic skill.	5 / 5
	Total	16 / 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-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.