ax-rust-agent-context

Use when writing Rust code with `axllm` for deciding between context maps, trajectory context policy, offline optimization (ACE/GEPA), and memory recall for long-context agents.

Quality

70%

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/rust/skills/ax-rust-agent-context/SKILL.md

Quality

Content

65%

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

The body is concise and well-structured with a concrete API surface, but its flagship code example is not fully executable and the skill lacks an explicit selection decision procedure and clearly signaled file navigation.

Suggestions

Make the Core Pattern snippet fully runnable by showing how `llm` and `inputs` are constructed, or mark the placeholders explicitly.

Turn the 'When To Use' bullets into an explicit decision procedure (e.g., 'If the task is persistent corpus lookup -> contextMap; if within-run compaction -> contextPolicy...').

Reframe the referenced files as one-level-deep navigation (e.g., '## References — API: see API.md; capabilities: see axir-capabilities.json; examples: see examples/') and ship them under a references/ bundle directory.

Dimension	Reasoning	Score
Conciseness	The body is a lean ~40 lines of terse bullets with no concept explanations or padding; it assumes Claude's competence and every section (Package Facts, Core Pattern, API Surface, Guardrails) earns its place, matching the 'lean and efficient' anchor.	3 / 3
Actionability	It provides a Rust snippet and concrete API symbols plus file pointers (API.md, axir-capabilities.json, examples/), but the Core Pattern uses undefined placeholders (`&llm`, `inputs`) so it is not copy-paste executable, fitting 'some concrete guidance but incomplete.'	2 / 3
Workflow Clarity	The 'When To Use' section gives selection guidance across the four features but no concrete decision sequence or validation checkpoints, matching 'steps listed but validation gaps; sequence present but checkpoints missing or implicit.'	2 / 3
Progressive Disclosure	Sections are well organized, but referenced files (API.md, axir-api.json, axir-capabilities.json, examples/) are listed flat as 'Package Facts' rather than clearly signaled one-level-deep navigation, and no bundle reference directory is present to verify them.	2 / 3
	Total	9 / 12 Passed

Description

75%

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 has an explicit 'Use when' trigger and a clear, distinctive niche, which carry completeness and distinctiveness. It is held back by jargon-heavy trigger terms and an abstract 'deciding between' action that weakens specificity and natural-term coverage.

Suggestions

Lead with a concrete verb describing the action (e.g., 'Selects and configures the right context feature...') instead of the abstract 'deciding between' phrasing.

Add natural-language trigger variations a user might actually say (e.g., 'long-context', 'context window', 'agent memory') alongside the technical terms.

Dimension	Reasoning	Score
Specificity	It names concrete capabilities ("context maps, trajectory context policy, offline optimization (ACE/GEPA), and memory recall"), but the governing verb "deciding between" is an abstract routing action rather than the concrete transform verbs (extract/fill/merge) the top anchor expects, so it lands in the 'names domain and some actions' band.	2 / 3
Completeness	It explicitly answers both halves: what it does (deciding between context maps, policy, optimization, and recall) and when to use it via an explicit "Use when writing Rust code with axllm..." trigger, satisfying the top anchor and the 'Use when' clause requirement.	3 / 3
Trigger Term Quality	"Use when writing Rust code with axllm" is a natural user phrase, but the remaining terms ("trajectory context policy", "offline optimization (ACE/GEPA)", "memory recall") are specialized jargon with missing common variations, matching 'some relevant keywords but missing common variations.'	2 / 3
Distinctiveness Conflict Risk	The combination of "Rust code with axllm" and "long-context agents" context selection is a sharply defined niche with distinct triggers that would not plausibly fire for unrelated skills.	3 / 3
	Total	10 / 12 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/rust/skills/ax-rust-agent-context/SKILL.md
Commit: fe8baf8

Reviewed: 5 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.