CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ax-go-agent-memory-skills

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking.

Quality

73%

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-memory-skills/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 dense, information-rich reference for a generated Go package that wastes almost no tokens, but it reads as an API behavior catalog rather than a usable guide: the lone code example is fragmentary and inconsistent with its own API surface list, no ordered workflow or validation step is provided, and every referenced file is missing from the bundle.

Suggestions

Make the Core Pattern snippet executable: add the import block, show how 'llm' is obtained, and reconcile the package prefix ('ax.NewAgent' vs 'axllm.NewAgent') with the Relevant API Surface section so the example is copy-paste ready.

Add a short ordered workflow for the most common task (e.g., configure catalogs/observers, run a forward, then export state) with an explicit verification step such as running a no-key example for deterministic local checks.

Ship the referenced materials (API.md, axir-api.json, examples) inside the bundle's references/ directory and list them in a dedicated, clearly signaled references section; move the 24.x/25.0.0 version-history notes into an 'Old patterns / deprecated' section.

DimensionReasoningScore

Conciseness

The body is lean and bullet-driven, and nearly every line conveys package-specific behavior Claude cannot know elsewhere (e.g., 'Forward-time skills override constructor entries by normalized ID'). Anchor 5 is blocked by minor trims ('Language: Go.') and inline time-sensitive version history ('Since 25.0.0...', 'a map saved by a 24.x port...') that the guidelines say belongs in a deprecated/old-patterns section, but there is no padded explanation of known concepts that would drag it to anchor 3.

4 / 5

Actionability

The single code snippet is a fragment rather than executable code: 'llm' is undefined, there are no imports, and 'ax.NewAgent' contradicts the 'axllm.NewAgent' listed under Relevant API Surface. The remaining content describes API behavior ('Constructor skills seed the loaded-skill prompt without firing load observers') instead of instructing how to write the code, matching anchor 3's 'some concrete guidance but incomplete... missing key details' rather than anchor 4's mostly-executable guidance.

3 / 5

Workflow Clarity

The content is reference-style — lifecycle facts, API lists, and guardrails — with no ordered sequence for a common task (e.g., wiring memory, observers, and state export) and no verification checkpoint beyond the general 'start from package examples' directive. It is not a simple single-task skill, so the simple-skill exception does not apply; anchor 3's 'sequence present but checkpoints missing or implicit' is the closest fit.

3 / 5

Progressive Disclosure

Sections are present and reasonably organized, but referenced materials ('API.md', 'axir-api.json', 'axir-capabilities.json', 'examples/', 'src/examples/go/long-agents/skills_and_memory_assistant.go') are not shipped in the bundle — no references/, scripts/, or assets/ directories exist — and the pointers are buried in Package Facts bullets rather than clearly signaled navigation. At ~59 lines with dangling references, it fits anchor 3 rather than the well-signaled, one-level-deep structure of anchor 4-5.

3 / 5

Total

13

/

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, well-scoped description that pairs an explicit 'Use when' trigger with a specific package path and a concrete list of capability areas. Its main weakness is fusing the 'what' and 'when' into one clause and using capability nouns instead of action verbs, which leaves it just below the top anchors.

DimensionReasoningScore

Specificity

The description names the domain ('writing Go code with github.com/ax-llm/ax/packages/go') and lists five specific capability areas ('agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking'). It falls short of anchor 5 because these are capability nouns rather than concrete action verbs (e.g., 'Extract text... fill forms'), but it clearly exceeds anchor 3's '1-2 concrete actions' with its detailed, well-scoped coverage.

4 / 5

Completeness

The 'when' is explicit and strong ('Use when writing Go code with...'), and the 'what' is conveyed through the embedded capability list. It sits at anchor 4 rather than 5 because the skill's actual action (e.g., guiding code generation) is only implied by the 'Use when... for X' construction — the what and when are fused into a single clause rather than each being explicitly and separately stated.

4 / 5

Trigger Term Quality

Includes strong natural triggers a user would actually provide: 'Go code', the full import path (which users paste directly), 'agent memory', and 'skill discovery'. Anchor 5 is not reached because natural variations like 'golang', 'Ax', 'AxAgent', or 'RLM' are missing, but coverage is solidly above anchor 3's 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

The description is pinned to a single specific package path ('github.com/ax-llm/ax/packages/go') with a Go-specific scope, giving it a clear niche with distinct triggers and minimal conflict risk — a direct match for anchor 5.

5 / 5

Total

17

/

20

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.

Validation — 15 / 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

Path

packages/go/skills/ax-go-agent-memory-skills/SKILL.md

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.