CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ax-python-agent-context

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

Quality

82%

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

SKILL.md
Quality
Evals
Security

Quality

Content

80%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 concise, well-structured overview that assumes Claude's competence and points to package docs and examples for depth. Its main gap is workflow clarity: the feature-selection decision the skill exists for is never given concrete criteria or a sequence.

Suggestions

Add decision criteria or a short decision table in 'When To Use' for choosing between contextMap, contextPolicy, optimization, and recall (e.g., what signals route a task to GEPA vs. memory recall), instead of only listing the four options.

Include one runnable code snippet for at least one of the four core features (e.g., setting a contextPolicy or invoking AxGEPA) and define how `llm` is constructed so 'Core Pattern' is copy-paste ready.

Replace the circular bullet 'Route long-context agent work to the right generated-package feature' with a concrete routing rule or checkpoint that tells the agent when it has chosen correctly.

DimensionReasoningScore

Conciseness

The body is lean and fact-dense — bullet-style 'Package Facts' ('Real network support: yes.', 'Runtime profiles: javascript-quickjs, python-pyodide'), a five-line core pattern, and guardrails with no padding or explanation of concepts Claude already knows. Every token earns its place.

5 / 5

Actionability

'Core Pattern' provides real, runnable-shaped code ('helper = agent("question:string -> answer:string")') and 'Relevant API Surface' lists exact symbols, but `llm` is left undefined and none of the four core decision features (contextMap, contextPolicy, optimization, recall) get a code example — the skill defers to 'examples/' instead. Concrete code with minor gaps, so above 3 but short of copy-paste-ready 5.

4 / 5

Workflow Clarity

'When To Use' bullets and guardrails give coherent structure, but the skill's central task — choosing between contextMap, contextPolicy, optimization, and recall — has no decision criteria, sequence, or checkpoints; 'Route long-context agent work to the right generated-package feature' restates the purpose without saying how to choose. Not 4 because checkpoints/criteria for the core decision are missing; above 2 because guardrails do constrain behavior.

3 / 5

Progressive Disclosure

At under 50 lines with no bundle files, the body is a well-organized overview with clearly signaled one-level references ('Package API docs: API.md and axir-api.json', 'Runnable examples: examples/') and easy navigation across its short sections, matching the simple-skill exception.

5 / 5

Total

17

/

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, niche-targeted description with an explicit 'Use when' clause and four named capability areas. Its main weakness is that the 'what' — what the skill actually does to help decide — is folded into the trigger clause and left somewhat abstract.

DimensionReasoningScore

Specificity

Names several concrete capability areas — 'context maps, trajectory context policy, offline optimization (ACE/GEPA), and memory recall' — tied to 'writing Python code with axllm'. Falls short of 5 because the stated action ('deciding between') is abstract and no concrete per-feature actions are listed; clearly above 3 with four specific named areas.

4 / 5

Completeness

The 'when' is explicit via 'Use when writing Python code with axllm…' and the 'what' (deciding between the four named features) is present but embedded in the when-clause rather than stated as a distinct capability statement. Both what and when are answerable, so above 3; short of 5 because the what is not cleanly and concretely separated.

4 / 5

Trigger Term Quality

Includes natural, user-sayable terms like 'Python code', 'axllm', 'context maps', 'offline optimization (ACE/GEPA)', 'memory recall', and 'long-context agents'. Not 5 because common variations and synonyms (e.g., 'context engineering', 'AxAgent', 'prompt optimization') are missing, but coverage is well above the 'some relevant keywords' level.

4 / 5

Distinctiveness Conflict Risk

Package-specific terms ('axllm', 'trajectory context policy', 'ACE/GEPA', 'memory recall for long-context agents') carve out a clear niche with distinct triggers and minimal overlap risk with generic Python or context-management skills.

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/python/skills/ax-python-agent-context/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.