CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ax-python-typesafe

Use when writing Python code with `axllm` for Typesafe Jev image inputs, boolean/class/rubric score/box signatures, decision evidence and provenance, native Noul/Choice/Score/Box, structured criteria and hybrid generation.

Quality

68%

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/python/skills/ax-python-typesafe/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, fact-rich reference that assumes Claude's competence and delivers real package-specific contracts rather than tutorial padding, but it is structured as an API digest rather than a usable guide: one import-less code snippet, no stepwise workflow with validation, and long inlined detail (API surface list, per-provider contract rules) that belongs in reference files that don't exist in the bundle.

Suggestions

Add complete, copy-paste-ready examples with imports for the main flows — (evidence) signatures, box localization, native Noul/Choice/Score questions — instead of a single import-less snippet, keeping the detailed constraint prose as surrounding notes.

Move the 'Relevant API Surface' symbol list and per-provider contract details (Gemini request schema, probability/image limits) into bundle reference files (e.g., references/api-surface.md, references/providers.md) and link them clearly from short overview sections.

Add a short numbered workflow with a validation checkpoint, e.g., 1) pick the signature pattern, 2) adapt the closest example from src/examples/python/generation/, 3) verify locally with the scripted no-key transport, 4) only then run against a provider with real credentials.

DimensionReasoningScore

Conciseness

The body is densely packed with package-specific facts Claude cannot know ("16 MiB per decoded image, 32 MiB per request", "inclusive 0.01 tolerance", "Noul stays in [0,01,0.99]"-style contract details) and never explains general concepts, matching anchor 4's 'efficient with minor trimmable instances'. It falls short of anchor 5 because the path "src/examples/python/generation/" is repeated four times and the 'Relevant API Surface' section is a ~60-symbol manifest dump that earns few tokens per line.

4 / 5

Actionability

There is one code snippet ("model = ai('typesafe', api_key=api_key, trueThreshold=0.9) ... decision = triage.forward(model, {'ticket': ticket})") but it lacks imports and key setup, and the many features described — box localization, native questions, reranking, Gemini decisions — get zero runnable code, only prose constraints and pointers to "Runnable ... examples are under src/examples/python/generation/". This matches anchor 3 (some concrete guidance, incomplete, missing key details) rather than 4, since most feature areas are described rather than executable.

3 / 5

Workflow Clarity

A rough progression exists ('When To Use' bullets, a 'Core Pattern', and guardrails like "Start from package examples for exact native syntax"), but there is no sequenced workflow from task to working code — no steps such as pick signature → adapt example → verify with no-key transport → run against provider. This lands on anchor 3 (sequence implicit, checkpoints missing); no destructive or batch operations are involved, so the cap-3 rule is not the binding constraint, and it is above anchor 2 because the guardrails and per-topic organization give a coherent if implicit order.

3 / 5

Progressive Disclosure

Sections are clearly headed and the skill points to external materials ("Package API docs: `API.md` and `axir-api.json`", "Capability manifest: `axir-capabilities.json`", "Runnable examples: `examples/`"), but the bundle itself contains no reference files — none of those paths exist under the skill — and detailed contract material (probability tolerance rules, image byte/pixel limits, the Gemini request schema, the long API symbol list) is inlined in SKILL.md where anchor examples put it in separate files. This matches anchor 3 (some structure, references not clearly signaled as links, content that should be separate is inline).

3 / 5

Total

13

/

20

Passed

Description

66%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 distinctive, information-dense description that names a clear niche and includes an explicit 'Use when' trigger, but it reads as a feature-keyword dump: one action verb wrapped in package jargon, with natural trigger variations (ax, AxGen, Gemini/OpenAI decisions) missing. It would reliably trigger for the right skill but is less readable and comprehensive than the top anchor examples.

Suggestions

Lead with a third-person capability statement (e.g., 'Provides API patterns, validation rules, and examples for the generated `axllm` package') before the 'Use when' clause so the 'what' is distinct from the trigger.

Convert the feature-noun enumeration into concrete actions, e.g., 'declare typed boolean/class/score/box signatures', 'retain probabilities and provenance with (evidence)', 'run no-key deterministic checks'.

Add the natural trigger terms users would actually type — 'ax', 'AxGen', 'typed decisions', 'Gemini Decisions API', 'OpenAI decisions' — since the body covers those providers but the description never mentions them.

DimensionReasoningScore

Specificity

The description names the domain precisely ("writing Python code with `axllm`") but offers only that single action verb; the remainder ("Typesafe Jev image inputs, boolean/class/rubric score/box signatures, decision evidence and provenance, native Noul/Choice/Score/Box, structured criteria and hybrid generation") is an enumeration of feature nouns rather than concrete actions. It sits above anchor 2 (domain named, actions minimal/generic) because the enumerated capabilities are concrete and specific, but below anchor 4 because no several distinct actions are listed.

3 / 5

Completeness

Both elements are present: the explicit trigger clause "Use when writing Python code with `axllm`" answers 'when', and the feature enumeration conveys 'what'. It falls short of anchor 5 because the 'what' is never stated as a distinct capability statement (there is no third-person lead like 'Provides API patterns and examples for...') and the trigger phrases are jargon-heavy rather than concrete natural phrases; it is clearly above anchor 3 because the 'Use when' clause is explicit, not weakly implied.

4 / 5

Trigger Term Quality

Relevant keywords exist ("Python", "axllm", "Typesafe", "signatures", "decision evidence"), and a user of this generated package would say some of them, but heavy package-internal jargon ("Jev", "Noul/Choice/Score/Box") dominates while natural variations users would actually type — "ax", "AxGen", "typed decisions", "Gemini decisions", "OpenAI decisions" — are absent. This matches anchor 3 (some relevant keywords, missing common variations/synonyms) rather than 4, since the body itself shows the skill also covers google-gemini-decisions and openai-decisions, none of which appear as triggers.

3 / 5

Distinctiveness Conflict Risk

The package name "axllm" combined with niche terms like "Typesafe Jev", "Noul", and "rubric score/box signatures" carves out a clear niche with minimal overlap risk against any generic Python skill. This cleanly matches anchor 5 (clear niche with distinct triggers).

5 / 5

Total

15

/

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-typesafe/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.