CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

axir-language-backend

Use when adding or changing generated AxIR language backends in this repo, including target registration, codegen templates, package metadata, examples, conformance, and verification. This is a repo-maintainer skill and must not be emitted into generated Ax packages.

Quality

87%

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

78%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 an exceptionally dense, non-generic rulebook with real file paths, commands, and explicit acceptance gates — highly actionable for a repo maintainer. Its main weakness is progressive disclosure: the lone reference to regex.md is buried in a paragraph and the file is missing from the bundle entirely.

Suggestions

Fix the dangling reference: either create references/regex.md with the UTF-16 semantics and matcher invariants, or point at the actual repo location of that material instead of a bare 'see regex.md'.

Surface external material clearly with a dedicated section or list (e.g., '## References — regex.md: UTF-16 pattern semantics') rather than embedding the only file reference mid-paragraph under 'Session validation and cancellation'.

Add a short failure-recovery loop to the Acceptance Bar (e.g., what to do first when 'axir verify' fails for the new target) so the validation gates double as feedback loops rather than pass/fail checks only.

DimensionReasoningScore

Conciseness

The body is dense, repo-specific imperative guidance ('survive seed domination, and use selection's objective averaging/scalarization', 'Delegated MCP tests abort only after the child starts its imported tool') with no explanation of concepts Claude already knows and no padding. Every bullet carries a non-obvious repo invariant, matching the lean/efficient anchor.

5 / 5

Actionability

Concrete, executable guidance is present: real file paths ('tools/axir/internal/axir/codegen.go', 'verify.go', '*_core_emit.go') and copy-paste commands ('npm run test:axir', 'axir verify --targets python,java,cpp,<new-target>'). Not 5 because much of the Implementation Rules section is policy/constraint statements with no generated-code exemplar showing the intended template shape.

4 / 5

Workflow Clarity

A clear ordered progression exists (First Checks → Implementation Rules → Required Touchpoints → Acceptance Bar → Avoid) with explicit validation gates ('npm run test:axir passes', 'axir verify ... passes for all default suites'). Not 5 because there are no failure-recovery feedback loops (no 'if verification fails, do X') and steps are not numbered.

4 / 5

Progressive Disclosure

Section structure is good, but the single external reference is buried in prose ('see regex.md for UTF-16 semantics') and regex.md does not exist anywhere in the skill bundle, making it a dangling reference. The dense rule lists also carry everything inline with no clearly signaled one-level-deep references, fitting 'some structure; references present but not clearly signaled'.

3 / 5

Total

16

/

20

Passed

Description

92%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, explicit description that clearly states both what the skill covers and when to use it, with concrete trigger phrases and a useful scope boundary separating it from product skills. Keyword coverage could add natural language-name variations maintainers would say.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete actions with comprehensive coverage: 'adding or changing generated AxIR language backends... including target registration, codegen templates, package metadata, examples, conformance, and verification'. No gaps in coverage of the backend-maintenance scope are evident, matching the comprehensive anchor rather than the 'minor gaps' anchor.

5 / 5

Completeness

Both halves are explicit: an 'Use when adding or changing generated AxIR language backends...' clause with concrete trigger phrases, and a concrete what-enumeration of the six sub-areas. It also adds an explicit scope boundary ('must not be emitted into generated Ax packages'), exceeding the score-4 anchor where 'when' could be more specific.

5 / 5

Trigger Term Quality

Good keyword coverage with terms maintainers would naturally say ('language backends', 'codegen templates', 'conformance', 'verification'), but common variations such as specific target language names (Python, Java, Go) are absent from the description itself. Not score 5 because synonyms and natural phrasing variants are incompletely covered; not 3 because the present keywords are relevant and non-generic.

4 / 5

Distinctiveness Conflict Risk

Clear niche ('generated AxIR language backends in this repo') with distinct triggers and an explicit disambiguation from the Ax product skills ('repo-maintainer skill and must not be emitted into generated Ax packages'), so overlap risk with other skills is minimal.

5 / 5

Total

19

/

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

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

ax-llm/ax

Path

tools/axir/skills/axir-language-backend/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.