program-to-tlaplus-spec-generator

Automatically generate TLA+ specifications from program code, repositories, or system implementations. Use when asked to generate TLA+ spec, create TLA+ specification from code, convert program to TLA+, formalize system in TLA+, extract TLA+ model from code, or when working with formal specification of concurrent systems, distributed systems, protocols, algorithms, or state machines that need to be verified.

1.04x

Quality

75%

Does it follow best practices?

Impact

95%

1.04x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/program-to-tlaplus-spec-generator/SKILL.md

Quality

Content

61%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 thorough, well-organized generation workflow with concrete templates and clearly signaled references. It is held back by redundancy between inline content and reference files, an unreferenced template asset, and the absence of an explicit verify-and-iterate checkpoint for the generated spec.

Suggestions

Add an explicit validation/feedback step to the workflow (e.g., run the SANY parser or TLC on the generated spec, review errors, fix, and re-run) so generation has a verify-and-iterate checkpoint.

Remove the inline Language-Specific Considerations section or reduce it to a one-line pointer, since the same material lives in references/language_patterns.md.

Reference assets/template.tla from the Generate TLA+ Module step so the bundle asset is discoverable and used.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and well-structured, but the Language-Specific Considerations section duplicates references/language_patterns.md and the Tips for Effective Specs section offers generic advice Claude already knows.	3 / 5
Actionability	It provides a concrete TLA+ module template, a TLC configuration template, and example abstraction-mapping tables, but the module template relies on bracketed placeholders ([constants], [action definition]) rather than fully copy-paste-ready code.	4 / 5
Workflow Clarity	The 9-step generation sequence is clearly numbered with per-step outputs, but there is no explicit validation or feedback checkpoint (e.g., parse with SANY or run TLC, then fix and re-run) for the generated specification.	3 / 5
Progressive Disclosure	Two real one-level-deep references are clearly signaled with markdown links, but assets/template.tla is never referenced from the body and the inline Language-Specific section duplicates its companion reference file.	4 / 5
	Total	14 / 20 Passed

Description

90%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 description with an explicit Use-when trigger clause and comprehensive, natural trigger phrasings tied to a distinctive niche. The only weakness is that the stated capability is a single action repeated with synonyms rather than several distinct concrete actions.

Dimension	Reasoning	Score
Specificity	The description names the domain and one core action ("Automatically generate TLA+ specifications from program code, repositories, or system implementations") with several source variants, but it does not list multiple distinct concrete actions as a 4 or 5 would require.	3 / 5
Completeness	It explicitly answers both what (generate TLA+ specifications from code/repos/implementations) and when ("Use when asked to generate TLA+ spec... or when working with formal specification of...").	5 / 5
Trigger Term Quality	It gives comprehensive natural trigger phrasings users would say ("generate TLA+ spec", "convert program to TLA+", "formalize system in TLA+", "extract TLA+ model from code") plus domain synonyms (concurrent systems, distributed systems, protocols, algorithms, state machines).	5 / 5
Distinctiveness Conflict Risk	TLA+ specification generation is a clear, narrow niche with distinct triggers, making conflict with other skills minimal.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ArabelaTso/Skills-4-SE
Path: skills/program-to-tlaplus-spec-generator/SKILL.md
Commit: 4f38503

Reviewed: 19 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.