prove

Prove validity of logical statements by negation and satisfiability checking. If the negation is unsatisfiable, the original statement is valid. Otherwise a counterexample is returned.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/prove/SKILL.md

Quality

Content

82%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 content is lean, executable, and well-structured with a real backing script and clear outcome-based branching. Merging the redundant Step 2/3 output handling and adding an explicit pre-run formula validation checkpoint would push it higher.

Suggestions

Collapse the overlapping output-interpretation content in Step 2 and Step 3 into a single section to remove redundancy.

Add an explicit validation checkpoint (e.g. check that variables are declared and the negated formula parses) before invoking the prover.

Consider moving the full parameters table to a short reference block or keeping it inline but trimming duplicate default descriptions.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes competence, using a tight Action/Expectation/Result structure without explaining SMT basics, but Step 2 and Step 3 redundantly restate the output interpretation.	4 / 5
Actionability	Provides copy-paste-ready, executable commands for the common cases (conjecture+vars, file input, debug tracing) backed by the real scripts/prove.py, covering the typical invocation patterns.	5 / 5
Workflow Clarity	Steps are clearly sequenced with outcome-based branching (valid/invalid/unknown/timeout) as feedback loops, but there is no explicit validation checkpoint of the formula before running and Steps 2-3 overlap.	4 / 5
Progressive Disclosure	Well-organized into labeled sections with a one-level-deep reference to scripts/prove.py and clearly signaled cross-skill links (encode, explain, simplify); the inline parameters table is appropriately sized for this skill.	4 / 5
	Total	17 / 20 Passed

Description

53%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.

The description clearly conveys what the skill does using a concrete method, but omits any explicit trigger guidance for when to invoke it. Adding a 'Use when...' clause with natural user phrases would raise completeness and trigger_term_quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to prove or disprove a logical statement, conjecture, or SMT-LIB assertion.'

Include natural synonyms users might say (theorem, tautology, validity check) to broaden trigger coverage.

Keep third-person voice (already correct) and avoid adding padding beyond the trigger clause.

Dimension	Reasoning	Score
Specificity	Names the domain ('logical statements') and two concrete actions ('negation and satisfiability checking', 'counterexample is returned'), but stops short of a comprehensive list of capabilities.	3 / 5
Completeness	The 'what' is stated clearly (prove validity via negation/satisfiability), but there is no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Relevant natural terms like 'prove', 'validity', and 'counterexample' appear, but common synonyms (theorem, tautology, SMT) and the natural phrasing a user would say are missing.	3 / 5
Distinctiveness Conflict Risk	The theorem-proving-via-SMT niche is fairly distinct with minimal conflict risk, though it could marginally overlap with a generic 'simplify' or SMT skill.	4 / 5
	Total	13 / 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: Z3Prover/z3
Path: .github/skills/prove/SKILL.md
Commit: 6aa9416

Reviewed: ~2 hours 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.