solve

Check satisfiability of SMT-LIB2 formulas using Z3. Returns sat/unsat with models or unsat cores. Logs every invocation to z3agent.db for auditability.

Quality

76%

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/solve/SKILL.md

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured, actionable, and has a clear workflow with validation checkpoints; its only weakness is mild redundancy from the Action/Expectation/Result framework restating output states.

Suggestions

Eliminate the repeated enumeration of sat/unsat/unknown/timeout across Step 2 Result and Step 3 Expectation — state it once and reference it, or trim the Expectation lines that restate the Result.

Dimension	Reasoning	Score
Conciseness	The body is lean and does not explain concepts Claude already knows, but the Action/Expectation/Result structure repeats the sat/unsat/unknown/timeout output states across Step 2 Result and Step 3 Expectation, so it could be tightened — matching the score-2 anchor.	2 / 3
Actionability	Provides fully executable commands ('python3 scripts/solve.py --formula ...', '--file', '--debug') plus a complete Parameters table referencing the real scripts/solve.py bundle file — copy-paste ready.	3 / 3
Workflow Clarity	The three-step sequence has explicit checkpoints: Step 1 gates on valid SMT-LIB2 (run encode first if needed) and Step 3 gives per-outcome recovery (try simplify / increase timeout), matching the score-3 anchor of clear sequence with validation and feedback loops.	3 / 3
Progressive Disclosure	A single-purpose skill under 50 lines, well-organized into steps and a parameters table; the referenced scripts/solve.py is a real one-level-deep bundle file with no nested reference chains, so the simple-skill allowance yields a 3.	3 / 3
	Total	11 / 12 Passed

Description

67%

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 is specific and occupies a clear, low-conflict niche, but it omits explicit 'when to use' trigger guidance and only partially covers natural trigger-term variations.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when checking whether SMT-LIB2 formulas or constraint sets are satisfiable, or when the user mentions Z3, SMT, sat/unsat, models, or unsat cores').

Broaden trigger-term coverage with natural variations such as 'SMT solver', 'constraint solving', and 'is this formula/constraint set satisfiable'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'Check satisfiability', 'Returns sat/unsat with models or unsat cores', 'Logs every invocation' — matching the score-3 anchor of multiple specific concrete actions.	3 / 3
Completeness	Clearly answers 'what' (check satisfiability, return models/cores, log invocations) but lacks any 'Use when...' clause or explicit trigger guidance, so per the rubric completeness is capped at 2.	2 / 3
Trigger Term Quality	Relevant terms (SMT-LIB2, Z3, satisfiability, sat/unsat, models, unsat cores) are present and natural for this niche, but common variations like 'SMT solver', 'constraint solving', or 'is this formula satisfiable' are missing, matching the score-2 anchor.	2 / 3
Distinctiveness Conflict Risk	SMT-LIB2/Z3 satisfiability checking is a clear, narrow niche with distinct triggers; it is unlikely to be confused with other skills.	3 / 3
	Total	10 / 12 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/solve/SKILL.md
Commit: 1c89937

Reviewed: 3 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.