optimize

Solve constrained optimization problems using Z3. Supports minimization and maximization of objective functions over integer, real, and bitvector domains.

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/optimize/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 validated workflow with a real bundle-script reference; the main weakness is redundant restating of the sat/unsat/timeout outcomes across steps that could be consolidated.

Suggestions

Consolidate the sat/unsat/unknown/timeout outcome handling into one place (e.g. Step 3) and reference it from Step 2 to remove the triple repetition.

Add a one-line note on multi-objective lexicographic ordering now that the intro mentions it, or trim that mention if it is not central.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes competence, but the sat/unsat/unknown/timeout outcomes are restated across Step 2 Expectation, Step 3 Expectation, and Step 3 Result, which could be tightened; this matches 'mostly efficient but could be tightened' rather than the fully-lean score-3 anchor.	2 / 3
Actionability	Provides a complete, executable SMT-LIB2 example and concrete copy-paste bash invocations of optimize.py with a full parameters table, matching the fully-executable score-3 anchor.	3 / 3
Workflow Clarity	Clear three-step sequence (formulate -> run -> interpret) with explicit outcome branching and a feedback loop ('On unsat or timeout: check constraints for contradictions or simplify'); this is not a destructive/batch operation so no cap applies, matching the score-3 anchor.	3 / 3
Progressive Disclosure	Under 50 lines and single-purpose, with well-organized Step 1/2/3 + Parameters sections and a single one-level reference to scripts/optimize.py (verified to exist); per the simple-skills scoring note this qualifies for score 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, concise, and third-person with a clear niche, but it lacks an explicit 'Use when...' trigger clause and its keywords are somewhat technical, capping completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g. 'Use when the user asks to minimize or maximize an objective subject to constraints, or mentions Z3, SMT optimization, or linear/integer programming').

Broaden trigger terms with natural user phrasings like 'find the minimum/maximum', 'optimize subject to', or 'linear/integer programming'.

Optionally mention soft constraints or multi-objective optimization in the trigger list since the body supports them.

Dimension	Reasoning	Score
Specificity	Lists concrete operations ('minimization and maximization of objective functions') and specific domains ('integer, real, and bitvector domains'), matching the multiple-specific-actions anchor rather than the partial score-2 anchor.	3 / 3
Completeness	Clearly states what the skill does but has no 'Use when...' clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 2; 'when' is only implied by the domain wording.	2 / 3
Trigger Term Quality	Relevant terms ('optimization', 'minimize/maximize', 'Z3', 'objective functions') are present but lean technical and omit common natural variations a user might say (e.g. 'find the minimum', 'optimize subject to'), so coverage is partial rather than complete.	2 / 3
Distinctiveness Conflict Risk	'Constrained optimization problems using Z3' is a clear niche with distinct triggers unlikely to overlap with other skills, matching the score-3 anchor.	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/optimize/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.