benchmark

Measure Z3 performance on a formula or file. Collects wall-clock time, theory solver statistics, memory usage, and conflict counts. Results are logged to z3agent.db for longitudinal tracking.

Quality

77%

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/benchmark/SKILL.md

Quality

Content

87%

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

The content is concise, highly actionable with verified executable commands, and well-organized with real one-level bundle references; its only gap is the absence of explicit validation checkpoints for batch/db operations, which caps workflow clarity.

Suggestions

Add an explicit verification step after batch runs, e.g. confirm z3agent.db contains the new run ('python3 ../../shared/z3db.py runs --skill benchmark --last 1') before declaring success.

Include a checkpoint in Step 1 to check the z3 exit code / result validity before logging, so failed runs are handled explicitly.

Add a brief error-recovery note for when Z3 times out or returns 'unknown' during a multi-run benchmark.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence; it never explains what Z3/SMT is and the Action/Expectation/Result structure is tight with every section earning its place.	3 / 3
Actionability	Provides fully executable commands (e.g. 'python3 scripts/benchmark.py --file problem.smt2 --runs 5') referencing a verified script, plus a complete parameters table with types and defaults — copy-paste ready.	3 / 3
Workflow Clarity	A clear 3-step Action/Expectation/Result sequence exists, but batch runs ('--runs N') and database logging lack explicit validation/verification checkpoints, which the guidelines say caps workflow clarity at 2 for batch/db operations.	2 / 3
Progressive Disclosure	Content is well-organized into labeled sections with one-level-deep references to real bundle files (verified scripts/benchmark.py; ../../shared/z3db.py), appropriate for this single-purpose skill.	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 distinctive about Z3 performance measurement and db-backed tracking, but it omits an explicit 'Use when...' trigger clause, which caps completeness and trigger-term quality below the top level.

Suggestions

Add an explicit trigger clause such as 'Use when benchmarking Z3, investigating solver performance regressions, or comparing tactic strategies.'

Expand natural trigger terms to include phrasings users actually say (e.g. 'benchmark Z3', 'profile an SMT solver', 'Z3 is slow').

Keep the concrete capability list but pair it with the when-guidance so both 'what' and 'when' are explicit.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Collects wall-clock time, theory solver statistics, memory usage, and conflict counts', 'logged to z3agent.db for longitudinal tracking'), matching the multiple-specific-actions anchor.	3 / 3
Completeness	Clearly answers 'what' but provides no explicit 'when' trigger guidance, which per the judging guidelines caps completeness at 2 even though the what-side is strong.	2 / 3
Trigger Term Quality	Contains relevant domain terms a user might say ('Z3 performance', 'wall-clock time', 'memory usage') but lacks a 'Use when...' trigger clause and common request phrasings, so it sits at 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (Z3 performance benchmarking with longitudinal db tracking) with distinct triggers, making conflict with other skills unlikely.	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/benchmark/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.