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

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/benchmark/SKILL.md

Quality

Content

80%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 body is lean, actionable, and well-sequenced with executable commands and a real referenced script. The main weakness is a missing explicit validation/error-recovery checkpoint for the database-writing batch run.

Suggestions

Add an explicit validation checkpoint in Step 1 (e.g. 'If z3 returns unknown/timeout or exit_code != 0, note it in the log before proceeding') to form a feedback loop around the batch run.

Tighten the closing line of the intro paragraph, which partially restates the first sentence, to remove minor padding.

Consider a brief 'Advanced' pointer (e.g. tactic-strategy configuration) to make progressive disclosure fully explicit.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes competence — it jumps to a 3-step procedure with concrete commands and a parameter table, with only minor padding (the closing paragraph restates the intro's purpose).	4 / 5
Actionability	It provides copy-paste-ready commands for every step (benchmark.py invocations, z3db.py queries) plus a full parameter table, and the referenced scripts/benchmark.py exists and matches the documented interface, covering the common cases.	5 / 5
Workflow Clarity	Steps are clearly sequenced with Action/Expectation/Result structure across three phases, but for a destructive/batch operation (repeated Z3 runs writing to z3agent.db) there is no explicit validation or error-recovery checkpoint before logging, leaving a minor validation gap rather than a full feedback loop.	4 / 5
Progressive Disclosure	Content is well-organized into steps plus a parameters section, and the one bundle file (scripts/benchmark.py) is referenced one level deep via concrete commands; minor gap is that there is no 'Advanced' section signaling where deeper material lives, but for a skill this size the structure is appropriate.	4 / 5
	Total	17 / 20 Passed

Description

56%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 is concrete and domain-specific about what it measures, but it omits any explicit 'Use when' trigger guidance, which caps completeness. Trigger-term coverage is more technical than natural.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when benchmarking Z3 on SMT formulas, profiling solver performance, or detecting regressions.'

Surface natural user phrasing and file extensions in the description (e.g. 'Z3 performance', '.smt2 files', 'solver timing') to improve trigger term coverage.

Mention tactic-strategy comparison as a concrete capability to round out the action list.

Dimension	Reasoning	Score
Specificity	Names the domain (Z3/SMT performance) and lists several concrete measurements collected (wall-clock time, theory solver statistics, memory usage, conflict counts), with only minor coverage gaps such as tactic-strategy comparison not being enumerated as an output.	4 / 5
Completeness	It gives a clear 'what' (measures Z3 performance and collects named statistics) but contains no 'Use when...' clause or equivalent trigger guidance, so the 'when' is only weakly implied and completeness is capped at 3 per the guidelines.	3 / 5
Trigger Term Quality	Relevant technical terms (Z3, SMT-LIB2, statistics, performance regressions) are present, but it lacks natural user-facing phrases like 'benchmark Z3', 'measure Z3 performance', or file extensions a user might say; coverage leans toward jargon over common synonyms.	3 / 5
Distinctiveness Conflict Risk	The Z3/SMT performance benchmarking niche is fairly distinct and unlikely to collide with unrelated skills, though the broad word 'performance' leaves minor overlap risk with generic profiling skills.	4 / 5
	Total	14 / 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/benchmark/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.