static-analysis

Run Clang Static Analyzer (scan-build) on Z3 source and log structured findings to z3agent.db.

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/static-analysis/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 a well-structured, actionable workflow with executable commands, explicit validation checkpoints, and real script references. The only meaningful weakness is the repetitive Action/Expectation/Result template, which adds mild verbosity without adding guidance.

Suggestions

Collapse the repeated 'Action: / Expectation: / Result:' scaffolding into direct imperative steps (e.g., '1. Run: python3 scripts/static_analysis.py --build-dir build') to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body avoids concept-explanation fluff and assumes Claude's competence, but the 'Action: / Expectation: / Result:' template repeated across three steps is mild verbosity that could be tightened into more direct imperatives.	2 / 3
Actionability	It provides fully executable, copy-paste-ready commands ('python3 scripts/static_analysis.py --build-dir build'), concrete SQL query examples, and a complete parameters table with types, defaults, and descriptions.	3 / 3
Workflow Clarity	The three steps are clearly sequenced, each with explicit 'On success / On failure' or 'On zero findings / On findings' validation checkpoints and error-recovery guidance, giving strong feedback loops for a batch analysis operation.	3 / 3
Progressive Disclosure	The ~70-line body is organized into clear sections and keeps detail inline appropriately for a single-purpose skill; the referenced scripts/static_analysis.py is a real one-level bundle file with no nested reference chains.	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 distinct, naming concrete tools and a clear target, but it omits an explicit 'when to use' trigger clause and is lean on trigger-term variations. Adding a 'Use when ...' sentence would raise completeness and trigger coverage.

Suggestions

Append a 'Use when ...' trigger clause (e.g., 'Use when running static analysis sweeps over Z3 or tracking static-checker regressions across commits') to explicitly answer when Claude should invoke this skill.

Broaden trigger terms to include natural variations like 'static checks', 'bug reports', or 'findings' so the description matches more of the phrasings a user would actually say.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions with named tools and targets: 'Run Clang Static Analyzer (scan-build) on Z3 source and log structured findings to z3agent.db.' It is not vague — it specifies the analyzer, the subject, and the structured output destination.	3 / 3
Completeness	It clearly answers 'what does this do' but provides no 'Use when...' clause or equivalent explicit trigger guidance for when Claude should invoke it, which caps completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	It includes the core natural terms a Z3 developer would say ('Clang Static Analyzer', 'scan-build', 'Z3'), but the phrasing is lean and misses common variations such as 'static checks', 'bug reports', or 'findings analysis' that users might also say.	2 / 3
Distinctiveness Conflict Risk	The combination of 'Clang Static Analyzer (scan-build)' plus 'Z3 source' plus 'z3agent.db' carves out a clear niche with distinct triggers that are unlikely to conflict 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/static-analysis/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.