Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From midnight-verify
Compact CLI tooling claim classification and method routing. Determines what kind of CLI claim is being verified and which verification method applies: CLI execution (primary for behavioral claims) or source investigation (for internal/architectural claims). Handles claims about compact compile flags, compactc behavior, compiler output structure, error messages, exit codes, version management, and CLI installation. Loaded by the /midnight-verify:verify command alongside the hub skill.
npx claudepluginhub devrelaicom/midnight-expert --plugin midnight-verifyHow this skill is triggered — by the user, by Claude, or both
Slash command
/midnight-verify:verify-toolingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill classifies Compact CLI tooling claims and determines which verification method to use. The /midnight-verify:verify command loads this alongside the `midnight-verify:verify-correctness` hub skill.
Verification by running Compact CLI commands and observing output. Checks CLI availability, runs commands, captures stdout/stderr/exit code, inspects filesystem changes, and interprets results. Covers flag existence, flag behavior, output structure, error messages, exit codes, version info, and CLI-vs-compactc comparisons. Loaded by the cli-tester agent.
This skill should be used when the user asks about the Compact CLI, Compact Dev Tool, Compact Developer CLI, or compact devtools for Midnight Network smart contract development, including setting up the Compact toolchain on a new machine, resolving "compact: command not found" or "No default compiler set" errors, validating that Compact source code compiles correctly, switching between compiler versions, pinning a project to a specific compiler version, understanding why compilation is slow or how to speed it up, figuring out which version of the compiler or language they're running, setting up a project-local toolchain directory, configuring import search paths for multi-file contracts, understanding error messages or exit codes from the compiler or formatter, setting up or uninstalling the Compact toolchain, resolving GitHub API rate limiting when listing or updating versions, or troubleshooting why format or fixup is reporting failures
This skill should be used when extracting testable claims from Midnight documentation or source content. Covers how to identify verifiable statements about Compact syntax, types, APIs, compiler behavior, and runtime errors. Defines the JSON output schema for structured claim lists. Relevant when asked to "extract claims", "find testable statements", "parse documentation for verifiable facts", or "produce a claim list from content chunks". Used by the claim-extractor agent in the midnight-fact-check pipeline.
Share bugs, ideas, or general feedback.
This skill classifies Compact CLI tooling claims and determines which verification method to use. The /midnight-verify:verify command loads this alongside the midnight-verify:verify-correctness hub skill.
Routing rule: If the claim is about what the language allows/disallows, route to verify-compact. If the claim is about what the CLI does when you run it, route here.
Overlap: "The compiler rejects X" could be either. If the claim is about a language rule ("you can't assign Field to Uint<8>"), it's Compact. If the claim is about CLI behavior ("the compiler exits with code 1 on syntax errors"), it's tooling.
CLI execution is the default. Source investigation is for when you genuinely can't run a command to answer the question.
midnight-verify:verify-by-source skill). For internal/architectural claims about how the compiler works under the hood.| Claim Type | Example | Primary | Secondary |
|---|---|---|---|
| Flag existence | "--skip-zk is a valid flag" | @"midnight-verify:cli-tester (agent)" (run --help, check output) | — |
| Flag behavior | "--skip-zk skips PLONK key generation" | @"midnight-verify:cli-tester (agent)" (compile with/without, compare output dirs) | @"midnight-verify:source-investigator (agent)" |
| Output structure | "Compilation produces build/contract/index.js" | @"midnight-verify:cli-tester (agent)" (compile, inspect filesystem) | — |
| Error messages | "Undeclared variables produce 'not in scope' error" | @"midnight-verify:cli-tester (agent)" (feed bad input, check stderr) | @"midnight-verify:source-investigator (agent)" |
| Exit codes | "Compilation errors exit with non-zero" | @"midnight-verify:cli-tester (agent)" (run, check $?) | — |
| Version info | "--language-version returns the current version" | @"midnight-verify:cli-tester (agent)" (run, parse output) | — |
| Installation | "compact is installed via npm" | @"midnight-verify:cli-tester (agent)" (check which compact) | @"midnight-verify:source-investigator (agent)" |
| CLI vs compactc | "compact compile invokes compactc" | @"midnight-verify:cli-tester (agent)" (run both, compare) | @"midnight-verify:source-investigator (agent)" |
| Compiler internals | "The compiler is written in Scheme" | @"midnight-verify:source-investigator (agent)" | — |
| CLI wrapper internals | "compact is a shell script wrapper" | @"midnight-verify:source-investigator (agent)" | @"midnight-verify:cli-tester (agent)" (file type check) |
When in doubt:
CLI execution is preferred whenever possible. The command ran and produced this output — that's more authoritative than reading source code about what the output should be.
The @"midnight-verify:cli-tester (agent)" may load this skill for context. It is a hint only — never cite skill content as evidence.
midnight-tooling:compact-cli skill — expected flags, compilation patterns, version management