codeguard-crystal

Crystal Codeguard Gate

Goal: turn "looks fine" into repeatable tool evidence, and honestly distinguish passed, failed, unverifiable, and planned.

Start in 30 seconds

1. Confirm at the repository root that shard.yml or the target file exists.
2. Probe tools:ameba --version。
3. Read-only check first:ameba。
4. Classify results as: code violations, missing configuration, missing tools, tool internal errors.
5. Execute only for safely fixable items:crystal tool format。
6. Re-run lint, and run the project's existing test/build gates.

You can directly ask:

• "Check this Crystal project, do not modify it first, give me a classification of lint failures."
• "Only fix Crystal formatting issues, list semantic issues first."
• "Verify Crystal lint, test, and build evidence before committing."

Capability boundaries

✅ Good at handling

1. Based on .cr and project markers, identify the Crystal workspace.
2. Execute ameba and retain exit codes, scope, and tool versions.
3. Distinguish formatting, static rules, configuration, dependency, and environment failures.
4. Use crystal tool format to handle reversible issues and re-scan.
5. Report local results in layers with CI/build/test evidence.

⚠️ Requires conditions

1. The target tool must already be installed and its version compatible with project constraints.
2. Must be executed from the correct repository or module root directory.
3. If the project has custom configuration, the committed configuration prevails.
4. Whether generated code, vendor, and cache directories are scanned must follow repository rules.

❌ Not applicable

1. Do not treat formatter passing as compilation, test, or security audit passing.
2. Do not silently install tools, upgrade dependencies, or modify team rules.
3. Do not use suppress/ignore/raising thresholds to mask real issues.
4. Do not claim "check passed" when tools or configuration are missing.

When to use

• The user requests checking or fixing Crystal code standards.
• AI modified .cr, needs pre-commit verification.
• CI shows failures related to ameba .
• Need to determine whether an issue can be auto-fixed or must be handled manually.

When not to use

• When the main task is learning language syntax, framework design, or business modeling, use the corresponding language professional skill instead.
• When the main task is dependency vulnerabilities, security auditing, or license governance, use a dedicated security skill.
• When the user only asks to explain an error and there is no project context, first do a local explanation, and do not claim the repository is all green.

Data and security

This skill does not collect, upload, send, or store user code and credentials. By default, it only reads local repository configuration and runs local tools; it does not install dependencies over the network, and does not record tokens, passwords, or private source code. Before any automatic fix, check the diff first; destructive or large-scale modifications must be explicitly confirmed by the user.

Execute contract

Item	Current fact
Status	stable(since Codeguard V0.5)
File extension	.cr
Project marker	shard.yml
Onboarding configuration	shard.yml
Tool readiness	brew install crystal-ameba
Probe command	使用命令查找与项目配置检查
lint	ameba
format/fix	crystal tool format
Project-level gate	ameba

Standard Workflow

Step 1: Determine the true scope

Confirm the repository root, module roots, generated directories, vendor directories, and user-specified files. For multi-module projects, first list the modules to be scanned; do not guess based on the current directory.

Step 2: Read the project contract

Read shard.yml and the actual commands in CI. Repository configuration takes precedence over this skill's examples; if the two conflict, report the difference first.

Step 3: Probe tools and versions

Run 对应工具 --version. Missing tools, incompatible versions, or failure to load configuration are all recorded as "unable to verify", not as a pass.

Step 4: Run read-only checks

Run ameba, recording the command, working directory, exit code, tool version, and the first actionable error.

Step 5: Failure classification

Type	Typical signal	Handling
Formatting	Indentation, whitespace, import order	Formatter is allowed, then check the diff
Static rules	unused, complexity, naming, dangerous API	Minimal semantic fix; no bulk guessing
Configuration	parser/config/schema not found	Fix onboarding or report prerequisites
Environment	command not found, version conflict	Report installation/version requirements; do not install silently
Tool internal error	crash, timeout, parser exception	Preserve raw evidence and narrow the reproduction scope

Step 6: Controlled fixes

Prioritize running crystal tool format. Only handle clearly reversible issues; dependency upgrades, rule exemptions, generated files, and business semantic changes must be explained separately.

Step 7: Verification loop

Re-run the same lint command, then run the project's existing tests and build. Write "pass" only when the command, scope, and exit code are all clear; otherwise write "not run" or "unable to verify".

Rules

1. Re-verify with the same command: after fixing, you must re-run the original command that triggered the failure.
2. Layered evidence: report lint, format, compile, test, and security separately.
3. Minimal changes: do not refactor along the way, and do not expand style fixes into business rewrites.
4. Configuration takes precedence: do not override the project's existing ignore, dialect, target, or version constraints.
5. No fabrication: tools not run, configurations not seen, and platforms not verified must be clearly marked.

Output template

Crystal Codeguard 结果
- 范围：<仓库/模块/文件>
- 工具：<名称与版本>
- 命令：<实际命令>
- 状态：PASS / FAIL / UNVERIFIED / PLANNED
- 发现：<按格式/规则/配置/环境分类>
- 修改：<文件与原因；无修改写 none>
- 复验：<命令、退出码>
- 未验证：<测试/构建/平台差异>

Gotchas

1. A missing tool is not a pass — you must output UNVERIFIED and a clear preparation method.
2. A formatter is not a linter — all-green formatting cannot cover static rules or compilation errors.
3. The root directory determines the result — Running in the wrong module may miss detections or load an incorrect configuration.
4. Placeholders are not literal arguments — {file} and must be replaced with real, authorized paths.
5. Automatic fixes may enlarge the diff — after fixing, review the diff first, then run the regression gate.
6. Generated and vendor directories require an explicit policy — do not arbitrarily scan or modify third-party content across the whole repository.

Domain pitfalls and fixes

1. Domain pitfalls — Ameba configuration and the Crystal version must match; formatting does not replace crystal spec。

When information is insufficient

Do not just say "please provide more information." First give a safe, read-only inspection plan, and list the specific items that still need confirmation:

1. repository/module root directory;
2. target tool and version;
3. project configuration file;
4. the authoritative command in CI;
5. whether automatic fixes are allowed.

FAQ

Q1: If the tool is not installed, can we conclude the code is fine? No. The status must be UNVERIFIED。

Q2: Can ignore or suppression be added automatically? No. An exemption is allowed only when the user explicitly accepts it and the reason is recorded.

Q3: Why does it still fail after formatting? The formatter only covers formatting; static rules, configuration, compilation, and tests still need to be handled separately.

Q4: Should generated code be scanned? By default, follow the repository configuration; when there are no rules, exclude generated/vendor first, then explain to the user.

Q5: How can we avoid changing too much at once? First fix in batches by failure category and file, and rerun the original command and review the diff after each batch.

Q6: If it passes locally, can we say CI will pass? No. CI's versions, environment variables, operating system, and command scope must also be aligned.

Load resources on demand

• When encountering exit codes, failure classification, or exemption decisions, read references/rules/gate-rules.md。
• When you need to verify this language's registry, toolchain, and project configuration, read references/tooling/toolchain.md。
• When you need copyable task examples, read by scenario examples/; there is no need to load all of them at once.