codeguard-pascal

Pascal / Delphi Codeguard Gate

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

Start in 30 seconds

1. At the repository root, confirm that 无专用标记文件 or the target file exists.
2. Probe tools:command --version。
3. Read-only check first:``。
4. Classify results into: code violations, missing configuration, missing tools, tool internal errors.
5. Only perform safely fixable items:ptop -b .。
6. Rerun lint, and run the project's existing test/build gates.

You can directly ask:

• "Check this Pascal / Delphi project, don't modify anything yet, and give me a classification of lint failures."
• "Only fix formatting issues in Pascal / Delphi, and list semantic issues first."
• "Verify Pascal / Delphi lint, test, and build evidence before committing."

Capability boundaries

✅ Good at handling

1. Identify the Pascal / Delphi workspace based on .pas, .dpr, .dpk, .lpr and project markers.
2. Run `` and retain exit codes, scope, and tool versions.
3. Distinguish formatting, static rules, configuration, dependency, and environment-related failures.
4. Use ptop -b . to handle reversible issues and rescan.
5. Report local results and CI/build/test evidence in separate layers.

⚠️ Requires conditions

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

❌ Out of scope

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 cover up real problems.
4. Do not claim "checks passed" when tools or configuration are missing.

When to use

• The user requests checking or fixing Pascal / Delphi code standards.
• AI modified .pas, .dpr, .dpk, .lpr, and pre-commit verification is needed.
• CI has failures related to Pascal / Delphi 工具链 .
• Need to determine whether an issue can be fixed automatically 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 message and there is no project context, first provide 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 or 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, inspect the diff first; destructive or large-scale changes must be explicitly confirmed by the user.

Execution Contract

Item	Current Fact
Status	stable(since Codeguard V0.5)
File Extension	.pas, .dpr, .dpk, .lpr
Project Marker	No dedicated marker file
Integration Configuration	Based on the repository's existing configuration
Tool Preparation	pasfmt
Probe Command	使用命令查找与项目配置检查
lint	未接入
format/fix	ptop -b .
Project-level gate	未接入

Standard Workflow

Step 1: Determine the real scope

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

Step 2: Read the project contract

Read the actual commands in Based on the repository's existing configuration and CI. The repository configuration takes precedence over this skill's examples; if the two conflict, report the differences first.

Step 3: Probe tools and versions

Run 对应工具 --version. If a tool is missing, the version is incompatible, or the configuration cannot be loaded, record it as "unable to verify", not as passed.

Step 4: Run read-only checks

Run 目标平台官方诊断, and record the command, working directory, exit code, tool version, and first actionable error.

Step 5: Failure classification

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

Step 6: Controlled fixes

Prefer to run ptop -b .. Handle only issues that are certain and reversible; 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. Only write "passed" 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. Evidence layering: 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 first: do not override the project's existing ignore, dialect, target, or version constraints.
5. Do not make things up: Tools that were not run, configurations that were not seen, and platforms that were not verified must be explicitly marked.

Output template

Pascal / Delphi 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 way to prepare.
2. A formatter is not a linter — all-green formatting cannot override static rules or compilation errors.
3. The root directory determines the result — running in the wrong module may miss checks or load the wrong configuration.
4. Placeholders are not literal arguments — {file} must be replaced with real, authorized paths.
5. Auto-fixes may expand the diff — after fixing, review the diff first, then run the regression gate.
6. Generated and vendor directories require an explicit policy — you must not casually scan or modify third-party content across the whole repository.

Domain pitfalls and fixes

1. Domain pitfall — when only formatting capability is available, you must not claim that static checks are complete; compiler or IDE diagnostics are still required.

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 files;
4. The authoritative command in CI;
5. Whether auto-fixes are allowed.

FAQ

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

Q2: Can you automatically add ignore or suppression? No. 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 you avoid changing too much at once? Fix in batches by failure category and file first, and rerun the original command and review the diff for each batch.

Q6: If it passes locally, can you say CI will pass? No. You also need to align with CI's version, environment variables, operating system, and command scope.

Load resources on demand

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