Goal: turn "looks fine" into repeatable tool evidence, and honestly distinguish pass, fail, unverifiable, and planned.
Start in 30 seconds
Currently planned only indicates that Codeguard can recognize no fixed extension, not that an executable gate exists.
- Clearly report "recognized, but currently cannot be verified by Codeguard".
- Keep the project's existing IDE, compiler, or platform diagnostic results; do not fabricate generic commands.
- If a check is necessary, use the target platform's official tool and mark the result as external evidence.
- Only after completing detection, lint, failure samples, and regression tests can the registry be upgraded to stable/beta.
Capability boundaries
✅ Good at handling
- Recognizing Ansible files and related user intent.
- Clearly explaining the current Codeguard support status and gaps.
- Defining verifiable acceptance conditions for future integration.
⚠️ Requires conditions
- Real target tool or platform diagnostic output.
- At least one failure sample and one passing sample.
- A repeatable non-interactive command or clear host boundary.
❌ Not applicable
- Do not execute nonexistent generic linter commands.
- Do not write extension recognition as a quality gate pass.
- Do not upgrade support status without runtime evidence.
When to use
- The user requests checking or fixing Ansible code standards.
- AI modified no fixed extension, requiring pre-commit validation.
- CI has failures related to
ansible-lint. - Need to determine whether a problem can be fixed automatically or must be handled manually.
When not to use
- The main task is learning language syntax, framework design, or business modeling; use the corresponding language professional skill instead.
- 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 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 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 automated fix, check the diff first; destructive or large-scale changes must be explicitly confirmed by the user.
Execution contract
| Project | Current facts |
|---|---|
| Status | planned(since Codeguard V0.3) |
| File extension | No fixed extension |
| Project marker | ansible.cfg, playbook.yml |
| Integration configuration | Based on the repository's existing configuration |
| Tool readiness | Playbook checks are handled by ansible-lint (yaml channel); semantic-level checks pending integration |
| Detection command | 使用命令查找与项目配置检查 |
| lint | ansible-lint |
| format/fix | ansible-lint --fix |
| Project-level gate | ansible-lint |
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, first list the modules that will be scanned; do not rely on guessing from the current directory.
Step 2: Read the project contracts
Read the actual commands in the repository's existing configuration and CI. Repository configuration takes precedence over this skill's examples; if the two conflict, report the differences first.
Step 3: Detect tools and versions
Run 对应工具 --version. Missing tools, incompatible versions, or configurations that fail to load are all recorded as "unable to verify," not as a pass.
Step 4: Perform read-only checks
Run ansible-lint, and record the command, working directory, exit code, tool version, and the first actionable error.
Step 5: Failure classification
| Type | Typical signal | Handling |
|---|---|---|
| Format | Indentation, whitespace, import order | Allow the formatter, then check 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 prerequisites |
| Environment | command not found, version conflicts | Report installation/version requirements; do not install silently |
| Tool internal errors | crash, timeout, parser exceptions | Preserve the original evidence and narrow the reproduction scope |
Step 6: Controlled fixes
Prefer to run ansible-lint --fix. Only handle 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 "pass" when the command, scope, and exit code are all clear; otherwise write "not run" or "unable to verify."
Rules
- Re-verify with the same command: After a fix, you must re-run the original command that triggered the failure.
- Evidence layering: Report lint, format, compile, test, and security separately.
- Minimal changes: Do not refactor along the way, and do not expand style fixes into business rewrites.
- Configuration takes precedence: Do not override the project's existing ignore, dialect, target, or version constraints.
- No fabrication: Tools not run, configurations not seen, and platforms not verified must be clearly marked.
Output template
Ansible 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
- Missing tools are not a pass — you must output
UNVERIFIEDand a clear preparation method. - A formatter is not a linter — all-green formatting cannot cover static rules or compilation errors.
- The root directory determines the result — running in the wrong module may miss checks or load the wrong configuration.
- Placeholders are not literal arguments —
{file}must be replaced with real, authorized paths. - Automatic fixes may expand the diff — after fixing, review the diff first, then run the regression gate.
- Generated and vendor directories require an explicit policy — Do not casually scan the entire repository or modify third-party content.
Domain pitfalls and fixes
- Domain pitfalls — The current entry is marked as planned; do not pass off the results of the YAML channel as an Ansible semantic gate.
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:
- repository/module root directory;
- target tool and version;
- project configuration file;
- the authoritative command in CI;
- whether automatic fixes are allowed.
FAQ
Q1: If the tool is not installed, can it be concluded that the code has no problems? No. The status must be UNVERIFIED。
Q2: Can ignore or suppression be added automatically? No. Exemptions may be granted only when the user explicitly accepts them 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; if there are no rules, exclude generated/vendor first, then explain to the user.
Q5: How can I avoid making too many changes at once? Fix in batches by failure category and file first, and rerun the original command and review the diff after each batch.
Q6: If it passes locally, can I say CI will pass? No. It is also necessary to align CI's versions, 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 it is necessary to check this language's registry, toolchain, and project configuration, read
references/tooling/toolchain.md。 - When a copyable task example is needed, read by scenario
examples/, and there is no need to load all of them at once.