Install
$ agentstack add skill-aiweline-welineframework-ci ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Role
This skill owns environment compatibility and command safety for automated execution paths. It is especially relevant where Windows quoting, shell composition, PHP compatibility, or environment-sensitive command behavior can break CI or release automation.
When To Use
- Use for shell composition, Windows quoting, environment compatibility, command wrappers, and automation portability issues.
- Use for keywords such as PowerShell, quoting, command safety, CI shell, environment compatibility, deployment command safety, and PHP version compatibility.
- Use when a feature works locally in one shell but may fail in CI or on Windows-oriented execution paths.
Source Material
AI-ENTRY.mdCLAUDE.mddev/ai/skills/windows-command-quoting/SKILL.mddev/ai/skills/php84-performance/SKILL.mddev/ai/skills/create-framework-command/SKILL.md
Responsibilities
- Prevent shell quoting bugs and argument-shape drift across automation environments.
- Review command composition for Windows and PowerShell safety.
- Check PHP-compatibility risks that can break automation or release tasks.
- Keep automation entry points explicit, reproducible, and stable.
Workflow
- Identify the command or automation path that must be portable and safe.
- Read the exact shell composition and inspect where quoting or interpolation can break.
- Normalize argument construction to explicit safe patterns for the target environment.
- Review PHP-compatibility assumptions that affect command execution.
- Run the narrowest confirming command on the intended environment path.
- Document environment assumptions and any required invocation rules.
- Report unresolved portability risks if exact cross-environment validation is not available.
Weline Rules
- Prefer explicit framework commands over ad hoc generated shell wrappers when possible.
- Do not edit
generated/directly. - In WLS-sensitive code, do not use
sleep,die, orexit. - Keep validation commands repeatable and automation-safe.
- A deployment request authorizes delivery flow only. Do not modify application or business code to clear validation failures, unit-test failures, or release-gate warnings unless the user explicitly asks for a fix; record the failures and report them after deployment.
- If a framework command times out while running a self-healing or nested
phppath, do not treat the timeout alone as proof that the schema/setup change failed; verify the target registration or schema surface directly before concluding. - The configured SAAS deployment target may be operated through local OpenSSH using the deployment-workspace SSH config/key and Windows Generic Credential entry; keep commands bounded to the documented delivery flow. Online targets without explicit local SSH credentials must be operated through the user's Chrome browser in JumpServer / Luna Web terminal, BaoTa Web terminal, or other user-authorized web terminal; the Codex built-in browser remains forbidden for deployment.
- Browser control fallback for online deployment must use Chrome extension tab control: locate tabs with
browser.user.openTabs(), attach withbrowser.user.claimTab(tabInfo), and operate the claimed tab withtab.cua,tab.playwright, andtab.clipboard. UseclaimTab + cuafor terminal interactions instead of OS input automation.
Inputs Required
- The affected command, shell path, or automation entry point.
- Target environment details such as PowerShell, Windows, or PHP version.
- The failure symptom or portability risk.
- Expected safe invocation form.
Expected Output
- A safer command composition or environment-compatible execution path.
- Evidence from a focused command run or compatibility check.
- Notes about environment assumptions and remaining edge cases.
Validation
- Run the affected command through the relevant shell path after the fix.
- Confirm argument quoting and interpolation behave as intended.
- Confirm PHP-compatibility-sensitive code paths still execute cleanly.
- Confirm the result is suitable for repeated automation use.
- When a command's nested PHP invocation depends on PATH, verify whether the environment actually exposes
phpto child processes before treating a stucksetup:upgradeas application failure.
Constraints
- Do not rely on fragile nested quoting patterns without explicit validation.
- Do not assume Linux-style shell behavior applies to Windows automation.
- Do not ignore PHP null-safety or version-compatibility risks in command code.
- Do not deliver a command path that only works in one manually prepared shell session.
- Do not provide or execute direct
sshdeployment commands for arbitrary online servers. Directsshis allowed only for the configured SAAS target with the local key/config; keep all other server-side deployment commands inside the Chrome-operated JumpServer / Luna terminal. - Do not use Windows or OS-level focus/input automation for deployment, including
SetForegroundWindow, system mouse movement/clicks,mouse_event,SendKeys, forced foreground windows, or system clipboard paths that can take focus from the user. Recover stuck terminals by opening or claiming a dedicated Chrome tab through the extension.
Shared Collaboration Contract
This specialist skill must follow 通用工程师-开发规范与代码质量 as the shared engineering and collaboration standard.
Before and during work:
- Know the Weline AI agent roster defined in the shared skill and
dev/ai/agent/README.md. - Keep work inside this specialist's ownership boundary.
- When a problem, blocker, risk, validation failure, or cross-agent issue is found, notify
@Weline-技术主管. - Do not silently expand scope to fix another agent's area.
- Include collaboration status in the final report.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Aiweline
- Source: Aiweline/WelineFramework
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.