php-full-stack-developer – OpenClaw Skill

---

name: php-full-stack-developer description: A senior, governance-backed PHP full-stack delivery OS for OpenClaw. Emphasizes pre-flight analysis, safe data changes, explicit contracts, and reproducible verification.

PHP Full-Stack Developer Skills (Senior)

Trigger Conditions

Use this skill when:

• The user requests engineering work: backend/frontend/DB/devops/CI, debugging, refactors, migrations, API work.
• The work could affect security, data integrity, API contracts, performance, or deployment.
• You need repeatable execution across sessions (memory + logs).
• There is uncertainty, contradictions, or multiple valid approaches.

Do not apply to unprompted agent-initiated work; log later if needed.

Prompting Principles (Senior Clarity)

• Start with Pre-Flight: define goal, acceptance criteria, risks, constraints, verification.
• Ask only the minimum questions that prevent expensive rework (auth/data/contracts/env).
• Prefer explicit contracts over “magic”: payload shape, errors, pagination, idempotency.
• Prefer reversible changes and staged rollout for risky work.
• Always produce “How to test” steps.

Two governance questions (required)

1. Should I make and log this into a project to store it in memory?
2. Should I execute now, or spin up a specialized agent for higher-quality work (more tokens)?

Stop-Work Rules (quick gates)

Stop and log a conflict if:

• Auth/authz rules are unclear for protected resources.
• DB change is destructive or constraints are unknown.
• API/UI contract change has unknown consumers.
• Runtime versions (PHP/framework/DB) are unknown for P1+ work.
• Rollback/rollout is missing for P1+ work.

Routing: see INFO_GOVERNANCE.md + LOG_CONFLICTS.md.

PHP Full-Stack Developer Skills (Markdown-Only)

This repository defines PHP Full-Stack Developer Skills: a Markdown-only, governance-backed execution OS for senior-quality delivery (Laravel/Symfony + JS/TS + SQL + Docker + CI/CD).

It references OpenClaw runtime workspace templates/logs; it does not ship those workspace files.

What this skill emphasizes

• Analyze the project before starting (pre-flight + discovery checklist).
• Risk-based rigor (P0–P3) with stop-work gates.
• Safe data changes (expand/contract when needed).
• Explicit API/UI contracts (payloads, errors, pagination, idempotency).
• Reproducible verification (commands + smoke path + observability).

Repository map

• SKILL.md — Entry point: triggers, prompting principles, stop-work rules.
• INFO_GOVERNANCE.md — Severity, gates, decision requirements, conflict routing.
• INFO_RUNTIME.md — OpenClaw runtime integration + pre-flight workflow.
• INFO_DISCOVERY.md — One-page “analyze before starting” checklist.
• INFO_TEMPLATES.md — Copy/paste templates (task spec, pre-flight, ADR, PR, incident).
• INFO_RESEARCH.md — Verification model (docs-first, reproduce, measure).
• LOG_CACHES.md — Log index (load only what’s needed).
• LOG_PROJECTS.md — Project registry and active focus.
• LOG_CHARTERS.md — Charters.
• LOG_CONFLICTS.md — Conflicts and gates.
• LOG_DECISIONS.md — Decision history (ADR-lite).
• LOG_ACTIVITY.md — Activity log.