القائمة
Mandatory per-turn gate protocol. Runs at the start of EVERY turn. Four sequential gates must be evaluated before any work begins. Not optional. Not skippable. Not implicit.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | skill-sweep |
| description | Mandatory per-turn gate protocol. Runs at the start of EVERY turn. Four sequential gates must be evaluated before any work begins. Not optional. Not skippable. Not implicit. |
| user-invocable | false |
This protocol executes at the start of every turn. Four gates, in order. Each gate produces an explicit output before the next gate opens. Skipping a gate is a protocol violation.
Time: ~10 seconds. Tools: None (reasoning only).
Evaluate session coherence against these criteria:
Output: CLEAR or DRIFT DETECTED (if drift, present handoff prompt per session-guard skill before continuing).
Decision test — the task is mechanical ONLY when ALL three are true:
If ANY answer is NO: research fires. Execute the research skill protocol (WebSearch/WebFetch for Tier 1/2 sources, community discourse, prior art check). No exceptions.
If ALL three are YES: skip research.
Output: RESEARCH COMPLETE (with key findings) or MECHANICAL TASK (with three YES justifications).
Review the task against all installed skills. Select which apply:
Skills compose together. When one skill's output feeds another skill's phase, use it.
Output: List of active skills and rules for this turn.
Execute with all active skills composed. Before shipping ANY output:
rules/root-cause.md § One-Pass Holistic Review)Output: SHIPPED after holistic review is complete. Never before.
Deep research and knowledge synthesis. Activates for ANY task involving factual claims, technical decisions, implementation patterns, or domain knowledge. Deactivated ONLY when the mechanical task test passes (all three conditions true).
Evaluates code changes, output, and implementations for correctness, maintainability, security, and adherence to project standards. Activates when evaluating any code — whether user-requested or as part of the mandatory holistic review before shipping.
Systematic debugging for any type of issue. Activates when any error, failure, or unexpected behavior is encountered during any task. Root-cause investigation at the deepest architectural level. Never symptom-by-symptom patching.
Structured planning for complex tasks, features, or projects. Activates when a task requires decomposition, has multiple components, or when requirements need clarification before implementation.
Initialize new projects with proper structure, documentation, and Claude configuration. Activates when creating any new project, repository, module, or significant component.
Systematic code refactoring to improve design without changing behavior. Activates when code structure needs improvement without behavior change, including during the refactor phase of TDD cycles.