复制这段 Prompt，发给你正在使用的 AI 助手。
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/LumiroCode/copilot-instructions.正在加载仓库 README…
已展示 37 / 37 个已收集 Skill。
Expert-level software engineering agent. Deliver production-ready, maintainable code. Execute systematically, interactively, and specification-driven. Document comprehensively. Gather evidence, then involve the user for approvals and business-direction…
原文语言：英语
Implement a single user-indicated phase from a whole plan.
原文语言：英语
Research, align business decisions with the user, and produce a locked phased implementation plan.
原文语言：英语
Review code changes, suggest improvements, and ensure code quality.
原文语言：英语
Orchestrates bugfixing with help of specialised subagents.
原文语言：英语
Orchestrates complex features development.
原文语言：英语
Codex-native counterpart of `/home/projekty/copilot-instructions/prompts/Solve_next_todo_item.prompt.md`.
原文语言：英语
Testing specialist for raw unit-failure capture and Playwright manual browser validation with actionable QA insights.
原文语言：英语
Implementation directive with consolidation of most important rules.
原文语言：英语
Researches and outlines multi-step plans - adjusted by me
原文语言：英语
Strict architecture guard for design/code review against docs/architecture.md, with hard failures for missing architecture source, strong separation-of-concerns checks, blackbox modularity enforcement, and overcomplication detection.
原文语言：英语
Produces final-goal Definition of Done and acceptance criteria from current app state, user impact, and UX evidence. Works interactively with the user through iterative refinement. This agent must not investigate solutions, implementation steps, or technical…
原文语言：英语
Challenge assumptions and encourage critical thinking to ensure the best possible solution and outcomes.
原文语言：英语
Expert at debugging web applications, analyzing errors, and identifying root causes
原文语言：英语
Perform janitorial tasks on any codebase including cleanup, simplification, and tech debt remediation.
原文语言：英语
Use when you need a painstaking, robotic analysis of ONE question from every relevant angle and then a focused, evidence-based answer. Triggers: deep one-question analysis, exhaustive single-question assessment, angle-by-angle reasoning, highly thorough…
原文语言：英语
Orchestrates post-coding finalization as an assessment-only pipeline: deep review, sanity checks, testing, and verification with triage-ready findings.
原文语言：英语
Selecting resolution for a problem base on RCA
原文语言：英语
Business-value and product-alignment reviewer. Judges changes by user-flow soundness, business value, product vision fit, and whether the result strengthens or weakens the product direction.
原文语言：英语
Specializes in reproducing production issues from user reports, log analysis, and performance metrics. Produces structured triage reports.
原文语言：英语
RCA analyzis of a problem
原文语言：英语
Verify implementation and tests against acceptance criteria using objective evidence and a strict pass/fail report.
原文语言：英语
Generate a unique conversation ID for orchestrator agents to namespace `/memories/session/*` artifacts and prevent collisions across parallel chats/subagent delegations. Produces an 8-character hex hash from random bytes.
原文语言：英语
Perform a sanity check (Why-WhatFor analysis) on your work before finalizing an approach or code change.
原文语言：英语
Perform a sanity check (Why-WhatFor analysis) on a decision before proceeding with it.
原文语言：英语
Verify layering violations, dependency direction, event-driven directionality-first data flow (directional, coherent, bounded), MerlinX ACL boundary integrity, and separation of concerns against docs/architecture.md.
原文语言：英语
Verify layering violations, dependency direction, event-driven directionality-first data flow (directional, coherent, bounded), MerlinX ACL boundary integrity, and separation of concerns against docs/architecture.md.
原文语言：英语
Generate a unique conversation ID for orchestrator agents to namespace `.agents/session/*` artifacts and prevent collisions across parallel chats/subagent delegations. Produces an 8-character hex hash from random bytes.
原文语言：英语
Run core PHP tests via tests/run_all.sh and return only failed test files with exact error/throw/fail lines. Use when user asks for failure-only raw output with no narrative summary.
原文语言：英语
Audit a conversation for undocumented decisions that meet logging criteria (durable, cross-cutting, non-obvious, normative).
原文语言：英语
Run the post-coding finalization pipeline: deep review, sanity checks/tests, verification, and triage-ready findings (no fixes).
原文语言：英语
Validate input sanitization, auth/authz enforcement, secrets exposure, and OWASP Top 10 patterns in changed code.
原文语言：英语
Analyze test files for meaningful assertions that process actual data; verify changed code is exercised by tests.
原文语言：英语
Run core PHP tests via tests/run_all.sh and return only failed test files with exact error/throw/fail lines. Use when user asks for failure-only raw output with no narrative summary.
原文语言：英语
Audit a conversation for undocumented decisions that meet logging criteria (durable, cross-cutting, non-obvious, normative).
原文语言：英语
Validate input sanitization, auth/authz enforcement, secrets exposure, and OWASP Top 10 patterns in changed code.
原文语言：英语
Analyze test files for meaningful assertions that process actual data; verify changed code is exercised by tests.
原文语言：英语
仓库 README 来源：README.md
查看 README 源文件