Copiez ce prompt dans l’assistant IA que vous utilisez.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/LumiroCode/copilot-instructions.Chargement du README du dépôt…
Affichage de 37 skills collectés sur 37.
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…
Langue du texte source : anglais
Implement a single user-indicated phase from a whole plan.
Langue du texte source : anglais
Research, align business decisions with the user, and produce a locked phased implementation plan.
Langue du texte source : anglais
Review code changes, suggest improvements, and ensure code quality.
Langue du texte source : anglais
Orchestrates bugfixing with help of specialised subagents.
Langue du texte source : anglais
Orchestrates complex features development.
Langue du texte source : anglais
Codex-native counterpart of `/home/projekty/copilot-instructions/prompts/Solve_next_todo_item.prompt.md`.
Langue du texte source : anglais
Testing specialist for raw unit-failure capture and Playwright manual browser validation with actionable QA insights.
Langue du texte source : anglais
Implementation directive with consolidation of most important rules.
Langue du texte source : anglais
Researches and outlines multi-step plans - adjusted by me
Langue du texte source : anglais
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.
Langue du texte source : anglais
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…
Langue du texte source : anglais
Challenge assumptions and encourage critical thinking to ensure the best possible solution and outcomes.
Langue du texte source : anglais
Expert at debugging web applications, analyzing errors, and identifying root causes
Langue du texte source : anglais
Perform janitorial tasks on any codebase including cleanup, simplification, and tech debt remediation.
Langue du texte source : anglais
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…
Langue du texte source : anglais
Orchestrates post-coding finalization as an assessment-only pipeline: deep review, sanity checks, testing, and verification with triage-ready findings.
Langue du texte source : anglais
Selecting resolution for a problem base on RCA
Langue du texte source : anglais
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.
Langue du texte source : anglais
Specializes in reproducing production issues from user reports, log analysis, and performance metrics. Produces structured triage reports.
Langue du texte source : anglais
RCA analyzis of a problem
Langue du texte source : anglais
Verify implementation and tests against acceptance criteria using objective evidence and a strict pass/fail report.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Perform a sanity check (Why-WhatFor analysis) on your work before finalizing an approach or code change.
Langue du texte source : anglais
Perform a sanity check (Why-WhatFor analysis) on a decision before proceeding with it.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Audit a conversation for undocumented decisions that meet logging criteria (durable, cross-cutting, non-obvious, normative).
Langue du texte source : anglais
Run the post-coding finalization pipeline: deep review, sanity checks/tests, verification, and triage-ready findings (no fixes).
Langue du texte source : anglais
Validate input sanitization, auth/authz enforcement, secrets exposure, and OWASP Top 10 patterns in changed code.
Langue du texte source : anglais
Analyze test files for meaningful assertions that process actual data; verify changed code is exercised by tests.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Audit a conversation for undocumented decisions that meet logging criteria (durable, cross-cutting, non-obvious, normative).
Langue du texte source : anglais
Validate input sanitization, auth/authz enforcement, secrets exposure, and OWASP Top 10 patterns in changed code.
Langue du texte source : anglais
Analyze test files for meaningful assertions that process actual data; verify changed code is exercised by tests.
Langue du texte source : anglais
Fichier source du README : README.md
Lire le README source