Menu
Drives full multi-agent implementation from a blueprint — fans out parallel-safe tasks into waves, runs sequential tasks in order, resolves conflicts, then verifies. Use to execute an approved plan.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Systematic performance profiling and optimization with a mandatory baseline-first gate — measure before changing, re-measure after. Use when something is slow or you need to hit a latency/throughput target.
Blameless post-mortem / RCA — gathers facts, reconstructs a timeline, runs 5-Whys, defines action items, writes the post-mortem file and commits it. Use after an incident or outage.
Structured design dialogue with a visual companion — produces an approved spec and design artifacts before any implementation begins. Use at the start of a feature, before writing code.
Thorough, research-grounded code review of a change, PR, or MR — multi-lens (correctness, security, simplification, tests), severity-ranked with impact + fix, configurable depth, optional PR comments. Use when asked to review code, "do a code review", "review this PR/MR", "review my changes/diff/branch", or audit a changeset before merge.
Use when the user asks to research, investigate, analyze, find out, explore, examine, audit, or evaluate something — structured multi-source research with consulting, library-doc search, web search, and guided output delivery.
Multi-agent code review AND remediation — dispatches correctness, security, and simplification reviewers in parallel, consolidates findings, then fixes criticals/highs. Use when reviewing a diff or PR before shipping.
Basé sur la classification professionnelle SOC
| name | orchestrate |
| description | Drives full multi-agent implementation from a blueprint — fans out parallel-safe tasks into waves, runs sequential tasks in order, resolves conflicts, then verifies. Use to execute an approved plan. |
Read ../../references/codex-adapter.md, then read ../../../skills/orchestrate/SKILL.md and follow the source skill through that Codex adapter. Keep the source skill's gates, safety checks, and completion criteria.
Translate source agent teams and magician:* profiles into available generic Codex agents with self-contained prompts. Dispatch only independent blueprint nodes in parallel, collect results through normal agent completion/waiting, and run sequential nodes locally or in order. Do not invent agent-closing or native workflow APIs. Commits are optional side effects: stage only task-owned files and require the user's commit authorization.
