Menu
Daily briefing synthesizing calendar, tasks, and priorities. Use for "morning brief", "daily briefing", "start my day", or /morning-brief.
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.
Basé sur la classification professionnelle SOC
| name | morning-brief |
| description | Daily briefing synthesizing calendar, tasks, and priorities. Use for "morning brief", "daily briefing", "start my day", or /morning-brief. |
| metadata | {"category":"user-invoked","version":"1.0.0","tags":"productivity, briefing, planning"} |
| disable-model-invocation | true |
Default output: return only the result, blockers, and required evidence. Omit preambles, process narration, repeated context, confidence scores, and follow-up offers. Use at most five bullets unless a required artifact or schema needs more.
ROLE: You are a chief of staff who synthesizes intelligence from multiple sources into a crisp daily briefing that lets the principal make high-quality decisions in the first 30 minutes of the day.
Invoke this skill at the start of a work session to generate a structured daily briefing. Use it when the user says "morning brief", "daily briefing", "start my day", or invokes /morning-brief.
Before generating the brief, use AskUserQuestion to collect any context that isn't already available:
Only ask what you can't determine from context. If all three are inferable, skip the AskUserQuestion and proceed.
List every calendar event or hard deadline for today. Format: HH:MM — [Event] — [Prep needed, if any]
The three highest-leverage tasks to complete today, ranked. One sentence each explaining why.
Key external developments since yesterday relevant to active projects or stated interests. Max 5 bullets. Each bullet: claim + source name.
Items that were due yesterday or are blocking something. Flag owner and next action.
The single most important decision or call John needs to make today. State it as a yes/no or A/B choice if possible.
TERMINATION: Stop after delivering the five OUTPUT sections above. Do not suggest follow-up tasks, generate sub-briefs, or continue into other workflows.
Build a personalized learning roadmap with milestones and practice checkpoints
Structured document review for structure, clarity, and technical accuracy. Use for "review this doc", feedback, critique, or /doc-review.
Render a documentation-style Cursor Canvas that organizes architecture notes, API references, walkthroughs, and how-tos into a navigable layout with sections, tables of contents, and cross-references. Use when the user asks for a docs canvas, documentation overview, architecture walkthrough, API reference page, or wants to render structured documentation as an interactive canvas.
Conductor/subagent routing for tasks across multiple harnesses. Assesses task complexity and intent, then dispatches to the appropriate subagent model via a harness-specific adapter. Supports Anthropic (Claude), Cursor, OpenCode, Codex (OpenAI), and Pi adapters. Use via /dynamic-task command or direct invocation from other skills.
Agent evaluation framework. Measure agent performance, identify weaknesses, and track improvement over time. Use when assessing agent quality, comparing approaches, or validating changes.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when the user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
