amey-thakur/ai-skills/agent-executive-briefing

Claude Code and agent skill by amey-thakur/ai-skills

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Produce a short honest briefing across every desk on a fixed cadence, surfacing decisions needed rather than activity performed. Use when leading a business through agent desks and needing one readable view.

Install

npx vskill@latest install amey-thakur/ai-skills/agent-executive-briefing

SKILL.md

The same SKILL.md was published earlier as amey-thakur/ai-skills/agent-executive-briefing.

Agent executive briefing

The failure of any multi-desk arrangement is that each desk reports and nobody synthesises, leaving the operator with six documents and no picture. A briefing desk exists to produce the one page that names what changed, what is at risk, and what needs deciding.

Team

  • Collector: gathers each desk's current state file.
  • Synthesiser (exec-one-pager): writes the briefing across desks

rather than desk by desk.

  • Omission checker: hunts for the bad news the synthesis softened.

Shape: scheduled collection, synthesis, then an adversarial pass.

Method

  1. Fix the cadence and the shape. Same sections, same order, same

day, so a reader can find the part they care about without reading the whole thing.

  1. Lead with decisions needed, not activity done. The operator's

scarce resource is decisions, and activity summaries bury them.

  1. Synthesise across desks, do not concatenate them. Sales

optimism beside a finance runway warning is one story, and reporting them separately hides it (see agent-company-blueprint).

  1. State movement with a cause. Every material change gets a named

reason, and unknown is an acceptable and useful answer.

  1. Run the omission check as a separate pass. Its only job is

finding what a well-informed sceptic would want that the draft does not say (see agent-board-reporting).

  1. Keep it to one page with links. Depth lives in the desk files;

the briefing is the index and the judgement.

  1. Track decisions to their outcome. Last period's decisions appear

with what happened, which is what makes the briefing a loop rather than a broadcast.

Run it

In Claude Code, run the collector over each desk's output directory, then the synthesiser, then the omission checker as a distinct subagent whose findings append to the briefing before the human reads it. A scheduled run makes the cadence real. Port to LangGraph with a fan-in node and a verification node.

Signals it works

  • The briefing opens with decisions, and previous decisions carry

outcomes.

  • The omission check regularly restores something the draft softened.
  • Cross-desk contradictions surface rather than sitting in two files.

Boundaries

This synthesises what desks report; it cannot see what they do not capture, and a desk reporting badly produces a confident wrong briefing. Agents summarise and do not decide. Anything shared beyond the operator, particularly with investors or staff, is a human communication with its own obligations.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
10
Repository forks
2
7-day trend score
17

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/amey-thakur/ai-skills/agent-executive-briefing/badge)](https://verified-skill.com/skills/amey-thakur/ai-skills/agent-executive-briefing)

Something wrong with this skill or its page? Tell us.