Add roundup plugin: self-configuring status briefing generator

[dvelton]

What this adds

A new plugin called roundup with two skills that automate the most tedious part of management communication: gathering scattered information and packaging it into status updates.

Skills

• roundup-setup -- Interactive onboarding that learns the user's communication style from pasted examples, discovers available data sources, builds audience profiles, and writes a persistent config to ~/.config/roundup/config.md.

• roundup -- Generates draft status briefings on demand by pulling from configured sources and synthesizing in the user's learned style for any defined audience.

What makes it different

• Learns from examples, not templates. The user pastes in updates they've already written, and the setup flow analyzes their format, tone, structure, and content categories. The generated briefings sound like them.

• Platform-agnostic. Adapts to whatever MCP tools are available -- GitHub, M365/WorkIQ, Slack, Google Workspace, or any combination. The setup flow discovers the environment and configures accordingly.

• Multi-audience. Define different audience profiles (leadership, team, cross-functional partners) with different detail levels and formats. Same underlying data, different output for each.

• Human-readable config. Everything lives in a plain markdown file the user can open and hand-edit anytime.

Files added

File	Purpose
plugins/roundup/.github/plugin/plugin.json	Plugin manifest
plugins/roundup/README.md	Plugin documentation
skills/roundup-setup/SKILL.md	Setup/onboarding skill (234 lines)
skills/roundup-setup/references/config-template.md	Config file template
skills/roundup/SKILL.md	Briefing generator skill (183 lines)

Validation

• npm run plugin:validate -- passes
• npm run skill:validate -- passes
• npm run build -- README and marketplace.json updated

[Copilot]

Pull request overview

Adds a new roundup plugin to the Awesome Copilot ecosystem, providing an onboarding skill to generate a persistent config and a generator skill to produce audience-specific status briefings from configured sources.

Changes:

• Added two new skills: roundup-setup (interactive onboarding + config generation) and roundup (briefing generation from configured sources).
• Added a new roundup plugin manifest + README, and registered it in the plugin marketplace.
• Updated docs indexes to list the new skills and plugin.

Reviewed changes

Copilot reviewed 8 out of 8 changed files in this pull request and generated 4 comments.

Show a summary per file

File	Description
skills/roundup/SKILL.md	Defines the briefing-generation flow: read config, choose audience/window, gather from sources, synthesize, present/iterate.
skills/roundup-setup/SKILL.md	Defines the interactive onboarding flow to learn user style/audiences/sources and write ~/.config/roundup/config.md.
skills/roundup-setup/references/config-template.md	Provides the human-editable config template used by setup and read by generator.
plugins/roundup/README.md	Plugin documentation and usage examples for installing and running the two skills.
plugins/roundup/.github/plugin/plugin.json	Plugin manifest wiring the plugin to the two skills.
docs/README.skills.md	Registers roundup and roundup-setup in the skills catalog.
docs/README.plugins.md	Registers the roundup plugin in the plugins catalog.
.github/plugin/marketplace.json	Adds roundup to the generated plugin marketplace list.

Comments suppressed due to low confidence (2)

plugins/roundup/README.md:72

• Same table formatting issue here: rows start with ||, which produces an unintended empty column. Switch to a normal markdown table (| Source | What It Looks For |, etc.) so it renders correctly.

| Source | What It Looks For |
|--------|-------------------|
| GitHub | PRs, issues, commits, review activity across your configured repos |
| M365 / WorkIQ | Email threads, Teams messages, calendar events, shared docs |
| Slack | Channel messages, threads, announcements |
| Google Workspace | Gmail, Calendar, Drive activity |

skills/roundup-setup/SKILL.md:105

• This suggests collecting per-audience detail levels in one combined prompt, which conflicts with the earlier "one question at a time" / "never bundle multiple questions" ground rules. Either adjust the ground rules to allow this exception (e.g., when the user lists many audiences) or change the flow to ask for each audience’s detail level in separate ask_user turns.

1. Ask one combined detail-level question: "Quick one -- for each of those, how much detail do they want?" and list the audiences with choices like "Big picture only / Moderate detail / Full play-by-play" so they can assign a level to each in one answer.

2. Then ask one open-ended question: "Any of those audiences need a notably different format or focus? For example, some people's leadership wants three bullets max while their team prefers a longer narrative."

3. Only ask audience-specific follow-ups if their answer flags a real difference. Don't interrogate every audience separately.

[aaronpowell]

Small merge conflict and then it should be fine to merge in