radar-publish-council
Skill4 starsChanged 5 months agoMITView on GitHub
Publishes the Strategic War Room addendum from /radar-council to all three surfaces. Appends the addendum to the local briefing markdown, fills the war_room section of the dashboard data and re-renders the dashboard, and appends the addendum to the Notion briefing page while checking its War Room box. Use after the agent team has converged on recommended moves.
In this repository8 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- radar-diff-changesSkill
- radar-merge-briefingSkill
- radar-onboardSkill
- radar-plan-targetsSkill
- radar-provision-notionSkill
- radar-publish-notionSkill
- radar-render-dashboardSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 29
Read radar.config.json last_run for the briefing markdown path, the dashboard data path, and briefing_notion_page_id.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
radar-publish-council
Automation level: AUTONOMOUS (the CHECKPOINT was the decision to run the council at all).
Goal: get the war-room addendum onto the same three surfaces the gather run published to, so the strategy lives next to the evidence.
Inputs
The synthesized addendum from the council lead, structured as:
{
"summary": "One paragraph of the consensus, no em dashes.",
"moves": [
{ "title": "Concrete move", "rationale": "Why, with the supporting source or dossier field." }
],
"dissents": [ "Any move a teammate still disputes, and why." ]
}Steps
- Read
radar.config.jsonlast_runfor the briefing markdown path, the dashboard data path, andbriefing_notion_page_id. - Local markdown: append a "Strategic War Room" section to
outputs/briefings/<date>-briefing.mdbelow the addendum marker. Render the summary, each move as a titled bullet with its rationale and source, and a "Dissents and risks" list. Keep every claim cited and free of em or en dashes. - Dashboard: set
war_roomin the dashboard data JSON (summaryandmoves[]). If the council assigned threat levels (low / medium / high) from the threat ranking, also write each into the matchingcompetitors[].threat_levelso the dashboard threat chips and the threat filter light up. Then re-run the inject step fromradar-render-dashboardsooutputs/dashboard/<date>-dashboard.htmlandindex.htmlnow show the war room. - Notion: append the same addendum to the Briefings page using
<notion_prefix>notion-update-pageonbriefing_notion_page_id, and set the page'sWar Roomcheckbox to true. - Confirm all three surfaces updated and return their paths and the Notion link.
Edge cases
- The council ran but no briefing exists yet for this date: stop and tell the user to run
/radarfirst; the council analyzes an existing briefing. - Notion page id missing (gather did not publish to Notion): update the local markdown and dashboard, and tell the user Notion was skipped because the briefing was never published there.
- Re-running after an earlier council on the same briefing: replace the existing war-room section rather than appending a second one, so the surfaces do not accumulate duplicates.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

