radar-publish-notion
Skill4 starsChanged 5 months agoMITView on GitHub
Publishes the run to Notion. Upserts one row per competitor in the Competitors database (matched by domain, with a Change field for week-over-week tracking) and creates a Briefings page holding the full briefing. Use after radar-merge-briefing. Requires the databases to exist (radar-provision-notion). Writing rows to an approved database is autonomous.
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-councilSkill
- radar-render-dashboardSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 16
Read radar.config.json. Need notion_prefix, competitors_ds, briefings_ds.
- Very specific: line 23
If found, <notion_prefix>notion-update-page with this run's values and set Change from the change set (New, Rising, Falling, Steady) and …
- Very specific: line 25
If not found, <notion_prefix>notion-create-pages under competitors_ds.
- Distinctive: line 26
Put each cited value in its column and the matching source URL in its paired Source column.
- Very specific: line 29
Create the Briefings page: <notion_prefix>notion-create-pages under briefings_ds with Title "Radar Briefing <date>", Run Date, Competitors …
≈ “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-notion
Automation level: AUTONOMOUS once the databases exist and were approved at setup. If they do not
exist, route to radar-provision-notion (CHECKPOINT). See
automation-levels.md.
Goal: reflect the run in Notion with honest change tracking, idempotently.
Steps
- Read
radar.config.json. Neednotion_prefix,competitors_ds,briefings_ds. If any is missing, stop and route toradar-provision-notion. - Load the combined dossier JSON and the change set produced by
radar-merge-briefing. - Upsert each competitor into the Competitors data source (matched by Domain):
- Find the existing row:
<notion_prefix>notion-searchor query the data source by Domain. - If found,
<notion_prefix>notion-update-pagewith this run's values and setChangefrom the change set (New, Rising, Falling, Steady) andLast Fetched. - If not found,
<notion_prefix>notion-create-pagesundercompetitors_ds. - Put each cited value in its column and the matching source URL in its paired Source column. Set Threat Level from the threat reading if present, else leave it unset rather than guessing.
- Find the existing row:
- Create the Briefings page:
<notion_prefix>notion-create-pagesunderbriefings_dswith Title "Radar Briefing<date>", Run Date, Competitors Tracked, Key Changes (the one-line digest), War Room unchecked. The page body is the briefing markdown fromradar-merge-briefing(Notion markdown). Store the returned page id inlast_run.briefing_notion_page_idsoradar-publish-councilcan append to it. - Obey no-em-dashes.md and no-fabrication.md in everything written: every web value keeps its source.
- Return the Notion page link to the caller.
Edge cases
- A competitor matches more than one existing row (dirty data): update the most recently edited and note the duplicate; do not create a third.
- Notion rate limit or transient error: retry the single failed write a couple of times, then report exactly which competitor failed so the user can re-run; the upsert keying makes a re-run safe.
- Page body too long for one create: create the page with the summary, then append the rest with an update.
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.

