weekly-brief
Skill0 starsChanged 4 months agoMITView on GitHub
Synthesize the user's newsletter and feed stack into one weekly signal briefing covering what structurally changed, why it matters, and what to do about it. Use when the user asks for their weekly briefing, a digest of their newsletters, or "what did I miss this week".
6 other projects use a version of this.
Adopted by
Most recently taken up by
- rgourley/quant-garagetheir own version, first seen Nov 1, 2026
- Lwhieldon/claude-project-mgmt-playbooktheir own version, first seen Oct 13, 2026
- ShenSeanChen/waku-agenttheir own version, first seen Oct 8, 2026
- rittmananalytics/wire-plugintheir own version, first seen Oct 5, 2026
- scape-velocity/escape-velocitytheir own version, first seen Oct 5, 2026
- 333Ben/hermes-client-kittheir own version, first seen Aug 31, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- ShenSeanChen/waku-agent★ 2ksame name
- rittmananalytics/wire-plugin★ 14same name
- rgourley/quant-garage★ 7same name
- Lwhieldon/claude-project-mgmt-playbook★ 4same name
- 333Ben/hermes-client-kit★ 0same name
- scape-velocity/escape-velocity★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- book-to-skillSkill
- buyback-time-auditSkill
- marketplace-monitorSkill
- market-pulseSkill
- meeting-intelSkill
- relationship-radarSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
If Gmail access is available in the session, pull the last 7 days of newsletter mail (labels or senders the user names.
- Distinctive: line 22
If the user's goals or current projects are known from context, load them.
- Distinctive: line 27
Read everything before writing anything.
- Distinctive: line 65
No completeness. A briefing that mentions everything ranks nothing.
- Distinctive: line 66
No hedging stacked on hedging.
- Distinctive: line 67
Never include a story you cannot connect to the reader.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Weekly Brief
One briefing that replaces an hour of newsletter triage. Signal, not summary.
Distilled from a Gmail pipeline that has produced a Monday-morning intelligence briefing from a curated newsletter stack for months. The editorial standard comes from that system: a briefing earns its length by changing what the reader does next.
Inputs
- If Gmail access is available in the session, pull the last 7 days of newsletter mail (labels or senders the user names; ask once and remember for next time).
- Otherwise accept pasted content, URLs, or a folder of saved articles.
- If the user's goals or current projects are known from context, load them; the "why it matters to you" sections depend on it.
Workflow
- Read everything before writing anything. Deduplicate: five newsletters covering the same launch is one story.
- Rank stories by structural weight, not volume of coverage. The test: is a constraint shifting (cost, capability, distribution, regulation), or is this commentary on things already known?
- Pick 2-4 structural shifts maximum. Kill everything else or demote it to one-line mentions.
- For each shift write three parts: what changed (facts, with links), why it matters broadly (the constraint that moved), and why it matters to this user specifically (their projects, their market, their next decision). The third part is the whole point; if you cannot write it, the story does not belong in the briefing.
- Close with a build-or-act section: at most 3 concrete opportunities or decisions implied by this week, each with a first step.
Output format
# Weekly Brief - week ending <date>
## This week's signal
<the one-paragraph frame for the week>
## Structural shifts
### 1. <shift>
**What changed:** ...
**Why it matters:** ...
**Why it matters to you:** ...
## Worth one line
- <story> - <link>
## Act on it
1. <opportunity or decision> - first step: <step>Anti-patterns
- No completeness. A briefing that mentions everything ranks nothing.
- No hedging stacked on hedging; pick the read and state it.
- Never include a story you cannot connect to the reader. That is what the source newsletter was for.
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.