weekly-learnings
Skill0 starsChanged 3 months agoMITView on GitHub
Use when asked to prepare a weekly reflection or summary of learnings, or when /weekly-learnings is invoked. Do NOT use for accountability or pattern analysis — use /weekly-signals for that.
In this repository17 other files it gives its agents.
- backlinksSkill
- challengeSkill
- connectSkill
- expandSkill
- fix-nested-code-fencesSkill
- ghostSkill
- ingestSkill
- learnedSkill
- mapSkill
- meetingSkill
- obsidianSkill
- source-mineSkill
- traceSkill
- vault-indexSkill
- vault-lintSkill
- vault-retrieveSkill
- weekly-signalsSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Don't: use this for accountability analysis — that's /weekly-signals.
- Distinctive: line 15
Follow Qwen Protocol with:
- Distinctive: line 22
If Qwen is unavailable:
- Very specific: line 25
Read this week's daily notes by running obsidian read file='Daily Notes/[date]' via bash for each date in the week
- Very specific: line 26
Run obsidian search query='[key theme or topic from the week]' limit=15 via bash to surface active notes from this week
- Distinctive: line 27
Read the most active notes from this week
- Very specific: line 33
If [argument] was provided, scope the reflection to that topic
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Skill: /weekly-learnings [argument]
Synthesize the week's vault additions into a written reflection — key learnings, recurring themes, and open questions — as prose, not a bullet dump of activities.
Don't: use this for accountability analysis — that's /weekly-signals. Don't produce a bullet dump — synthesize into actual insights.
Steps
- Parse the argument/topic from Shane's request.
- Follow Qwen Protocol with:
task: "Synthesize this week's vault additions and highlights into a meaningful weekly reflection or email update. What were the key learnings, themes, and open questions?"skill: "weekly-learnings"
- Review Qwen's result, synthesize if needed, and present to Shane.
Fallback
If Qwen is unavailable:
- Determine the current week's date range (Monday–Sunday, YYYY-MM-DD)
- Read this week's daily notes by running
obsidian read file='Daily Notes/[date]'via bash for each date in the week - Run
obsidian search query='[key theme or topic from the week]' limit=15via bash to surface active notes from this week - Read the most active notes from this week
- Synthesize into a weekly reflection with these sections:
- Key learnings (3–5 concrete insights, not summaries of activity)
- Recurring themes (what kept coming up across different contexts?)
- Open questions (what is still unresolved or needs more thinking?)
- What surprised me (anything that shifted existing assumptions?)
- If
[argument]was provided, scope the reflection to that topic - Present the reflection to Shane — format as a written piece, not a bullet dump
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.

