work-summary-kit
CLAUDE.md0 starsChanged 7 months agoMITView on GitHub
Reusable daily and weekly work summary system for Claude Code.
In this repository3 other files it gives its agents.
- daily-summarySkill
- summary-initSkill
- weekly-summarySkill
The file
We split this CLAUDE.md into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 31
Create adapters/{source-name}.md following the structure of existing adapters
- Very specific: line 32
Add the source to config/config.schema.json
- Very specific: line 33
Add conditional loading in skills/daily-summary/SKILL.md
- Distinctive: line 34
Add a corresponding output section to templates
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md 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
work-summary-kit
Reusable daily and weekly work summary system for Claude Code.
Project Structure
skills/-- Claude Code skills (the main entry points)daily-summary/SKILL.md-- Generates daily work summariesweekly-summary/SKILL.md-- Aggregates dailies into weekly summariessummary-init/SKILL.md-- Interactive setup wizard
adapters/-- Data source collection instructions (one file per source)templates/-- Output format specificationsconfig/-- JSON Schema, example configsscheduling/-- Automation templates for launchd/cron
How It Works
- User runs
/summary-initto generate~/.config/work-summary/config.json - User runs
/daily-summary-- the skill reads config, loads relevant adapters, generates output - User runs
/weekly-summaryon Fridays -- aggregates the week's daily summaries
Architecture
- Skills are the entry points. They orchestrate the workflow.
- Adapters are loaded conditionally based on which data sources are enabled in config. Each adapter is a self-contained markdown file with collection instructions.
- Templates define output format. The skill reads the template and uses it as a format specification.
- Config lives at
~/.config/work-summary/config.json(never in this repo).
Adding a New Adapter
- Create
adapters/{source-name}.mdfollowing the structure of existing adapters - Add the source to
config/config.schema.json - Add conditional loading in
skills/daily-summary/SKILL.md - Add a corresponding output section to templates
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.

