weekly-summary
Skill0 starsChanged 7 months agoMITView on GitHub
Generate a weekly work summary by aggregating daily summaries. Calculates velocity trends, project health, and next-week priorities. Run /weekly-summary at the end of the week (typically Friday afternoon). Requires daily summaries to exist.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- quarto-dev/q2their own version, first seen Nov 9, 2026
- dmzoneill/skillstheir own version, first seen Oct 24, 2026
- iShawnWang/skillstheir own version, first seen Sep 14, 2026
- Duckz289/Pipeline-to-proposal-Plugin-STANDARDtheir own version, first seen Jul 27, 2026
- LJW0401/claude-code-skillstheir own version, first seen Apr 30, 2026
- kunwl123456/zeroclaw-skills-collectiontheir own version, first seen Feb 19, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- quarto-dev/q2★ 302same name
- kunwl123456/zeroclaw-skills-collection★ 27same name
- dmzoneill/skills★ 2same name
- Duckz289/Pipeline-to-proposal-Plugin-STANDARD★ 2same name
- iShawnWang/skills★ 1same name
- LJW0401/claude-code-skills★ 1same 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 repository3 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- daily-summarySkill
- summary-initSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
15 rules. 0 are common, 13 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
13
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 38
If missing, tell user to run /summary-init first.
- Distinctive: line 63
Commit count and line changes (from Code Activity or Metrics)
- Distinctive: line 77
Read each section of the daily file.
- Distinctive: line 108
Look for the previous week's summary:
- Distinctive: line 114
If it exists, read it and extract the same metrics for comparison.
- Distinctive: line 121
If no previous week exists, skip the comparison section.
- Distinctive: line 125
This is the most important step: Don't just concatenate daily items.
- Distinctive: line 130
Write a synthesized 2-3 line summary that captures the full week's progress
- Distinctive: line 131
Add an impact statement
- Distinctive: line 143
Blocked: No tasks completed, explicit blockers, dependency waiting
- Distinctive: line 152
Follow the template format to generate the weekly summary with all aggregated data.
- Very specific: line 170
Update state file with new weekStartDate (next Monday).
- Distinctive: line 181
Synthesize over repeat: Never just list daily items.
- Distinctive: line 182
Trends matter: Always compare to previous week when available.
- Distinctive: line 186
Keep scannable: Use consistent formatting, metrics at the top, details below.
“Common” is measured: kept by at least 6 in 10 of the 3 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 Summary Generator
Step 0: Initialize
Get current date/time:
TZ={timezone from config} date "+%Y-%m-%d %H:%M:%S %Z (%A)"Calculate the current ISO week number and week date range:
TZ={timezone} date "+%V" # ISO week number
TZ={timezone} date -v-Mon "+%Y-%m-%d" # Monday of this week (macOS)
TZ={timezone} date -v-Fri "+%Y-%m-%d" # Friday of this week (macOS)For Linux, use date -d "last monday" / date -d "next friday" equivalents.
Step 1: Load Configuration
Read ~/.config/work-summary/config.json.
If missing, tell user to run /summary-init first.
Resolve paths (same as daily-summary skill).
Step 2: Locate Daily Summaries
Find all daily summaries from this week in the configured daily output directory:
ls {daily_output_dir}/Match files from Monday through Friday (or today if running mid-week).
If no daily summaries exist, tell the user:
No daily summaries found for this week. Run
/daily-summaryfirst to generate them.
If only some days have summaries, note which days are missing and proceed with available data.
Step 3: Read and Parse Daily Summaries
For each daily summary file, read it and extract:
Metrics
- Tasks completed count (from Metrics or Completed Tasks section)
- Commit count and line changes (from Code Activity or Metrics)
- JIRA tickets mentioned (from JIRA section)
- Meeting count and total hours (from Meetings section)
- Focus time hours (from Meetings section)
- Slack message count (from Slack section)
Content
- Accomplishments by project
- Key decisions made
- Blockers (resolved and new)
- Action items
Parsing approach
Read each section of the daily file. Look for the section headers that match the template format:
## Executive Summaryor## Summary## Metrics## Code Activity## JIRA Ticket Updates## Meetingsor## Meetings & Time Allocation## Slack Activity## Completed Tasks## Active Blockersor## Blockers
Extract numbers from metrics lines (regex for digits following labels).
Step 4: Aggregate Metrics
Sum and average across all daily summaries:
total_tasks = sum of daily task counts
total_commits = sum of daily commit counts
total_lines_added = sum of daily additions
total_lines_removed = sum of daily removals
total_meeting_hours = sum of daily meeting hours
total_meeting_count = sum of daily meeting counts
total_focus_hours = sum of daily focus hours
working_days = number of daily summaries found
avg_tasks_per_day = total_tasks / working_days
avg_commits_per_day = total_commits / working_daysStep 5: Compare to Previous Week
Look for the previous week's summary:
previous_week_file = {weekly_output_dir}/{previous week filename}If it exists, read it and extract the same metrics for comparison.
Calculate week-over-week changes:
change_pct = ((this_week - last_week) / last_week) * 100If no previous week exists, skip the comparison section.
Step 6: Synthesize Accomplishments
This is the most important step. Don't just concatenate daily items.
For each project that appears across multiple days:
- Collect all accomplishments from each day
- Identify the narrative arc (started -> worked on -> completed)
- Write a synthesized 2-3 line summary that captures the full week's progress
- Add an impact statement
Example:
- Monday: "Created prompt template" + Tuesday: "Documented template" + Wednesday: "Launched to team"
- Synthesis: "Prompt template system created, documented, and launched. 80% reduction in setup time."
Step 7: Assess Project Health
For each project mentioned in daily summaries:
Strong: 2+ tasks completed this week, active commits, no open blockers, forward progress Needs Attention: Some progress but challenges noted, approaching deadline Blocked: No tasks completed, explicit blockers, dependency waiting
Step 8: Generate Output
Load the weekly template:
{kit_path}/templates/{config.output.weekly_template}.mdFollow the template format to generate the weekly summary with all aggregated data.
Step 9: Write File
Determine filename from config.output.weekly_file_naming:
| Pattern | Replacement |
YYYY | 4-digit year |
WW | ISO week number (zero-padded) |
[text] | Literal text |
Default: YYYY-[W]WW.md -> 2026-W10.md
Write to {weekly_output_dir}/{filename}.
Step 10: Update State
Update state file with new weekStartDate (next Monday).
Step 11: Report
Tell the user:
- Where the file was written
- Key highlights: top accomplishments, velocity trend, project health summary
- Any missing daily summaries
Quality Rules
- Synthesize over repeat: Never just list daily items. Always combine related work into narratives.
- Trends matter: Always compare to previous week when available.
- Focus on outcomes: Lead with impact, not process.
- Project-centric: Organize by project health and momentum.
- Forward-looking: End with next week's priorities.
- Keep scannable: Use consistent formatting, metrics at the top, details below.
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.

