p-daily-report
Skill15 starsChanged 9 days agoMITView on GitHub
Use when reviewing what you worked on, creating standups, writing status updates, tracking daily/weekly progress, or asking "what did I do today
In this repository31 other files it gives its agents.
- claude-permissions-auditSkill
- claude-skill-orchestration-auditSkill
- claude-skill-prereq-auditSkill
- claude-skill-spec-auditSkill
- dev-cli-consistency-auditSkill
- dev-code-qualitySkill
- dev-new-toolSkill
- dev-software-designSkill
- gh-dep-pr-triageSkill
- gh-issue-reportSkill
- gh-org-chartSkill
- gh-oss-go-bumpSkill
- gh-oss-release-prepSkill
- gh-oss-releaseSkill
- gh-review-triageSkill
- git-conventional-commitSkill
- gws-meeting-schedulerSkill
- p-activity-digestSkill
- p-blog-post-miningSkill
- p-blog-writerSkill
- p-clipboard-copySkill
- p-daily-reflectionSkill
- p-daily-standupSkill
- p-ego-searchSkill
- p-md-to-slidesSkill
- p-meeting-prepSkill
- p-news-briefingSkill
- project-namerSkill
- p-slack-triageSkill
- p-violentmonkey-userscript-syncSkill
- restaurant-searchSkill
The file
We split this skill into the rules it gives an agent
11 rules. About 0 are common, 8 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
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 31
If any values are missing or the user requests changes, use:
- Distinctive: line 69
Before gathering data, check tool availability concurrently (parallelize if possible):
- Distinctive: line 78
Use results to skip unavailable data sources in subsequent steps.
- Distinctive: line 84
If this file doesn't exist or is empty, skip this step and proceed to GitHub activity.
- Very specific: line 96
Read a generous buffer: offset=(lines - 3000) to cover ~2 weeks of activity
- Very specific: line 144
If gh is not installed or not authenticated, skip this step and note in the report.
- Very specific: line 150
If gws is not installed, skip this step and omit the Calendar section from the report.
- Distinctive: line 156
If the Slack MCP server is not connected, skip this step and omit the Slack section from the report.
- Distinctive: line 162
Deduplicate: Before formatting, deduplicate across sources — the same PR may appear in both GitHub API results and Slack messages.
- Distinctive: line 210
If a project has no PRs or reviews, it's summary-only.
- Distinctive: line 224
Summarize: After writing, tell the user the file path and give a brief overview of what was captured.
≈ “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
Daily Report Generator
<!-- skillctx:begin -->Setup
Locate this skill's directory (the folder containing this SKILL.md), then run the resolver script from there:
python <skill-dir>/scripts/skillctx-resolve.py resolve p-daily-reportThe resolver outputs each binding as key: value (one per line). Substitute each {binding_key} placeholder below with the resolved value.
If any values are missing or the user requests changes, use:
python <skill-dir>/scripts/skillctx-resolve.py set p-daily-report <key> <value><!-- skillctx:end -->Generate activity reports from Claude Code conversation history, GitHub activity, and Slack messages.
IMPORTANT output rule: The generated report file must never mention "Claude", "Claude Code", "sessions", "history.jsonl", or any implementation details about how the data was gathered. The report should read as a clean, source-agnostic activity log. This rule applies only to the written output — these skill instructions may freely reference Claude internals.
When to Use
- End of day/week summaries
- Standup prep
- Status updates for stakeholders
- Tracking accomplishments across projects
Options
--days Nor number: Last N days (default: today)--yesterday: Yesterday only--project NAME: Filter by project--summary: Add project summary table
Date Range Reference
Determine {date} and {next_date} from options. Get today's date with date +%Y-%m-%d.
| Option | {date} | {next_date} |
| default (today) | today | tomorrow |
--yesterday | yesterday | today |
--days N | N days ago | tomorrow |
Steps
Parallel Initialization
Before gathering data, check tool availability concurrently (parallelize if possible):
# Run all three concurrently
gh api /user --jq '.login' # confirms gh is authenticated; capture as gh_user
gws calendar +agenda --today # confirms gws is available (or note unavailable)
slack_read_user_profile # confirms Slack MCP is connected (or note unavailable)Use results to skip unavailable data sources in subsequent steps.
Aggregate Claude Activity
Location: {claude_history_path}
If this file doesn't exist or is empty, skip this step and proceed to GitHub activity.
Format: JSONL with fields:
timestamp: Unix milliseconds → convert to local dateproject: Full path → extract last segment as namedisplay: User's messagesessionId: Groups related work
Reading Entries
- Get line count:
wc -l {claude_history_path} - Read a generous buffer:
offset=(lines - 3000)to cover ~2 weeks of activity - Filter entries by timestamp — convert
timestamp(Unix ms) to local date, compare against target date range, discard entries outside the range
Extract GitHub Repos from Project Paths
Project paths using ghq convention contain the owner/repo:
/Users/*/ghq/github.com/{owner}/{repo} → {owner}/{repo}Extract with pattern: match github.com/ then take the next two path segments.
- Build a map of
owner/repo→ project display name - Non-GitHub project paths (e.g.,
~/notes/project-x) have no repo — keep them for the report as local projects, skip them for GitHub queries
Filter Noise
Remove:
- Slash commands (
/clear,/model, etc.) - Single responses: "yes", "no", "1", "2", "a", "b"
- Empty/duplicate entries
Summarize by Session
Group same-sessionId entries into meaningful summaries:
| Raw Messages | Summary |
| "fix lint", "yes", "run tests" | Working on linting and tests |
| "implement X", "yes", "continue" | Implementing X feature |
| "investigate bug", "this error..." | Debugging issues |
Categorize
Tag with: feat, fix, refactor, docs, test, ci, plan
Steps 2, 3, and 4 are independent data sources. Dispatch all three concurrently (parallelize if possible). Proceed to Output only after all three complete.
Get GitHub Activity (parallelize if possible)
→ See references/agent-gather-github-report.md
If gh is not installed or not authenticated, skip this step and note in the report.
Get Google Calendar (parallelize if possible)
→ See references/agent-gather-calendar-report.md
If gws is not installed, skip this step and omit the Calendar section from the report.
Get Slack Activity (parallelize if possible)
→ See references/agent-gather-slack-report.md
If the Slack MCP server is not connected, skip this step and omit the Slack section from the report.
SYNC: Proceed to Output only after all data gathering steps complete.
Deduplicate: Before formatting, deduplicate across sources — the same PR may appear in both GitHub API results and Slack messages. Use PR URLs as primary keys to merge overlapping records.
Output Format
---
date: YYYY-MM-DD
type: daily-report
---# Daily Activity Report YYYY-MM-DD
## Calendar
- 14:30 Design review
- 16:00 1:1 with manager
## owner/repo-name
Implemented user authentication and fixed pagination bug. Added logout button
and improved empty state handling.
- PR #12 Add status line styles [merged]
- Review #45 Cleanup implementation [APPROVED]
## notebook
Worked on meeting notes and snippets conversion.
## Slack
- **#eng**: Discussed deployment rollback strategy and shared post-mortem findings
- **#project-x**: Reviewed design mockups and confirmed timeline for v2 launch
## Other Repositories
- Review myorg/repo#5 bump time dep [APPROVED]
- Issue myorg/other-repo#10 Bug report [open]Per-project format:
- Summary (required): 1-3 sentences synthesized from all sources (Claude history, commit messages, PR descriptions). Written as prose, no tags or prefixes. Captures what you did, not how the data was gathered.
- PRs and reviews (optional): Listed below the summary only when they exist. No subheader — just the items. Format:
- PR #N title [state]or- Review owner/repo#N title [STATE]. - If a project has no PRs or reviews, it's summary-only.
Other rules:
- Non-GitHub projects from Claude history use their directory name as the section header (e.g., "notebook").
- Items from GitHub that don't match any known project go under "Other Repositories".
- Omit any section that has no activity.
- No
[tag]prefixes, no commit hashes, no "N commits pushed".
Output Path
- Create date directory:
mkdir -p {notebook_daily_dir}/YYYY-MM-DD/ - Write report file:
{notebook_daily_dir}/YYYY-MM-DD/report.md- For multi-day reports:
{notebook_daily_dir}/YYYY-MM-DD/report-N-days.md
- For multi-day reports:
- Summarize: After writing, tell the user the file path and give a brief overview of what was captured.
Summary Table (with --summary)
| Project | Days Active | Activities | PRs | Reviews | Top Focus |
| ------- | ----------- | ---------- | --- | ------- | --------- |
| my-proj | 5 | 45 | 3 | 2 | feat, fix |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.

