mcpbeat

Weekly Report

azure/weekly-report

>- **WORKFLOW SKILL** — Generate weekly executive reports for the azd team. Pulls PR/issue/release data from GitHub, reads changelogs, combines with team notes, and produces a polished markdown report. summary, generate report, report time. (use changelog-generation), general docs, PRs.

1k tokens
context cost
the whole folder, loaded on every use
3
files
instructions only
0
copies elsewhere
how many repositories repackaged it
555
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/Azure/azure-dev --skill weekly-report

What comes with it

2 491 bytes besides the instruction
references/SECTION-RULES.md
references/TONE-RULES.md

The instruction itself

14 sections, as written by the author

Weekly Executive Report Generator

Generates weekly executive reports for the Azure Developer CLI (azd) team leadership.

Prerequisites

| Tool | Purpose |

|------|---------|

| gh | GitHub CLI — authenticated with repo access |

| jq | JSON filtering for release queries |

| git | Repository data |

Report Format (strict order)

📝 TLDR
📊 Metrics
⚠️ Risks + Blockers
🎯 Changelog
📋 This Week
🔜 Next Week
🚩 Learnings
🔥 Demos/Links

Execution Flow

Step 1: Confirm date range

Cadence is Thursday to Thursday. Confirm with the user if unclear.

Step 2: Pull repo data

Replace START and END below with the dates from Step 1.

cd <repo-root>  # the azure-dev repository root
git checkout main && git pull --rebase

PRs merged:

gh pr list --repo Azure/azure-dev --state merged --search "merged:START..END" --limit 200 --json number,title,mergedAt

Issues closed:

gh issue list --repo Azure/azure-dev --state closed --search "closed:START..END" --limit 200 --json number,title,closedAt

Releases:

gh api repos/Azure/azure-dev/releases --paginate | jq '[.[] | select(.published_at >= "START" and .published_at <= "END") | {name, tag_name, published_at}]'

Step 3: Read changelogs

Changelog data is maintained by the changelog-generation skill.

  • Core: cli/azd/CHANGELOG.md
  • Agents: cli/azd/extensions/azure.ai.agents/CHANGELOG.md
  • Finetuning: cli/azd/extensions/azure.ai.models/CHANGELOG.md

Step 4: Wait for team notes

Do NOT assemble the report until the user provides team notes from emails, Teams, meetings, etc.

Only product and engineering content.

Step 5: Assemble report

Combine repo data with team notes. Follow all rules below.

Step 6: Iterate

Expect 5–15 rounds of edits. Apply changes surgically. After removals, check for related content elsewhere (risks → next week → learnings → TLDR) and offer to clean up.

Output

Save reports to the Copilot CLI session workspace (~/.copilot/session-state/<session-id>/files/) as weekly-report-{month}{startday}-{endday}.md.

Section Rules

{{ references/SECTION-RULES.md }}

Tone and Style

{{ references/TONE-RULES.md }}

Example Report

Use the latest completed report in the session files as a format reference.

How to use it

Copy the folder

Take azure/weekly-report from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.