agentleFS
philpalmieriphilpalmieri/engineering-manager-skills/skills/management/weekly-snippet/SKILL.md

weekly-snippet

Skill1 starsChanged 6 months agoMITView on GitHub

Draft a weekly status update (snippet) for your manager. Gathers GitHub activity for all team members, cross-references vault context and last week's snippet, and produces a structured update with wins, upcoming work, and strategic commentary. Use when asked to prep or write a weekly snippet.

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 8 are distinctive, and 4 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.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the most recent snippet file to understand:

    line 30
  2. Very specific:

    Search the vault for unchecked tasks tagged #snippetIdea:

    line 39
  3. Distinctive:

    Cap detection: If any query returns exactly 50 or 100 results, the API likely capped.

    line 71
  4. Very specific:

    If the team config has a project_number, check the project board for recent sprint status updates.

    line 75
  5. Distinctive:

    Look for recent status updates on the Sprint Progress view.

    line 81
  6. Distinctive:

    Don't include items that shipped more than 1 week ago as wins

    line 87
  7. Distinctive:

    Don't repeat old news: Only include activity from the current week.

    line 148
  8. Distinctive:

    Credit people: Use @mentions. Highlight individual contributions.

    line 149
  9. Distinctive:

    Be honest about risks: If something is slipping, say so.

    line 151
  10. Distinctive:

    Link everything: Every project reference should have an issue/PR link for context.

    line 158
  11. Very specific:

    Key project matching: If the team config has a snippet.key_projects array, use the keywords to match PRs/issues to known projects and group …

    line 160
  12. Very specific:

    Source links: When a section was informed by a #snippetIdea bullet or other tagged item, add a from [[Source/File]] line below it.

    line 161

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Weekly Snippet

Draft a weekly status update summarizing team wins, upcoming ships, incidents, and strategic observations. Combines GitHub activity data with vault context to produce a ready-to-edit snippet.

When to use

  • "Prep this week's snippet", "do my snippets", "weekly snippet", "write my update"

Prerequisites

  • Team roster (team.json) with member logins
  • GitHub CLI (gh) authenticated with org access
  • Previous snippets in the vault for style reference (location from setup config)
  • Obsidian vault with daily notes, project files, and people files

Process

Step 1: Calibrate style and continuity

  1. Read the most recent snippet file to understand:
    • Current writing style and voice
    • What was listed as "Upcoming Ships" last week (did any ship? → move to Wins)
    • Ongoing threads that need updates
    • Section structure and formatting patterns
  2. Optionally read 1-2 older snippets for additional calibration

Step 2: Scan for snippet ideas in the vault

Search the vault for unchecked tasks tagged #snippetIdea:

grep -rn '\- \[ \].*#snippetIdea' <vault_path>/Dailies/ <vault_path>/Projects/ <vault_path>/People/

For each match, read surrounding context. Incorporate into the draft where relevant:

  • Strategic/architecture concerns → Top of Mind
  • Shipped or in-progress work → Wins or Upcoming Ships
  • Track which ideas you used and which you skipped (report after drafting)

Step 3: Fetch team activity from GitHub

For each team member in the roster, run these searches. Date range: prior Monday through today.

Authored PRs:

gh search prs --author={login} --owner={org} --created={start}..{end} --json number,title,repository,state,createdAt,closedAt --limit 50

Merged PRs (main repo if applicable):

gh search prs --author={login} --owner={org} --merged={start}..{end} --json number,title,repository,mergedAt --limit 50

Closed issues (excluding noise):

gh search issues --repo={team_repo} --state=closed --closed={start}..{end} --json number,title,labels,assignees --limit 50

Filter out noise using the snippet.noise_labels list from the team config. Use snippet.incident_labels to identify incident issues separately.

Cap detection: If any query returns exactly 50 or 100 results, the API likely capped. Split the date range in half and re-query to get complete data.

Step 3b: Check project board for sprint context

If the team config has a project_number, check the project board for recent sprint status updates. This helps contextualize wins by sprint goals and flags planned upcoming work.

gh project view {project_number} --owner {org} --format json

Look for recent status updates on the Sprint Progress view. Use sprint goals to group wins and frame upcoming work.

Step 4: Cross-reference with last week

  • Items from last week's "Upcoming Ships" that now have merged PRs or closed issues → move to Wins
  • Items still in progress → keep in Upcoming Ships with updated status
  • Don't include items that shipped more than 1 week ago as wins

Step 5: Draft the snippet

Use this structure:

## Weekly Snippet - YYYY-MM-DD

### Top of Mind

**[Topic]**
- Strategic commentary, concerns, observations
- Link relevant issues/PRs

---

### Wins

**[Project Name] ([#issue](url))**
- What shipped, who did it, why it matters
- @mentions for credit

---

### Upcoming Ships

**[Project Name] ([#issue](url))**
- Current status, what's left, target timeline
- Any risks or blockers

---

### Incidents This Week

On-call: @{login}

- **[monitor-name]**: [#issue](url), [date], [status]. Brief description of what happened and resolution.

Step 6: Save and summarize

  1. Save to the configured snippets directory with tomorrow's date (or the next business day) as filename: YYYY-MM-DD.md
  2. Append a live Obsidian Tasks query block at the bottom to surface remaining #snippetIdea items:
```tasks
not done
description includes #snippetIdea
```
  1. Summarize what you included: which #snippetIdea items were incorporated (and where), which were skipped (and why)
  2. Flag anything uncertain (e.g., "not sure if this PR was this week or last")
  3. Suggest items the user might want to add manually (meetings, conversations, decisions that don't show up in GitHub)

Content guidelines

  • Wins should be specific. Name the person, the PR/issue, and what it does. Not just "worked on X."
  • Top of Mind is for strategic thinking. Architecture concerns, process observations, cross-team dynamics, things that need attention but aren't tasks.
  • Upcoming Ships should have status. On track? At risk? Blocked? What's left?
  • Don't repeat old news. Only include activity from the current week.
  • Credit people. Use @mentions. Highlight individual contributions.
  • Group related items. Multiple PRs for the same project go under one heading.
  • Be honest about risks. If something is slipping, say so. If a dependency is blocking, name it.

Rules

  • Voice: Match the user's established snippet style. Read previous snippets before writing.
  • No filler. Skip projects with no meaningful activity this week.
  • Incidents only if they happened. Omit the section entirely if no incidents fired.
  • Link everything. Every project reference should have an issue/PR link for context.
  • Date range matters. The snippet covers Monday through today. Don't pull in work from before Monday unless it's a carryover from last week's Upcoming.
  • Key project matching: If the team config has a snippet.key_projects array, use the keywords to match PRs/issues to known projects and group them under those headings. This ensures recurring workstreams are tracked consistently.
  • Source links: When a section was informed by a #snippetIdea bullet or other tagged item, add a from [[Source/File]] line below it. If multiple sources inform one section, combine: from [[Dailies/2026-05-08]], [[People/Jane]], [[Projects/API Redesign]]. These links let the user jump to context and signal which items to finalize after review.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.