agentleFS
mikezamayiasmikezamayias/agent-skills/skills/sync-context/SKILL.md

sync-context

Skill1 starsChanged 25 days agoBSD-3-ClauseView on GitHub

Morning briefing that aggregates 7 days of GitHub PRs and issues, Slack threads and PostHog errors into one dump. Use on /sync, "sync context", "morning briefing", "what did I miss" or "catch me up".

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 4

    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
  1. Distinctive:

    Run the following in parallel using subagents:

    line 15
  2. Very specific:

    If the slack skill is available:

    line 30
  3. Distinctive:

    If Slack is not configured: skip and note "Slack not configured — run /slack setup"

    line 35
  4. Distinctive:

    Ask: "Want me to pull up any of these items in detail?"

    line 95
  5. Very specific:

    Keep the dump fresh — always overwrite context-dump.md, don't append

    line 99
  6. Distinctive:

    If a service fails, note it in the output and continue with others

    line 100

“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.

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

Sync Context

The idea comes from tip 4 in Boris Cherny's Claude Code team tips: a command that syncs the last 7 days of work tools into one context dump.

You have been invoked to aggregate recent context from connected services and produce a morning briefing.

Process

Run the following in parallel using subagents:

Agent A — GitHub (via gh CLI)

gh pr list --author @me --state all --limit 10 --json number,title,state,updatedAt,url
gh pr list --reviewer @me --state open --limit 10 --json number,title,state,updatedAt,url
gh issue list --assignee @me --state open --limit 10 --json number,title,labels,updatedAt,url
gh search issues --involves @me --created=">$(date -v-7d +%Y-%m-%d)" --json number,title,repository,updatedAt --limit 20

Summarize: open PRs needing review, PRs I authored that have reviews, open issues assigned to me.

Agent B — Slack (via slack skill if available)

If the slack skill is available:

  • Pull recent threads from the last 2–3 days in relevant channels
  • Summarize: unread threads, mentions, action items

If Slack is not configured: skip and note "Slack not configured — run /slack setup"

Agent C — PostHog (via MCP)

mcp__posthog__query-run with HogQL:
  SELECT event, count() as cnt, max(timestamp) as last_seen
  FROM events
  WHERE timestamp > now() - INTERVAL 7 DAY
    AND event LIKE '%error%'
  GROUP BY event
  ORDER BY cnt DESC
  LIMIT 20

Summarize: top errors, spike patterns, anything new in the last 24h vs 7-day baseline.

Output

Write to ~/.claude/context-dump.md:

# Context Dump — [DATE TIME]

## GitHub

### PRs Needing My Attention

- [#N] title — state (updated X ago) [url]

### My Open Issues

- [#N] title — labels (updated X ago) [url]

## Slack

[summary or "not configured"]

## PostHog — Recent Errors

| Error | Count (7d) | Last Seen |
| ----- | ---------- | --------- |
| ...   | ...        | ...       |

---

## Suggested Focus

Based on the above, the highest-priority items appear to be:

1. [most urgent item]
2. [second most urgent]
3. [third most urgent]

_Generated by /sync-context_

After Writing

  1. Display the "Suggested Focus" section directly in chat
  2. Ask: "Want me to pull up any of these items in detail?"

Notes

  • Keep the dump fresh — always overwrite context-dump.md, don't append
  • If a service fails, note it in the output and continue with others
  • The goal is a 2-minute brief, not exhaustive data — summarize aggressively

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.