sync
- Repo stars 330
- License MIT
- Author updated Live
- Author repo claude-skill-registry
- Domain
- Other
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 94 / 100 · audit passed
- Author / version / license
- @majiayu000 · MIT
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Network behavior
- External requests
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: sync
description: Start-of-session sync - pull latest, check handoffs, reviews, and blocked items Run at the start…
category: other
runtime: no special runtime
---
# sync output preview
## PART A: Task fit
- Use case: Start-of-session sync - pull latest, check handoffs, reviews, and blocked items Run at the start of each session to sync with other agents and see what needs attention. git fetch origin main git checkout main git pull origin main Look for handoff notes addressed to this agent: makes outbound network calls. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Steps / 1. Pull Latest / 2. Check for Handoffs” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Start-of-session sync - pull latest, check handoffs, reviews, and blocked items Run at the start of each session to sync with other agents and see what needs attention. git fetch origin main git checkout main git pull origin main Look for handoff notes addressed to this agent: makes outbound network calls. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “Steps / 1. Pull Latest / 2. Check for Handoffs” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files; may access external network resources; usually needs no extra API key.
## Running Rules
- read files, write/modify files; may access external network resources; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. Choose the trigger
The source mentions slash commands such as `/review`, `/sync`; use them first when your agent supports command triggers.
Provide inputs and boundaries
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files.
Validate with a small run
Start with a small task and check whether the result follows “Steps / 1. Pull Latest / 2. Check for Handoffs”. Inspect diffs, logs, previews, or tests before expanding scope.
Review before delivery
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: sync
description: Start-of-session sync - pull latest, check handoffs, reviews, and blocked items Run at the start…
category: other
source: majiayu000/claude-skill-registry
---
# sync
## When to use
- Start-of-session sync - pull latest, check handoffs, reviews, and blocked items Run at the start of each session to sy…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Steps / 1. Pull Latest / 2. Check for Handoffs” and keep inference separate from source facts.
- read files, write/modify files; may access external network resources; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. Evidence boundary and execution chain
The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "sync" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Steps / 1. Pull Latest / 2. Check for Handoffs
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files | may access external network resources
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}Agent Sync
Run at the start of each session to sync with other agents and see what needs attention.
Steps
1. Pull Latest
git fetch origin main
git checkout main
git pull origin main2. Check for Handoffs
Look for handoff notes addressed to this agent:
# List recent handoffs
ls -la kanban-work/handoffs/ 2>/dev/null | tail -10
# Check for unread handoffs (files modified in last 24h)
find kanban-work/handoffs/ -name "*.md" -mtime -1 2>/dev/nullIf handoffs exist, read them and summarize what needs attention.
3. Check Items in Review
yurtle-kanban list --status reviewCan this agent help review any of these? Show the list and offer to run /review EXP-XXX.
4. Check Blocked Items
yurtle-kanban list --status blockedCan this agent unblock any of these? Show blockers and reasons.
5. Check My In-Progress Items
yurtle-kanban list --status in_progressAre any of these assigned to this agent or stale? Recommend:
- Resume work on existing item, OR
- Pick up new work if nothing in progress
6. Show Ready Work
# Show ready items filtered by agent capability if tags exist
yurtle-kanban list --status ready --limit 57. Generate Sync Summary
Output a summary like:
## Agent Sync Complete
**Handoffs:** X pending (read them with `cat kanban-work/handoffs/...`)
**Reviews:** X items need review
**Blocked:** X items blocked
**In Progress:** X items (Y assigned to me)
**Ready:** X items available
### Recommended Next Action
[Pick the most important thing to do]Tips
- Run
/syncat the start of every session - If there are handoffs, read them first
- If there are reviews from other agents, consider helping
- Check blocked items - you might be able to unblock someone
Decide Fit First
Design Intent
How To Use It
Boundaries And Review