Automated summary
Checks implementation progress, detects discrepancies against Plans.md, updates task markers to match reality, and suggests the next prioritized action.
Strengths
- Cross-references real repository state (git status, commits, Agent Trace) with cc:TODO/cc:WIP/cc:done markers in Plans.md
- Proposes Plans.md updates with a confirmation step and a stated reason for each change
- Flags anomalies such as multiple in-progress tasks or unprocessed pm:requested items
- Produces a quantified progress summary plus a concrete next-step recommendation
Limitations
- Relies on the presence and format of Plans.md and the .claude/state/agent-trace.jsonl trace file
- Assumes a specific marker convention (cc:TODO, cc:WIP, cc:done, pm:requested) tied to one workflow
- Explicitly not intended for casual progress chit-chat
Use it when you need an accurate status check and want Plans.md reconciled with the actual state of the code before picking the next task.
Don't load it for informal 'how's it going' chat that isn't about syncing or evaluating the plan.
Security analysis
CautionThe skill uses Bash, Write, and Edit, but all shell commands shown are local, read-only inspections (cat, git status/diff/log, jq on a trace log) with no network calls, no secret handling, and no destructive operations. File modification is limited to Plans.md and gated behind an explicit yes/no confirmation. Powerful tools used for a legitimate workflow, hence caution rather than safe or risky.
- •Invokes Bash for local git/file inspection and jq pipelines (read-only, but shell access)
- •Writes/edits Plans.md markers automatically after a confirmation prompt
- •Reads agent trace state file (.claude/state/agent-trace.jsonl) which may contain local project metadata
Examples
/sync-status/sync-status --verboseCheck where I'm at and sync Plans.md with what's actually been done, then tell me what to do next.name: sync-status description: "Checks progress, updates Plans.md to match reality, and suggests next action. Use when user mentions '/sync-status', progress check, where am I at, or sync Plans.md. Do NOT load for: casual 'how is it going' chat, informal progress questions." allowed-tools: ["Read", "Write", "Edit", "Bash", "Grep", "Glob"] argument-hint: "[--verbose]"
Sync Status Skill
Checks current implementation status, detects differences with Plans.md, and suggests next action.
Quick Reference
- "How far have we progressed?" → this skill
- "What should I do next?" → organize and suggest
- "Check if Plans.md matches actual progress" → detect and update
Deliverables
- Progress check: Consistency between implementation and Plans.md
- Difference update: Update Plans.md markers to match reality
- Next action suggestion: What to do next with priority
Execution Flow
Step 1: Gather Current Status (Parallel)
# Plans.md state
cat Plans.md
# Git change status
git status
git diff --stat HEAD~3
# Recent commit history
git log --oneline -10
# Agent Trace (直近の編集ファイル)
tail -20 .claude/state/agent-trace.jsonl 2>/dev/null | jq -r '.files[].path' | sort -u
Step 1.5: Agent Trace Analysis
Agent Trace から直近の編集履歴を取得し、Plans.md のタスクと照合:
# 直近の編集ファイル一覧
RECENT_FILES=$(tail -20 .claude/state/agent-trace.jsonl 2>/dev/null | jq -r '.files[].path' | sort -u)
# プロジェクト情報
PROJECT=$(tail -1 .claude/state/agent-trace.jsonl 2>/dev/null | jq -r '.metadata.project')
PROJECT_TYPE=$(tail -1 .claude/state/agent-trace.jsonl 2>/dev/null | jq -r '.metadata.projectType')
照合ポイント: | チェック項目 | 検出方法 | |------------|---------| | Plans.md にないファイル編集 | Agent Trace vs タスク記述 | | タスク記述と異なるファイル | 想定ファイル vs 実際の編集 | | 長時間編集がないタスク | Agent Trace 時系列 vs WIP期間 |
Step 2: Detect Differences
| Check Item | Detection Method |
|------------|------------------|
| Done but still cc:WIP | Commit history vs marker |
| Started but still cc:TODO | Changed files vs marker |
| cc:done but not committed | git status vs marker |
Step 3: Update Plans.md
If differences detected, suggest and execute:
📝 Plans.md update needed
| Task | Current | After | Reason |
|------|---------|-------|--------|
| XX | cc:WIP | cc:done | Committed |
Update? (yes / no)
Step 4: Output Progress Summary
## 📊 Progress Summary
**Project**: {{project_name}} ({{project_type}})
| Status | Count |
|--------|-------|
| 🔴 Not started (cc:TODO) | {{count}} |
| 🟡 In progress (cc:WIP) | {{count}} |
| 🟢 Done (cc:done) | {{count}} |
**Progress rate**: {{percent}}%
### 📄 直近の編集ファイル (Agent Trace)
- {{file1}}
- {{file2}}
- ...
Step 5: Suggest Next Action
🎯 What to do next
**Priority 1**: {{task}}
- Reason: {{requested / unblock}}
**Recommended**: /work, /harness-review
Anomaly Detection
| Situation | Warning |
|-----------|---------|
| Multiple cc:WIP | ⚠️ Multiple tasks in progress |
| pm:requested not processed | ⚠️ Process PM's request first |
| Large gap | ⚠️ Task management not keeping up |
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/sync-status-check-mmio717z/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/sync-status-check-mmio717z' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/sync-status-check-mmio717z/download' --output '.skill-downloads/sync-status-check-mmio717z/SKILL.md.part' && mv '.skill-downloads/sync-status-check-mmio717z/SKILL.md.part' '.skill-downloads/sync-status-check-mmio717z/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Original excerpt: Quick Reference
- "How far have we progressed?" → this skill
- "What should I do next?" → organize and suggest
- "Check if Plans.md matches actual progress" → detect and update
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/sync-status-check-mmio717z/SKILL.md' && test -s '.skill-downloads/sync-status-check-mmio717z/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/sync-status' && cp -R '.skill-downloads/sync-status-check-mmio717z' '.claude/skills/sync-status'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/sync-status-check-mmio717z'openskills read 'sync-status-check-mmio717z'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/sync-status-check-mmio717z/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
PDF Reader
Productivity
Read and extract text from PDF files, including documents, reports, contracts, and spreadsheets. Works with local files, URLs, and WhatsApp attachments. Use whenever PDF content is needed, even if not explicitly requested.
Discord Messaging Workflows
Productivity
Use the message tool to send, edit, and moderate Discord messages with interactive components.
Interactive Verdict Preview
Productivity
Generate an interactive HTML preview of keep/drop verdicts for maintainer review, then process the pasted feedback JSON.