nav-marker
について
nav-markerスキルは、子公司对外担保总额为13.4亿元,占最近一期经审计净资产的40.23%。 文字通顺,没有逻辑错误。但有一个小笔误:“公司及控股子公司子公司”应为“公司及控股子公司”。建议修改为: 【芳源股份:为全资子公司提供1亿元连带责任担保】芳源股份公告称,为满足全资子公司芳源循环生产经营需要,公司与中国银行签订《最高额保证合同》,为其提供最高1亿元连带责任保证担保,担保期限至2026年12月31日。本次担保为之前合同续期,不增加担保余额,担保后余额仍为13.4亿元。截至公告披露日,公司及控股子公司对外担保总额为13.4亿元,占最近一期经审计净资产的40.23%。
クイックインストール
Claude Code
推奨/plugin add https://github.com/alekspetrov/navigatorgit clone https://github.com/alekspetrov/navigator.git ~/.claude/skills/nav-markerこのコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします
ドキュメント
Navigator Marker Skill
Create context markers - save points that preserve conversation state so you can resume work later without re-explaining everything.
When to Invoke
Invoke this skill when the user:
- Says "save my progress", "create checkpoint", "mark this"
- Says "before I take a break", "save before lunch"
- Mentions "risky refactor ahead", "experiment with new approach"
- Says "end of day", "stopping for today"
- Before compacting context
DO NOT invoke if:
- User is asking about existing markers (use listing, not creation)
- Context is fresh (< 5 messages exchanged)
Execution Steps
Step 1: Check Navigator Structure
Verify .agent/.context-markers/ directory exists:
mkdir -p .agent/.context-markers
Step 2: Determine Marker Name
If user provided name:
- Use their name (sanitize: lowercase, hyphens for spaces)
- Example: "Before Big Refactor" → "before-big-refactor"
If no name provided:
- Auto-generate with timestamp:
marker-{YYYY-MM-DD}-{HHmm} - Example:
marker-2025-10-16-1430
Ask user for optional note:
Creating marker: [name]
Add a note? (optional - helps remember context later)
Example: "OAuth working, need to add tests"
Note:
Step 3: Generate Marker Content
Create marker document with this structure:
# Context Marker: [name]
**Created**: [YYYY-MM-DD HH:MM]
**Note**: [user's note or "No note provided"]
---
## Conversation Summary
[Summarize last 10-15 messages:
- What user was working on
- Key decisions made
- Problems solved
- Current progress state
]
## Documentation Loaded
[List docs that were Read during session:
- Navigator: ✅ .agent/DEVELOPMENT-README.md
- Task: TASK-XX-feature.md
- System: project-architecture.md
- SOPs: [if any]
]
## Files Modified
[List files with Write/Edit calls:
- src/auth/login.ts (implemented OAuth)
- src/routes/auth.ts (added endpoints)
- tests/auth.test.ts (created tests)
]
## Current Focus
[What user is working on right now:
- Feature: Authentication with OAuth
- Phase: Integration complete, testing pending
- Blockers: [if any]
]
## Technical Decisions
[Key architectural choices:
- Using passport.js over next-auth (better control)
- JWT tokens in httpOnly cookies (XSS protection)
- Redis for session storage (scalability)
]
## Next Steps
[What to do after restore:
1. Finish writing tests for OAuth flow
2. Add error handling for failed logins
3. Document setup in README
]
## Restore Instructions
To restore this marker:
\```bash
Read .agent/.context-markers/[filename]
\```
Or use: `/nav:markers` and select this marker
Step 4: Save Marker File
Write marker to file:
Write(
file_path: ".agent/.context-markers/[timestamp]_[name].md",
content: [generated marker content]
)
Filename format: {YYYY-MM-DD-HHmm}_{name}.md
Example: 2025-10-16-1430_before-big-refactor.md
Step 4.5: Verify Marker Creation
After creating marker, verify it was written successfully:
# Verify file exists and is non-empty
if [ -f ".agent/.context-markers/[filename]" ] && [ -s ".agent/.context-markers/[filename]" ]; then
# Calculate checksum for verification
checksum=$(md5 -q ".agent/.context-markers/[filename]" 2>/dev/null || md5sum ".agent/.context-markers/[filename]" | cut -d' ' -f1)
# Log to central marker log
echo "[$(date -u +"%Y-%m-%dT%H:%M:%SZ")] ✅ Marker created: [filename] (checksum: $checksum)" >> .agent/.marker-log
echo "✅ Marker verified successfully"
else
echo "❌ Marker creation failed - file missing or empty"
exit 1
fi
Marker verification ensures:
- File exists on disk
- File has content (non-empty)
- Checksum logged for integrity verification
- Creation event logged to central log
Step 5: Confirm Creation
Show success message with verification details:
✅ Context marker created!
Marker: [name]
File: .agent/.context-markers/[filename]
Size: [X] KB (~[Y] tokens)
Checksum: [md5-hash]
Verified: ✅
This marker captures:
- Last [N] messages of conversation
- Files you were working on
- Technical decisions made
- Next steps to continue
To restore later:
- Start new session
- Say "load marker [name]"
- Or use /nav:markers to list all markers
Logged to: .agent/.marker-log
Scripts
create_marker.py: Generates marker content from conversation analysis
- Input: Conversation history (from Claude)
- Output: Formatted markdown marker
Common Use Cases
Before Lunch Break
User: "Save my progress, taking lunch"
→ Creates marker: "lunch-break-2025-10-16"
→ Captures current state
→ User resumes after lunch: "Load my lunch marker"
Before Risky Refactor
User: "Mark this before I refactor routing"
→ Creates marker: "before-routing-refactor"
→ If refactor fails, restore marker
→ If refactor succeeds, delete marker
End of Day
User: "End of day checkpoint"
→ Creates marker: "eod-2025-10-16"
→ Note: "OAuth done, tests tomorrow"
→ Next morning: "Load yesterday's marker"
Before Context Compact
Automatic (via nav-compact skill):
→ Creates marker: "before-compact-2025-10-16-1500"
→ Compact clears conversation
→ Marker preserves knowledge
→ Next session: Auto-offers to restore
Marker Best Practices
Good marker names:
lunch-break(clear when/why)before-api-refactor(indicates purpose)feature-complete(marks milestone)eod-friday(specific timing)
Bad marker names:
temp(not descriptive)marker1(meaningless)test(confusing)
When to create markers:
- ✅ Before breaks (lunch, EOD)
- ✅ Before risky changes
- ✅ Before context compact
- ✅ At milestones (feature complete)
- ❌ After every single message (noise)
- ❌ When context is fresh (< 5 messages)
Error Handling
Marker directory missing:
Creating .agent/.context-markers/ directory...
✅ Ready to save markers
Duplicate marker name:
⚠️ Marker "[name]" already exists
Options:
1. Overwrite (replace existing)
2. Append timestamp (create "[name]-v2")
3. Choose different name
Your choice [1-3]:
Insufficient context:
⚠️ Very little context to save (< 5 messages)
Markers work best when there's significant progress to preserve.
Continue anyway? [y/N]:
Success Criteria
Marker creation is successful when:
- Marker file created in
.agent/.context-markers/ - Filename is unique and descriptive
- Content includes: summary, loaded docs, files modified, next steps
- User knows how to restore marker later
- Marker is 2-5k tokens (comprehensive but efficient)
Notes
- Markers are git-ignored (personal session save points)
- Team members don't see each other's markers
- Markers can be deleted anytime with
/nav:markers clean - Typical marker size: 2-5k tokens (97.7% compression from 130k conversation)
This skill provides same functionality as /nav:marker command but with natural language invocation.
GitHub リポジトリ
関連スキル
algorithmic-art
メタThis Claude Skill creates original algorithmic art using p5.js with seeded randomness and interactive parameters. It generates .md files for algorithmic philosophies, plus .html and .js files for interactive generative art implementations. Use it when developers need to create flow fields, particle systems, or other computational art while avoiding copyright issues.
subagent-driven-development
開発This skill executes implementation plans by dispatching a fresh subagent for each independent task, with code review between tasks. It enables fast iteration while maintaining quality gates through this review process. Use it when working on mostly independent tasks within the same session to ensure continuous progress with built-in quality checks.
executing-plans
デザインUse the executing-plans skill when you have a complete implementation plan to execute in controlled batches with review checkpoints. It loads and critically reviews the plan, then executes tasks in small batches (default 3 tasks) while reporting progress between each batch for architect review. This ensures systematic implementation with built-in quality control checkpoints.
cost-optimization
その他This Claude Skill helps developers optimize cloud costs through resource rightsizing, tagging strategies, and spending analysis. It provides a framework for reducing cloud expenses and implementing cost governance across AWS, Azure, and GCP. Use it when you need to analyze infrastructure costs, right-size resources, or meet budget constraints.
