[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6ENSX7TF8DDKT93GPV64CSJ":3,"skill-same:01M6ENSX7TF8DDKT93GPV64CSJ":75},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":51,"ownerHtmlUrl":52,"ownerBlogUrl":6,"ownerDescription":53,"updatedAt":54,"install":55,"resources":68},"01M6ENSX7TF8DDKT93GPV64CSJ","chronicle-assistant-guide",null,"Project-agnostic guidance for AI assistants using Chronicle. Provides search-first directives, best practices, and workflow patterns across ALL Chronicle-tracked projects. Works with or without MCP server.","ComeOnOliver\u002Fskillshub","ComeOnOliver","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F43215937?v=4","01M6E5JNFECJAAVFE0W7SMWWD2","Haoran Shu","01M6E5JNNDQS7AJZDYFQ8TPZCK",67,"MIT","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fchandlerhardy\u002Fchronicle-assistant-guide\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"assistant","chronicle assistant guide","guide","chronicle","workflow","best practices","search","server","first","projects","mcp server","guidance","workflow patterns","patterns","across","project","MCP","2026-11-10 10:12:30",false,"---\nname: chronicle-assistant-guide\ndescription: Project-agnostic guidance for AI assistants using Chronicle. Provides search-first directives, best practices, and workflow patterns across ALL Chronicle-tracked projects. Works with or without MCP server.\n---\n\n# Chronicle Assistant Guide\n\n> **Purpose**: Universal directives for AI assistants using Chronicle\n> **Scope**: Works across ALL projects (with MCP server OR CLI-only)\n> **Priority**: Load this FIRST when Chronicle is available\n\n---\n\n## Auto-Activation\n\n> **This skill auto-activates!** (Milestone #13)\n>\n> Prompts like \"how do I use chronicle?\" automatically trigger this skill. Lower priority than other skills.\n>\n> **Trigger patterns:** how to use chronicle, chronicle help, chronicle guide\n> **See:** `docs\u002FHOOKS.md` for full details\n\n---\n\n## ⚡ CRITICAL: Pre-Flight Checklist\n\n**Before starting ANY Chronicle-related task, run through this checklist:**\n\n1. ✅ **SEARCH FIRST**: Search Chronicle's history\n   - **With MCP**: `mcp__chronicle__search_sessions(query=\"relevant keywords\", limit=5)`\n   - **Without MCP**: `chronicle search \"relevant keywords\" --limit 5`\n   - Has this been done before?\n   - What context exists about this feature\u002Fissue?\n   - What approaches failed or succeeded?\n\n2. ✅ **Check Skills**: Is there a Chronicle skill for this task?\n   - `chronicle-workflow` - Session workflow guidance\n   - `chronicle-session-documenter` - Document to Obsidian\n   - `chronicle-context-retriever` - Search past work\n   - `chronicle-project-tracker` - Roadmap and milestones\n\n3. ✅ **Prefer MCP over CLI**: Use best available tool\n   - **MCP available?** → Fast (\u003C10ms), structured JSON, no subprocess overhead\n   - **CLI only?** → Still works, slightly slower (~100ms), parse formatted output\n   - Both provide the same data, choose based on environment\n\n4. ✅ **Check roadmap**: View current milestones and next steps\n   - **With MCP**: `mcp__chronicle__get_roadmap(days=7)`\n   - **Without MCP**: `chronicle roadmap --days 7`\n   - Is this already tracked as a milestone?\n   - Are there related next steps?\n\n**Why this matters:** Chronicle dogfoods itself. Every mistake we make is recorded. Learn from history!\n\n---\n\n## ? Core Directives\n\n### 1. ALWAYS Search Chronicle Before Implementing\n\n**The Rule (use whichever is available):**\n\n**Option 1: MCP (if available)**\n```python\n# Before implementing ANY feature:\nmcp__chronicle__search_sessions(query=\"feature name\", limit=5)\n\n# Before debugging:\nmcp__chronicle__search_sessions(query=\"error or symptom\", limit=5)\n\n# When user questions something:\nmcp__chronicle__search_sessions(query=\"topic keywords\", limit=5)\n```\n\n**Option 2: CLI (always works)**\n```bash\n# Before implementing ANY feature:\nchronicle search \"feature name\" --limit 5\n\n# Before debugging:\nchronicle search \"error or symptom\" --limit 5\n\n# When user questions something:\nchronicle search \"topic keywords\" --limit 5\n```\n\n**Real examples from Chronicle's own history:**\n\n**Example 1: Session 21 transcript cleaning confusion**\n```\nUser: \"I can't believe there's no cleaning to be done on session 21\"\n❌ Without search: Spent time debugging, confused why 0% reduction\n✅ With search: Would have found Session 13 implemented transcript cleaning\n→ Result: Immediately understood cleaning happens at storage time\n→ Time saved: 15+ minutes of debugging\n```\n\n**Example 2: Sessions 30 & 31 - Duplicate MCP optimization**\n```\nSession 30 (Oct 24): Fixed MCP response size by excluding summaries from get_sessions()\nSession 31 (Oct 24): SAME issue - MCP responses too large, same fix needed\n\n❌ What happened: Session 31 didn't search for \"MCP response size\"\n✅ What should have happened: Search finds Session 30's solution immediately\n→ Result: Could have referenced Session 30's approach instead of rediscovering\n→ Time saved: 10+ minutes of diagnosis and implementation\n```\n\n**Example 3: Skill documentation update (Session 32)**\n```\nTask: Update chronicle-session-documenter skill with MCP tool instructions\n❌ What I did: Jumped straight to editing SKILL.md without searching\n✅ What I should have done: Search \"skill documentation update\" first\n→ Result: Might have found context about skill format standards\n→ Lesson: Even when search finds nothing, the habit prevents future mistakes\n```\n\n**Cost Calculator:**\n```\nTime to search:        \u003C1 second\nTime saved (average):  10-20 minutes per incident\nIncidents so far:      3+ documented cases\nTotal time wasted:     ~45+ minutes that could have been saved\nCost of skipping:      45 minutes \u002F 1 second = 2,700x ROI on searching!\n```\n\n**Make it a reflex:** The 1-second search is ALWAYS worth it. No exceptions.\n\n---\n\n### 2. Prefer MCP Tools, Fall Back to CLI\n\n**Priority Order:**\n1. ✅ **Chronicle Skills** (best - handles complex workflows)\n2. ✅ **MCP tools** (fastest - if MCP server available)\n3. ✅ **CLI commands** (portable - works everywhere Chronicle is installed)\n\n**Why MCP is preferred when available:**\n- **Speed**: MCP queries database directly (\u003C10ms), CLI spawns subprocess (~100ms)\n- **Programmatic**: Returns structured JSON, not formatted text\n- **Reliable**: No parsing of human-readable output\n- **Efficient**: No terminal formatting overhead\n\n**When to use CLI:**\n- MCP server not configured (e.g., minimal installations, FreeBSD, remote systems)\n- User explicitly requests CLI output\n- Testing CLI functionality\n\n**Examples:**\n\n**With MCP Available:**\n```python\n# Fast, structured responses\nroadmap = mcp__chronicle__get_roadmap(days=7)\nsessions = mcp__chronicle__search_sessions(query=\"storage\", limit=5)\nsummary = mcp__chronicle__get_session_summary(session_id=16)\n```\n\n**Without MCP (CLI Fallback):**\n```bash\n# Portable, works everywhere\nchronicle roadmap --days 7\nchronicle search \"storage\" --limit 5\nchronicle session 16\n```\n\n**Decision Pattern:**\n```\nNeed Chronicle data\n├─ MCP available? → Use mcp__chronicle__\u003Ctool>()\n└─ MCP not available? → Use chronicle \u003Ccommand>\n```\n\n---\n\n## ? Available Tools (MCP + CLI)\n\n> **Note**: All operations below work with BOTH MCP tools and CLI commands. Use MCP for speed when available, CLI for portability.\n\n**Session & Commit Tracking:**\n\n**MCP Approach:**\n```python\n# List sessions (summaries excluded by default for performance)\nmcp__chronicle__get_sessions(limit=10, tool=\"claude-code\", repo_path=\"\u002Fpath\", days=7)\nmcp__chronicle__get_sessions(limit=10, include_summaries=True)  # Optional: include summaries\n\n# Get single session details with full summary\nmcp__chronicle__get_session_summary(session_id=16)\n\n# Batch retrieve summaries for multiple sessions\nmcp__chronicle__get_sessions_summaries(session_ids=[15, 16, 17])\n\n# Search and other queries\nmcp__chronicle__search_sessions(query=\"MCP server\", limit=10)\nmcp__chronicle__get_commits(limit=20, repo_path=\"\u002Fpath\", days=7)\nmcp__chronicle__search_commits(query=\"retry logic\", limit=20)\nmcp__chronicle__get_timeline(days=1, repo_path=\"\u002Fpath\")\nmcp__chronicle__get_stats(days=7)\n```\n\n**CLI Equivalents:**\n```bash\n# List and view sessions\nchronicle sessions --limit 10 --tool claude-code\nchronicle session 16  # Get details with summary\n\n# Search\nchronicle search \"MCP server\" --limit 10\n\n# Commits and timeline\nchronicle show today --limit 20\nchronicle timeline today\n\n# Statistics\nchronicle stats --days 7\n```\n\n**Project Tracking:**\n\n**MCP Approach:**\n```python\nmcp__chronicle__get_milestones(status=\"in_progress\", milestone_type=\"feature\", limit=20)\nmcp__chronicle__get_milestone(milestone_id=1)\nmcp__chronicle__get_next_steps(completed=False, milestone_id=1, limit=20)\nmcp__chronicle__get_roadmap(days=7)\nmcp__chronicle__update_milestone_status(milestone_id=1, new_status=\"completed\")\nmcp__chronicle__complete_next_step(step_id=1)\n```\n\n**CLI Equivalents:**\n```bash\n# Milestones\nchronicle milestones --status in_progress\nchronicle milestone 1\n\n# Roadmap and next steps\nchronicle roadmap --days 7\nchronicle next-steps --pending\n\n# Updates\nchronicle milestone-status 1 completed\nchronicle complete-step 1\n```\n\n---\n\n## ? Typical Workflows\n\n### Starting a New Task\n\n**With MCP:**\n```python\n# 1. Search for related past work\nresults = mcp__chronicle__search_sessions(query=\"authentication\", limit=5)\n\n# 2. Check roadmap\nroadmap = mcp__chronicle__get_roadmap(days=7)\n\n# 3. If needed, check specific session\nif results:\n    session = mcp__chronicle__get_session_summary(session_id=results[0][\"id\"])\n\n# 4. Now implement with full context\n```\n\n**With CLI:**\n```bash\n# 1. Search for related past work\nchronicle search \"authentication\" --limit 5\n\n# 2. Check roadmap\nchronicle roadmap --days 7\n\n# 3. View specific session details\nchronicle session \u003Cid>\n\n# 4. Now implement with full context\n```\n\n### Debugging an Issue\n\n**With MCP:**\n```python\n# 1. Search for error message or symptom\nresults = mcp__chronicle__search_sessions(query=\"hang freeze stuck\", limit=5)\n\n# 2. Get full context from relevant session\nif results:\n    session = mcp__chronicle__get_session_summary(session_id=results[0][\"id\"])\n    # Read how it was solved before\n```\n\n**With CLI:**\n```bash\n# 1. Search for error message or symptom\nchronicle search \"hang freeze stuck\" --limit 5\n\n# 2. View relevant session\nchronicle session \u003Cid>\n# Read how it was solved before\n```\n\n### Understanding Project History\n\n**With MCP:**\n```python\n# Get overview\nstats = mcp__chronicle__get_stats(days=30)\ntimeline = mcp__chronicle__get_timeline(days=7)\n\n# Find specific work\nsessions = mcp__chronicle__search_sessions(query=\"optimization\", limit=10)\n```\n\n**With CLI:**\n```bash\n# Get overview\nchronicle stats --days 30\nchronicle timeline week\n\n# Find specific work\nchronicle search \"optimization\" --limit 10\n```\n\n---\n\n## ? Common Mistakes to Avoid\n\n**❌ DON'T:**\n- Jump straight to implementing without searching\n- Ignore the CLI when MCP isn't available\n- Forget to check the roadmap\n- Ignore related sessions in search results\n\n**✅ DO:**\n- Search first, implement second (MCP or CLI)\n- Use best available tool (MCP preferred, CLI fallback)\n- Check roadmap before creating new milestones\n- Read summaries of related sessions for context\n\n---\n\n## ? Chronicle Quick Reference\n\n**Session Organization (Phase 6):**\n```bash\n# Organize sessions (use CLI for these)\nchronicle rename-session 32 \"Feature Implementation\"\nchronicle tag-session 32 optimization,phase-6\nchronicle link-session 32 --related-to 30,31\nchronicle auto-title 31  # AI-generated title\nchronicle graph --sessions 28-32  # Visualize relationships\n```\n\n**Current State:**\n- Database: `~\u002F.ai-session\u002Fsessions.db` (SQLite)\n- Transcripts: `~\u002F.ai-session\u002Fsessions\u002F*.cleaned` (file-based)\n- Configuration: `~\u002F.ai-session\u002Fconfig.yaml`\n- MCP Server: Provides 15+ tools for querying Chronicle\n\n**Storage:**\n- Summaries: Generated automatically in background after session ends\n- Titles: Can be set manually or AI-generated\n- Tags: JSON array for categorization\n- Relationships: parent_session_id, related_session_ids\n\n---\n\n## ? Pro Tips\n\n1. **Always search before implementing** - Chronicle has 100+ hours of documented work\n2. **Use batch operations** - `get_sessions_summaries()` for multiple sessions at once\n3. **Filter aggressively** - Use repo_path, days, tool filters to narrow results\n4. **Check session organization** - Look for titles\u002Ftags to understand session purpose\n5. **Follow the graph** - Use `chronicle graph` to see session relationships\n6. **Trust the summaries** - They're generated by AI and usually accurate\n7. **Update roadmap** - Complete next steps and milestones as you work\n\n---\n\n## ? Related Resources\n\n- **Project CLAUDE.md**: May have project-specific directives\n- **Chronicle Skills**: Use `chronicle-workflow`, `chronicle-context-retriever`, etc.\n- **MCP Documentation**: See `MCP_SERVER.md` in Chronicle repo\n\n---\n\n**Remember:** This skill applies to ALL projects using Chronicle. The directives here are universal best practices for AI assistants.\n","# Chronicle Assistant Guide\n\n> **Purpose**: Universal directives for AI assistants using Chronicle\n> **Scope**: Works across ALL projects (with MCP server OR CLI-only)\n> **Priority**: Load this FIRST when Chronicle is available\n\n---\n\n## Auto-Activation\n\n> **This skill auto-activates!** (Milestone #13)\n>\n> Prompts like \"how do I use chronicle?\" automatically trigger this skill. Lower priority than other skills.\n>\n> **Trigger patterns:** how to use chronicle, chronicle help, chronicle guide\n> **See:** `docs\u002FHOOKS.md` for full details\n\n---\n\n## ⚡ CRITICAL: Pre-Flight Checklist\n\n**Before starting ANY Chronicle-related task, run through this checklist:**\n\n1. ✅ **SEARCH FIRST**: Search Chronicle's history\n   - **With MCP**: `mcp__chronicle__search_sessions(query=\"relevant keywords\", limit=5)`\n   - **Without MCP**: `chronicle search \"relevant keywords\" --limit 5`\n   - Has this been done before?\n   - What context exists about this feature\u002Fissue?\n   - What approaches failed or succeeded?\n\n2. ✅ **Check Skills**: Is there a Chronicle skill for this task?\n   - `chronicle-workflow` - Session workflow guidance\n   - `chronicle-session-documenter` - Document to Obsidian\n   - `chronicle-context-retriever` - Search past work\n   - `chronicle-project-tracker` - Roadmap and milestones\n\n3. ✅ **Prefer MCP over CLI**: Use best available tool\n   - **MCP available?** → Fast (\u003C10ms), structured JSON, no subprocess overhead\n   - **CLI only?** → Still works, slightly slower (~100ms), parse formatted output\n   - Both provide the same data, choose based on environment\n\n4. ✅ **Check roadmap**: View current milestones and next steps\n   - **With MCP**: `mcp__chronicle__get_roadmap(days=7)`\n   - **Without MCP**: `chronicle roadmap --days 7`\n   - Is this already tracked as a milestone?\n   - Are there related next steps?\n\n**Why this matters:** Chronicle dogfoods itself. Every mistake we make is recorded. Learn from history!\n\n---\n\n## ? Core Directives\n\n### 1. ALWAYS Search Chronicle Before Implementing\n\n**The Rule (use whichever is available):**\n\n**Option 1: MCP (if available)**\n```python\n# Before implementing ANY feature:\nmcp__chronicle__search_sessions(query=\"feature name\", limit=5)\n\n# Before debugging:\nmcp__chronicle__search_sessions(query=\"error or symptom\", limit=5)\n\n# When user questions something:\nmcp__chronicle__search_sessions(query=\"topic keywords\", limit=5)\n```\n\n**Option 2: CLI (always works)**\n```bash\n# Before implementing ANY feature:\nchronicle search \"feature name\" --limit 5\n\n# Before debugging:\nchronicle search \"error or symptom\" --limit 5\n\n# When user questions something:\nchronicle search \"topic keywords\" --limit 5\n```\n\n**Real examples from Chronicle's own history:**\n\n**Example 1: Session 21 transcript cleaning confusion**\n```\nUser: \"I can't believe there's no cleaning to be done on session 21\"\n❌ Without search: Spent time debugging, confused why 0% reduction\n✅ With search: Would have found Session 13 implemented transcript cleaning\n→ Result: Immediately understood cleaning happens at storage time\n→ Time saved: 15+ minutes of debugging\n```\n\n**Example 2: Sessions 30 & 31 - Duplicate MCP optimization**\n```\nSession 30 (Oct 24): Fixed MCP response size by excluding summaries from get_sessions()\nSession 31 (Oct 24): SAME issue - MCP responses too large, same fix needed\n\n❌ What happened: Session 31 didn't search for \"MCP response size\"\n✅ What should have happened: Search finds Session 30's solution immediately\n→ Result: Could have referenced Session 30's approach instead of rediscovering\n→ Time saved: 10+ minutes of diagnosis and implementation\n```\n\n**Example 3: Skill documentation update (Session 32)**\n```\nTask: Update chronicle-session-documenter skill with MCP tool instructions\n❌ What I did: Jumped straight to editing SKILL.md without searching\n✅ What I should have done: Search \"skill documentation update\" first\n→ Result: Might have found context about skill format standards\n→ Lesson: Even when search finds nothing, the habit prevents future mistakes\n```\n\n**Cost Calculator:**\n```\nTime to search:        \u003C1 second\nTime saved (average):  10-20 minutes per incident\nIncidents so far:      3+ documented cases\nTotal time wasted:     ~45+ minutes that could have been saved\nCost of skipping:      45 minutes \u002F 1 second = 2,700x ROI on searching!\n```\n\n**Make it a reflex:** The 1-second search is ALWAYS worth it. No exceptions.\n\n---\n\n### 2. Prefer MCP Tools, Fall Back to CLI\n\n**Priority Order:**\n1. ✅ **Chronicle Skills** (best - handles complex workflows)\n2. ✅ **MCP tools** (fastest - if MCP server available)\n3. ✅ **CLI commands** (portable - works everywhere Chronicle is installed)\n\n**Why MCP is preferred when available:**\n- **Speed**: MCP queries database directly (\u003C10ms), CLI spawns subprocess (~100ms)\n- **Programmatic**: Returns structured JSON, not formatted text\n- **Reliable**: No parsing of human-readable output\n- **Efficient**: No terminal formatting overhead\n\n**When to use CLI:**\n- MCP server not configured (e.g., minimal installations, FreeBSD, remote systems)\n- User explicitly requests CLI output\n- Testing CLI functionality\n\n**Examples:**\n\n**With MCP Available:**\n```python\n# Fast, structured responses\nroadmap = mcp__chronicle__get_roadmap(days=7)\nsessions = mcp__chronicle__search_sessions(query=\"storage\", limit=5)\nsummary = mcp__chronicle__get_session_summary(session_id=16)\n```\n\n**Without MCP (CLI Fallback):**\n```bash\n# Portable, works everywhere\nchronicle roadmap --days 7\nchronicle search \"storage\" --limit 5\nchronicle session 16\n```\n\n**Decision Pattern:**\n```\nNeed Chronicle data\n├─ MCP available? → Use mcp__chronicle__\u003Ctool>()\n└─ MCP not available? → Use chronicle \u003Ccommand>\n```\n\n---\n\n## ? Available Tools (MCP + CLI)\n\n> **Note**: All operations below work with BOTH MCP tools and CLI commands. Use MCP for speed when available, CLI for portability.\n\n**Session & Commit Tracking:**\n\n**MCP Approach:**\n```python\n# List sessions (summaries excluded by default for performance)\nmcp__chronicle__get_sessions(limit=10, tool=\"claude-code\", repo_path=\"\u002Fpath\", days=7)\nmcp__chronicle__get_sessions(limit=10, include_summaries=True)  # Optional: include summaries\n\n# Get single session details with full summary\nmcp__chronicle__get_session_summary(session_id=16)\n\n# Batch retrieve summaries for multiple sessions\nmcp__chronicle__get_sessions_summaries(session_ids=[15, 16, 17])\n\n# Search and other queries\nmcp__chronicle__search_sessions(query=\"MCP server\", limit=10)\nmcp__chronicle__get_commits(limit=20, repo_path=\"\u002Fpath\", days=7)\nmcp__chronicle__search_commits(query=\"retry logic\", limit=20)\nmcp__chronicle__get_timeline(days=1, repo_path=\"\u002Fpath\")\nmcp__chronicle__get_stats(days=7)\n```\n\n**CLI Equivalents:**\n```bash\n# List and view sessions\nchronicle sessions --limit 10 --tool claude-code\nchronicle session 16  # Get details with summary\n\n# Search\nchronicle search \"MCP server\" --limit 10\n\n# Commits and timeline\nchronicle show today --limit 20\nchronicle timeline today\n\n# Statistics\nchronicle stats --days 7\n```\n\n**Project Tracking:**\n\n**MCP Approach:**\n```python\nmcp__chronicle__get_milestones(status=\"in_progress\", milestone_type=\"feature\", limit=20)\nmcp__chronicle__get_milestone(milestone_id=1)\nmcp__chronicle__get_next_steps(completed=False, milestone_id=1, limit=20)\nmcp__chronicle__get_roadmap(days=7)\nmcp__chronicle__update_milestone_status(milestone_id=1, new_status=\"completed\")\nmcp__chronicle__complete_next_step(step_id=1)\n```\n\n**CLI Equivalents:**\n```bash\n# Milestones\nchronicle milestones --status in_progress\nchronicle milestone 1\n\n# Roadmap and next steps\nchronicle roadmap --days 7\nchronicle next-steps --pending\n\n# Updates\nchronicle milestone-status 1 completed\nchronicle complete-step 1\n```\n\n---\n\n## ? Typical Workflows\n\n### Starting a New Task\n\n**With MCP:**\n```python\n# 1. Search for related past work\nresults = mcp__chronicle__search_sessions(query=\"authentication\", limit=5)\n\n# 2. Check roadmap\nroadmap = mcp__chronicle__get_roadmap(days=7)\n\n# 3. If needed, check specific session\nif results:\n    session = mcp__chronicle__get_session_summary(session_id=results[0][\"id\"])\n\n# 4. Now implement with full context\n```\n\n**With CLI:**\n```bash\n# 1. Search for related past work\nchronicle search \"authentication\" --limit 5\n\n# 2. Check roadmap\nchronicle roadmap --days 7\n\n# 3. View specific session details\nchronicle session \u003Cid>\n\n# 4. Now implement with full context\n```\n\n### Debugging an Issue\n\n**With MCP:**\n```python\n# 1. Search for error message or symptom\nresults = mcp__chronicle__search_sessions(query=\"hang freeze stuck\", limit=5)\n\n# 2. Get full context from relevant session\nif results:\n    session = mcp__chronicle__get_session_summary(session_id=results[0][\"id\"])\n    # Read how it was solved before\n```\n\n**With CLI:**\n```bash\n# 1. Search for error message or symptom\nchronicle search \"hang freeze stuck\" --limit 5\n\n# 2. View relevant session\nchronicle session \u003Cid>\n# Read how it was solved before\n```\n\n### Understanding Project History\n\n**With MCP:**\n```python\n# Get overview\nstats = mcp__chronicle__get_stats(days=30)\ntimeline = mcp__chronicle__get_timeline(days=7)\n\n# Find specific work\nsessions = mcp__chronicle__search_sessions(query=\"optimization\", limit=10)\n```\n\n**With CLI:**\n```bash\n# Get overview\nchronicle stats --days 30\nchronicle timeline week\n\n# Find specific work\nchronicle search \"optimization\" --limit 10\n```\n\n---\n\n## ? Common Mistakes to Avoid\n\n**❌ DON'T:**\n- Jump straight to implementing without searching\n- Ignore the CLI when MCP isn't available\n- Forget to check the roadmap\n- Ignore related sessions in search results\n\n**✅ DO:**\n- Search first, implement second (MCP or CLI)\n- Use best available tool (MCP preferred, CLI fallback)\n- Check roadmap before creating new milestones\n- Read summaries of related sessions for context\n\n---\n\n## ? Chronicle Quick Reference\n\n**Session Organization (Phase 6):**\n```bash\n# Organize sessions (use CLI for these)\nchronicle rename-session 32 \"Feature Implementation\"\nchronicle tag-session 32 optimization,phase-6\nchronicle link-session 32 --related-to 30,31\nchronicle auto-title 31  # AI-generated title\nchronicle graph --sessions 28-32  # Visualize relationships\n```\n\n**Current State:**\n- Database: `~\u002F.ai-session\u002Fsessions.db` (SQLite)\n- Transcripts: `~\u002F.ai-session\u002Fsessions\u002F*.cleaned` (file-based)\n- Configuration: `~\u002F.ai-session\u002Fconfig.yaml`\n- MCP Server: Provides 15+ tools for querying Chronicle\n\n**Storage:**\n- Summaries: Generated automatically in background after session ends\n- Titles: Can be set manually or AI-generated\n- Tags: JSON array for categorization\n- Relationships: parent_session_id, related_session_ids\n\n---\n\n## ? Pro Tips\n\n1. **Always search before implementing** - Chronicle has 100+ hours of documented work\n2. **Use batch operations** - `get_sessions_summaries()` for multiple sessions at once\n3. **Filter aggressively** - Use repo_path, days, tool filters to narrow results\n4. **Check session organization** - Look for titles\u002Ftags to understand session purpose\n5. **Follow the graph** - Use `chronicle graph` to see session relationships\n6. **Trust the summaries** - They're generated by AI and usually accurate\n7. **Update roadmap** - Complete next steps and milestones as you work\n\n---\n\n## ? Related Resources\n\n- **Project CLAUDE.md**: May have project-specific directives\n- **Chronicle Skills**: Use `chronicle-workflow`, `chronicle-context-retriever`, etc.\n- **MCP Documentation**: See `MCP_SERVER.md` in Chronicle repo\n\n---\n\n**Remember:** This skill applies to ALL projects using Chronicle. The directives here are universal best practices for AI assistants.\n",{"name":5,"description":7},"main","def8531e65114c0fca8fb8551c1871ee0eed705c","skills\u002Faiskillstore\u002Fmarketplace\u002Fchandlerhardy\u002Fchronicle-assistant-guide",24,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub","https:\u002F\u002Fskillshub.wtf","https:\u002F\u002Fgithub.com\u002FComeOnOliver","AI & Blockchain Engineer\r\n","2026-06-24 22:07:19",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add ComeOnOliver\u002Fskillshub --skill chronicle-assistant-guide",{"tool":61,"command":62},"bunx","bunx skills add ComeOnOliver\u002Fskillshub --skill chronicle-assistant-guide",{"tool":64,"command":65},"pnpm","pnpm dlx skills add ComeOnOliver\u002Fskillshub --skill chronicle-assistant-guide","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fchandlerhardy\u002Fchronicle-assistant-guide\u002FSKILL.md",true,[69],{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"skill-report.json","REFERENCE","参考文档",15396,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fchandlerhardy\u002Fchronicle-assistant-guide\u002Fskill-report.json",[76,86,95,104,110,117],{"skillNo":77,"name":78,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":82,"publishedAt":41},"01M6FKJN13GMG4KY57J3QD8GY5","model-hierarchy-skill","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzscole\u002Fmodel-hierarchy-skill\u002Fmodel-hierarchy-skill\u002FSKILL.md",[81],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[83,84,85],"model","model hierarchy","model hierarchy skill",{"skillNo":87,"name":88,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":92,"publishedAt":41},"01M6FKJJJ6GCAMR4PPPRD12M5X","zoom-mcp","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fzoom-mcp\u002FSKILL.md",[91],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[40,93,94],"zoom","zoom mcp",{"skillNo":96,"name":97,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":41},"01M6FKJE3KYT3KPEZMEEHYKA6K","zoom-apps-sdk","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fzoom-apps-sdk\u002FSKILL.md",[],[101,102,103,93],"sdk","zoom apps sdk","apps",{"skillNo":105,"name":106,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":41},"01M6FKJ9EDH9Q5VWDF8HAJRSP0","windows","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwindows\u002FSKILL.md",[],[106],{"skillNo":111,"name":112,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":116,"publishedAt":41},"01M6FKJ666BEEFC3AE9GJ72Q93","whiteboard","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwhiteboard\u002FSKILL.md",[115],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[112],{"skillNo":118,"name":119,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":41},"01M6FKJ21WFCDGTJQ2Q91T9DVW","websockets","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwebsockets\u002FSKILL.md",[],[119]]