Skip to content
conport-memory logo

Conport Memory

conport-memory

Access Context Portal (ConPort) as persistent project memory via MCPorter. Load/update project context, log decisions and progress, track patterns. Use PROACTIVELY at session start to load context and throughout work to log decisions. Combats AI amnesia across sessions.

SKILL.md

Full skill instructions

<conport_memory_skill> <overview> ConPort is your project's memory bank - a SQLite-backed knowledge base that persists decisions, progress, patterns, and context across Claude Code sessions. Access via MCPorter CLI without MCP installation. </​overview>

<when_to_use_proactively> <scenario trigger="session_start">Load product_context and active_context</​scenario> <scenario trigger="architectural_decision">Log decision with rationale and tags</​scenario> <scenario trigger="task_completion">Update progress with status</​scenario> <scenario trigger="pattern_discovery">Log system_pattern for reuse</​scenario> <scenario trigger="session_end">Update active_context with current state</​scenario> </​when_to_use_proactively>

<mcporter_base_command> npx mcporter call --stdio "uvx --from context-portal-mcp conport-mcp --mode stdio" conport.TOOL_NAME </​mcporter_base_command>

<core_commands> <command name="Get Product Context" purpose="Load overall project goals/​architecture"> npx mcporter call --stdio "uvx --from context-portal-mcp conport-mcp --mode stdio"
conport.get_product_context </​command>

<command name="Update Product Context" purpose="Set project overview">
  npx mcporter call --stdio "uvx --from context-portal-mcp conport-mcp --mode stdio" \
    conport.update_product_context content:"Project overview text..."
</​command>

<command name="Get Active Context" purpose="Load current working focus">
  npx mcporter call --stdio "uvx --from context-portal-mcp conport-mcp --mode stdio" \
    conport.get_active_context
</​command>

<command name="Update Active Context" purpose="Update current session state">
  npx mcporter call --stdio "uvx --from context-portal-mcp conport-mcp --mode stdio" \
    conport.update_active_context content:"Currently working on..."
</​command>

<command name="Log Decision" purpose="Record architectural decision">
  npx mcporter call --stdio "uvx --from context-portal-mcp conport-mcp --mode stdio" \
    conport.log_decision \
    summary:"Decision title" \
    rationale:"Why this was decided" \
    details:"Full decision details" \
    tags:'["architecture", "database"]'
</​command>

<command name="Get Decisions" purpose="Retrieve logged decisions">
  npx mcporter call --stdio "uvx --from context-portal-mcp conport-mcp --mode stdio" \
    conport.get_decisions tags:'["architecture"]'
</​command>

<command name="Search Decisions" purpose="Full-text search across decisions">
  npx mcporter call --stdio "uvx --from context-portal-mcp conport-mcp --mode stdio" \
    conport.search_decisions_fts query:"authentication"
</​command>

<command name="Log Progress" purpose="Record task status">
  npx mcporter call --stdio "uvx --from context-portal-mcp conport-mcp --mode stdio" \
    conport.log_progress \
    status:"in_progress" \
    description:"Implementing user authentication"
</​command>

<command name="Get Progress" purpose="Retrieve progress entries">
  npx mcporter call --stdio "uvx --from context-portal-mcp conport-mcp --mode stdio" \
    conport.get_progress status:"in_progress"
</​command>

<command name="Log System Pattern" purpose="Document reusable pattern">
  npx mcporter call --stdio "uvx --from context-portal-mcp conport-mcp --mode stdio" \
    conport.log_system_pattern \
    name:"Repository Pattern" \
    description:"Data access abstraction" \
    tags:'["architecture", "data-layer"]'
</​command>

<command name="Get System Patterns" purpose="Retrieve documented patterns">
  npx mcporter call --stdio "uvx --from context-portal-mcp conport-mcp --mode stdio" \
    conport.get_system_patterns
</​command>

<command name="Log Custom Data" purpose="Store project-specific key-value data">
  npx mcporter call --stdio "uvx --from context-portal-mcp conport-mcp --mode stdio" \
    conport.log_custom_data \
    category:"glossary" \
    key:"MFA" \
    value:'{"definition": "Multi-Factor Authentication", "context": "Security feature"}'
</​command>

<command name="Export to Markdown" purpose="Export all ConPort data">
  npx mcporter call --stdio "uvx --from context-portal-mcp conport-mcp --mode stdio" \
    conport.export_conport_to_markdown output_dir:"./​context-export"
</​command>

</​core_commands>

<session_workflow> <phase name="Session Start"> 1. Check if context_portal/​context.db exists 2. If exists: - get_product_context - understand project goals - get_active_context - resume from last session - get_progress status:"in_progress" - see pending tasks - get_decisions - review recent architectural decisions 3. If not exists: prompt user to run /​conport-init </​phase>

<phase name="During Work">
  - log_decision - when making architectural choices
  - log_progress - when completing tasks
  - log_system_pattern - when discovering reusable patterns
  - log_custom_data - for project-specific context
</​phase>

<phase name="Session End">
  1. update_active_context - record current state and next steps
  2. log_progress - mark completed items
</​phase>

</​session_workflow>

<knowledge_graph> Link related items to build explicit relationships:

npx mcporter call --stdio "uvx --from context-portal-mcp conport-mcp --mode stdio" \
  conport.link_conport_items \
  source_type:"decision" source_id:"dec-123" \
  target_type:"progress" target_id:"prog-456" \
  relationship:"implements"

Retrieve linked items:
npx mcporter call --stdio "uvx --from context-portal-mcp conport-mcp --mode stdio" \
  conport.get_linked_items item_type:"decision" item_id:"dec-123"

</​knowledge_graph>

<available_tools> Product/​Active Context: - get_product_context, update_product_context - get_active_context, update_active_context

Decisions:
- log_decision, get_decisions, search_decisions_fts, delete_decision_by_id

Progress:
- log_progress, get_progress, update_progress, delete_progress_by_id

Patterns:
- log_system_pattern, get_system_patterns, delete_system_pattern_by_id

Custom Data:
- log_custom_data, get_custom_data, delete_custom_data
- search_project_glossary_fts, search_custom_data_value_fts

Knowledge Graph:
- link_conport_items, get_linked_items

Utility:
- get_item_history, get_recent_activity_summary
- export_conport_to_markdown, import_markdown_to_conport
- batch_log_items, get_conport_schema

</​available_tools> </​conport_memory_skill>

More Productivity & Planning skills

brainstorming logo
Productivity & Planning

brainstorming

Structured design dialogue that validates ideas before implementation begins.

295.4K 385.7K
View
ui-ux-pro-max logo
Productivity & Planning

ui-ux-pro-max

Comprehensive design intelligence for web and mobile UI/UX across 10 technology stacks.

133.1K 383.9K
View
writing-plans logo
Productivity & Planning

writing-plans

Comprehensive implementation plans for multi-step tasks, breaking down specs into bite-sized, testable steps.

295.4K 268K
View
using-superpowers logo
Productivity & Planning

using-superpowers

Introduction to the obra skills system with mandatory skill invocation rules and best practices.

295.4K 259.8K
View
executing-plans logo
Productivity & Planning

executing-plans

Execute a written implementation plan with critical review and task checkpoints.

295.4K 229.1K
View
dispatching-parallel-agents logo
Productivity & Planning

dispatching-parallel-agents

Delegate independent tasks to specialized agents working concurrently with isolated context.

295.4K 206.3K
View
using-git-worktrees logo
Productivity & Planning

using-git-worktrees

Isolated git worktrees with smart directory selection and safety verification.

295.4K 205.2K
View
webapp-testing logo
Productivity & Planning

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

179.7K 170.6K
View
content-strategy logo
Productivity & Planning

content-strategy

Plan searchable and shareable content that drives traffic, builds authority, and generates leads.

53.3K 150.9K
View
repo-intake-and-plan logo
Productivity & Planning

repo-intake-and-plan

README-first repository scanner that extracts commands and classifies reproduction candidates without executing them.

497 139.6K
View
marketing-ideas logo
Productivity & Planning

marketing-ideas

Brainstorm and prioritize marketing strategies tailored to your SaaS stage, budget, and goals.

53.3K 137.2K
View
site-architecture logo
Productivity & Planning

site-architecture

Plan and optimize your website's page hierarchy, navigation, URL structure, and internal linking.

53.3K 112.8K
View

Productivity AI tools

Vimcal logo
Productivity

Vimcal

The world's fastest calendar for remote work

Free
View
SaveDay logo
Productivity

SaveDay

Capture, organize, and utilize your knowledge effortlessly.

Free
View
A
Productivity

Any Summary

Instant Summaries of Audio & Video Interviews with AnySummary

Freemium
View
M
Productivity

Map This

Transform PDFs into engaging mind maps.

Freemium
View
ChatPDF logo
Productivity

ChatPDF

Chat with any PDF instantly

Free
View
I
Productivity

intellisay

Create an optimal daily plan using your voice

Paid
View
A
Productivity

Aurora AI

A productivity platform to centralize organizational knowledge and workflows with contextual AI assistance.

Paid
View
AskYourPDF logo
Productivity

AskYourPDF

AskYourPDF Pricing Plans: Tailored to Your Needs

Free
View