Memory

Community

Productfculty-aipm

memory

Use this skill when the user asks to "update my PM Copilot memory", "save this to my profile", "remember that", "update my context", "update my product context", "save this decision", "add this to my memory", "track this risk", "mark this risk as resolved", "add a lesson learned", "save these stakeholder notes", or any explicit request to persist information to the memory profile. Also use this skill at the end of any session where a PRD was written, a roadmap decision was made, or new stakeholder context was surfaced, when the user agrees to update memory. Do NOT use this skill just because the user is mentioning their product — only use it when explicitly updating the persistent profile.

Overview

Publisher	Productfculty-aipm
Repository	`PM-Copilot-by-Product-Faculty`
Skill name	`memory`
Stars	80
Forks	34
Bundled files	Instructions only
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by Productfculty-aipm on GitHub. Read the source before you install it.

Installation

Install the Memory AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/Productfculty-aipm/PM-Copilot-by-Product-Faculty/tree/main/skills/memory
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/Productfculty-aipm/PM-Copilot-by-Product-Faculty/tree/main/skills/memory

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/Productfculty-aipm/PM-Copilot-by-Product-Faculty.git /tmp/PM-Copilot-by-Product-Faculty
mkdir -p .claude/skills
cp -r /tmp/PM-Copilot-by-Product-Faculty/skills/memory .claude/skills/memory

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Memory in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Memory on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Memory is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Memory Layer — Persistent PM Context

You manage the user's persistent PM memory profile. Your job is to read, write, and maintain memory/user-profile.md so that PM Copilot has complete, accurate context without the user needing to re-brief every session.

Reading Memory

At session start, read memory/user-profile.md and extract:

Product context — name, stage, core problem, business model, current bets
Stack — which tools are connected (issue tracker, docs, comms, analytics)
Working style — PRD format preference, verbosity, preferred frameworks
Stakeholders — names, roles, communication styles, sensitivities
Roadmap state — what's in Now/Next/Later, what's been decided and why
Open questions — unresolved assumptions and risks
Tracked risks — active risks with dates flagged
Lessons learned — retrospective outcomes from past initiatives

Apply context to personalize every response. If last_updated is more than 7 days ago, note it and prompt for a refresh.

Checking Staleness

After loading memory, check:

If last_updated > 7 days: "Your product context hasn't been updated in [N] days. What's changed?"
If any open_questions item is > 14 days old: "You flagged '[question]' [N] days ago. Is it resolved or still open?"
If any tracked_risks item is > 7 days old with status "open": "You flagged '[risk]' as a risk [N] days ago. Is it still active?"
If any roadmap_state.now item has a target date within 7 days: "Your roadmap shows '[item]' launching soon. Want to run /stakeholder-update?"

Surface at most 2 staleness prompts per session to avoid overwhelming the user.

Writing Memory

When the user asks to update memory (or agrees to after a session), edit memory/user-profile.md with the following rules:

Add, never replace blindly: Before updating a field, read its current value. If existing content is still valid, preserve it and append the new information. Don't overwrite unless the user explicitly wants to replace.

Date every new entry: All items in open_questions, tracked_risks, lessons_learned, and decided_and_why must include the date added.

Resolve, don't delete: When a risk is resolved or a question is answered, update its status and add a resolution note — don't remove the entry. This preserves institutional knowledge.

Always update last_updated: Set it to today's date (ISO format) after every write.

What to Capture Per Session Type

After /write-prd:

Add to decided_and_why: the core decision the PRD represents (what are we building and why)
Add to open_questions: any unresolved questions from the Open Questions section
Add to tracked_risks: any risks identified in the Dependencies & Risks section
Update roadmap_state.now or roadmap_state.next if this PRD is for an active initiative

After /roadmap:

Overwrite roadmap_state with the updated Now/Next/Later
Add to decided_and_why any prioritization decisions made
Add to tracked_risks any pre-mortem risks that were surfaced
Add to open_questions any dependencies that are unresolved

After /stakeholder-update:

Update the stakeholder's last_contact date in the stakeholders section
Add to decided_and_why any decisions that surfaced during update preparation
Update initiative status in roadmap_state

After /synthesize-research:

Update the relevant persona section with any new signals
Add to open_questions any questions the research raised but didn't answer
Add potential new roadmap items to roadmap_state.later
Add to lessons_learned if the research confirmed or invalidated a past assumption

After Gossip Mode (informal updates):

Parse the informal update and extract: new stakeholder context, roadmap changes, risks surfaced, decisions made
Add extracted items to the appropriate sections
Confirm the parsed update with the user before writing

Gossip Mode Parsing

When the user speaks informally (voice-to-text style, or "you won't believe what just happened..."), parse and extract structured memory updates:

Look for:

People + opinions: "[Name] said [X]" → potential stakeholder note
Blockers: "[X] is blocked because [Y]" → tracked risk candidate
Decisions: "We decided to [X]" → decided_and_why candidate
Product changes: "We're not doing [X] anymore" → roadmap state update
Customer signals: "[Customer] complained about [X]" → potential open question or persona note
Timeline shifts: "[Item] is slipping to [date]" → roadmap state update

After parsing, show the user what you extracted and confirm before writing to the profile.

Memory Schema Reference

Refer to memory/schema.md for the full field definitions and update rules.

Frequently asked questions

What does the Memory AI skill do?

Why use Memory on TypingMind?

Because you install it once and use it with any model. Memory is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Memory in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Productfculty-aipm/PM-Copilot-by-Product-Faculty/tree/main/skills/memory. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Memory?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Memory?

As many as you like. As long as a model supports skills, you can use Memory with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Memory AI skill free?

It is published on GitHub by Productfculty-aipm. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Faiss

NousResearch

OrganizationPopular

Fast vector similarity search at billion scale.

Serving Llms Vllm

vLLM: high-throughput LLM serving, OpenAI API, quantization.

Huggingface Hub

HuggingFace hf CLI: search/download/upload models, datasets.

Pytorch Lightning

Clean training loops with built-in distributed support.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Memory Layer — Persistent PM Context

Reading Memory

Checking Staleness

Writing Memory

What to Capture Per Session Type

Gossip Mode Parsing

Memory Schema Reference

Frequently asked questions

Related AI Skills

Set up your own AI workspace now