memory

Name: memory
Author: Productfculty-aipm

70stars33forks

How to install memory?

productfculty-aipm/pm-copilot-by-product-faculty/memory

$npx -y skills add Productfculty-aipm/PM-Copilot-by-Product-Faculty --skill memory

Installs into the current project.

Summary

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"

Files · 1

View on GitHub

SKILL.md

1	# Memory Layer — Persistent PM Context
2
3	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.
4
5	## Reading Memory
6
7	At session start, read `memory/user-profile.md` and extract:
8
9	1. Product context — name, stage, core problem, business model, current bets
10	2. Stack — which tools are connected (issue tracker, docs, comms, analytics)
11	3. Working style — PRD format preference, verbosity, preferred frameworks
12	4. Stakeholders — names, roles, communication styles, sensitivities
13	5. Roadmap state — what's in Now/Next/Later, what's been decided and why
14	6. Open questions — unresolved assumptions and risks
15	7. Tracked risks — active risks with dates flagged
16	8. Lessons learned — retrospective outcomes from past initiatives
17
18	Apply context to personalize every response. If `last_updated` is more than 7 days ago, note it and prompt for a refresh.
19
20	## Checking Staleness
21
22	After loading memory, check:
23	- If `last_updated` > 7 days: "Your product context hasn't been updated in [N] days. What's changed?"
24	- If any `open_questions` item is > 14 days old: "You flagged '[question]' [N] days ago. Is it resolved or still open?"
25	- 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?"
26	- If any `roadmap_state.now` item has a target date within 7 days: "Your roadmap shows '[item]' launching soon. Want to run /stakeholder-update?"
27
28	Surface at most 2 staleness prompts per session to avoid overwhelming the user.
29
30	## Writing Memory
31
32	When the user asks to update memory (or agrees to after a session), edit `memory/user-profile.md` with the following rules:
33
34	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.
35
36	Date every new entry: All items in `open_questions`, `tracked_risks`, `lessons_learned`, and `decided_and_why` must include the date added.
37
38	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.
39
40	Always update `last_updated`: Set it to today's date (ISO format) after every write.
41
42	## What to Capture Per Session Type
43
44	After /write-prd:
45	- Add to `decided_and_why`: the core decision the PRD represents (what are we building and why)
46	- Add to `open_questions`: any unresolved questions from the Open Questions section
47	- Add to `tracked_risks`: any risks identified in the Dependencies & Risks section
48	- Update `roadmap_state.now` or `roadmap_state.next` if this PRD is for an active initiative
49
50	After /roadmap:
51	- Overwrite `roadmap_state` with the updated Now/Next/Later
52	- Add to `decided_and_why` any prioritization decisions made
53	- Add to `tracked_risks` any pre-mortem risks that were surfaced
54	- Add to `open_questions` any dependencies that are unresolved
55
56	After /stakeholder-update:
57	- Update the stakeholder's `last_contact` date in the stakeholders section
58	- Add to `decided_and_why` any decisions that surfaced during update preparation
59	- Update initiative status in `roadmap_state`
60
61	After /synthesize-research:
62	- Update the relevant persona section with any new signals
63	- Add to `open_questions` any questions the research raised but didn't answer
64	- Add potential new roadmap items to `roadmap_state.later`
65	- Add to `lessons_learned` if the research confirmed or invalidated a past assumption
66
67	After Gossip Mode (informal updates):
68	- Parse the informal update and extract: new stakeholder context, roadmap changes, risks surfaced, decisions made
69	- Add extracted items to the appropriate sections
70	- Confirm the parsed update with the user before writing
71
72	## Gossip Mode Parsing
73
74	When the user speaks informally (voice-to-text style, or "you won't believe what just happened..."), parse and extract structured memory updates:
75
76	Look for:
77	- People + opinions: "[Name] said [X]" → potential stakeholder note
78	- Blockers: "[X] is blocked beca

People who liked this also viewed

6 picks

Type

memory

70stars33forks

View on GitHub

How to install memory?

productfculty-aipm/pm-copilot-by-product-faculty/memory

$npx -y skills add Productfculty-aipm/PM-Copilot-by-Product-Faculty --skill memory

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Memory Layer — Persistent PM Context
2
3	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.
4
5	## Reading Memory
6
7	At session start, read `memory/user-profile.md` and extract:
8
9	1. Product context — name, stage, core problem, business model, current bets
10	2. Stack — which tools are connected (issue tracker, docs, comms, analytics)
11	3. Working style — PRD format preference, verbosity, preferred frameworks
12	4. Stakeholders — names, roles, communication styles, sensitivities
13	5. Roadmap state — what's in Now/Next/Later, what's been decided and why
14	6. Open questions — unresolved assumptions and risks
15	7. Tracked risks — active risks with dates flagged
16	8. Lessons learned — retrospective outcomes from past initiatives
17
18	Apply context to personalize every response. If `last_updated` is more than 7 days ago, note it and prompt for a refresh.
19
20	## Checking Staleness
21
22	After loading memory, check:
23	- If `last_updated` > 7 days: "Your product context hasn't been updated in [N] days. What's changed?"
24	- If any `open_questions` item is > 14 days old: "You flagged '[question]' [N] days ago. Is it resolved or still open?"
25	- 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?"
26	- If any `roadmap_state.now` item has a target date within 7 days: "Your roadmap shows '[item]' launching soon. Want to run /stakeholder-update?"
27
28	Surface at most 2 staleness prompts per session to avoid overwhelming the user.
29
30	## Writing Memory
31
32	When the user asks to update memory (or agrees to after a session), edit `memory/user-profile.md` with the following rules:
33
34	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.
35
36	Date every new entry: All items in `open_questions`, `tracked_risks`, `lessons_learned`, and `decided_and_why` must include the date added.
37
38	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.
39
40	Always update `last_updated`: Set it to today's date (ISO format) after every write.
41
42	## What to Capture Per Session Type
43
44	After /write-prd:
45	- Add to `decided_and_why`: the core decision the PRD represents (what are we building and why)
46	- Add to `open_questions`: any unresolved questions from the Open Questions section
47	- Add to `tracked_risks`: any risks identified in the Dependencies & Risks section
48	- Update `roadmap_state.now` or `roadmap_state.next` if this PRD is for an active initiative
49
50	After /roadmap:
51	- Overwrite `roadmap_state` with the updated Now/Next/Later
52	- Add to `decided_and_why` any prioritization decisions made
53	- Add to `tracked_risks` any pre-mortem risks that were surfaced
54	- Add to `open_questions` any dependencies that are unresolved
55
56	After /stakeholder-update:
57	- Update the stakeholder's `last_contact` date in the stakeholders section
58	- Add to `decided_and_why` any decisions that surfaced during update preparation
59	- Update initiative status in `roadmap_state`
60
61	After /synthesize-research:
62	- Update the relevant persona section with any new signals
63	- Add to `open_questions` any questions the research raised but didn't answer
64	- Add potential new roadmap items to `roadmap_state.later`
65	- Add to `lessons_learned` if the research confirmed or invalidated a past assumption
66
67	After Gossip Mode (informal updates):
68	- Parse the informal update and extract: new stakeholder context, roadmap changes, risks surfaced, decisions made
69	- Add extracted items to the appropriate sections
70	- Confirm the parsed update with the user before writing
71
72	## Gossip Mode Parsing
73
74	When the user speaks informally (voice-to-text style, or "you won't believe what just happened..."), parse and extract structured memory updates:
75
76	Look for:
77	- People + opinions: "[Name] said [X]" → potential stakeholder note
78	- Blockers: "[X] is blocked beca

People who liked this also viewed

6 picks

Type