people-memory
Skill2 starsChanged 15 days agoMITView on GitHub
Maintains Obsidian Personal vault People profiles in `06 - People/` as persistent relationship memory during conversation. Use when any person is mentioned by full name, aliases, nicknames, or contextual references, or when the user asks to create or update a person profile.
We split this skill into the rules it gives an agent
11 rules. About 0 are common, 8 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Keep useful relationship memory in Obsidian People profiles without writing noise.
- Very specific: line 16
Search existing profiles under 06 - People/ by filename, aliases, known names, and relevant context.
- Very specific: line 18
Use Assets/Templates/t.people.md as the source template convention for new profiles.
- Distinctive: line 25
If creation or a prompt is needed, use TEMPLATES.md for the exact profile shape and question wording.
- Distinctive: line 26
Write only when allowed by the write gate.
- Distinctive: line 28
Run the QA checklist before responding.
- Distinctive: line 34
Write only when one of these is true:
- Distinctive: line 39
Do not write when:
- Distinctive: line 47
Ask one direct clarification question, then stop, when:
- Distinctive: line 62
Do not expose unrelated profile contents.
- Very specific: line 64
Do not read .omo/ runtime state for memory content, and do not edit .omo/.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
People Memory
Purpose
Keep useful relationship memory in Obsidian People profiles without writing noise. This skill is a concise entry point, with detailed matching, prompts, and QA kept in the companion docs.
Quick Start
- Trigger on any person mention, including full names, aliases, nicknames, and contextual references such as
my manager,my cousin, orthe founder I met last week. - Load REFERENCE.md before matching or updating.
- Search existing profiles under
06 - People/by filename, aliases, known names, and relevant context. - Decide whether the write gate passes before editing.
- Use
Assets/Templates/t.people.mdas the source template convention for new profiles. - Load QA.md before reporting completion after any write.
Core Workflow
- Detect the person mention or explicit create/update request.
- Match the person using REFERENCE.md, including confidence and contextual reference rules.
- If creation or a prompt is needed, use TEMPLATES.md for the exact profile shape and question wording.
- Write only when allowed by the write gate.
- Preserve existing profile structure and fields while making the smallest useful change.
- Run the QA checklist before responding.
Write Gate
Triggering is broad. Writing is narrow.
Write only when one of these is true:
- The user explicitly asks to create or update a person profile.
- The conversation adds new useful relationship memory, such as identity, contact details, role, company, alias, where-met context, preferences, commitments, follow-ups, or meaningful conversation notes.
Do not write when:
- The person is only mentioned in passing.
- The fact is already present in the matched profile.
- The information is vague, unresolved, or not useful as durable relationship memory.
Ask Instead Of Writing
Ask one direct clarification question, then stop, when:
- A name, alias, or nickname matches multiple plausible profiles.
- A contextual reference does not resolve to exactly one confident person.
- Creation is requested but the full name or one context clue is missing.
- The update would overwrite an existing
email,phone,linkedin, orcompanyvalue.
Output Contract
Return exactly one of these modes:
- Mini diff after write: name the profile path and summarize only the fields or notes changed.
- No-write response: say no write was made and give the short reason.
- One clarification question and stop: ask only what is needed to proceed.
Do not expose unrelated profile contents.
Do not read .omo/ runtime state for memory content, and do not edit .omo/.
References
- Load REFERENCE.md before matching, creating, or updating any profile.
- Load TEMPLATES.md when you need exact prompts, profile shape, or output wording.
- Load QA.md before reporting completion after a write.
In this repository48 other files it gives its agents.
- accessibilitySkill
- agent-instructionsSkill
- analyze-change-effectsSkill
- article-processingSkill
- ci-cd-automationSkill
- comment-styleSkill
- commitSkill
- communicate-clearlySkill
- compare-solutionsSkill
- create-project-instructionsSkill
- daily-meeting-updateSkill
- debugSkill
- deprecate-and-removeSkill
- design-code-structureSkill
- domain-searchSkill
- error-handlingSkill
- explain-codeSkill
- explain-decisionsSkill
- github-actionsSkill
- handoffSkill
- humanizeSkill
- issue-workflowSkill
- observabilitySkill
- performance-optimizationSkill
- planningSkill
- pr-followupSkill
- prototypeSkill
- pr-review-followupSkill
- pr-reviewSkill
- prSkill
- report-work-activitySkill
- retroSkill
- review-code-changesSkill
- simplify-codeSkill
- skill-maintenanceSkill
- stacked-prSkill
- task-breakdownSkill
- tddSkill
- teachSkill
- typescript-best-practicesSkill
- verification-authoringSkill
- verifySkill
- wayfinderSkill
- workflow-to-skillSkill
- work-modeSkill
- worktrunkSkill
- write-documentationSkill
- youtube-processingSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

