# Session end Human Guide

## What This Is For
End-of-session capture: knowledge-base daily log, memory mirroring, candidate surfacing. It gives the agent a clearer input/output frame for session end: what context to ask for, what decisions to make, and what usable artifact to return.

Use this as a human-readable version of the Session end agent skill. It is meant for marketers, operators, founders, and other non-coders who want the workflow without reading agent-specific implementation instructions.

## When To Use This
- Use this when you need a repeatable process for session end.
- Use this when the task needs judgment, examples, constraints, or a clear output format rather than a one-off prompt.
- Use this when you want to hand an AI assistant enough context to produce a usable marketing artifact.

## When Not To Use This
- Do not use this when you only need a quick factual answer.
- Do not use this when the work depends on private data you cannot share with the assistant.
- Do not use this as a replacement for legal, compliance, financial, or medical review.

## What You Need Before Starting
- The goal or business outcome you want.
- The audience, customer segment, or market context.
- Any source material the assistant should respect, such as notes, briefs, examples, URLs, or brand guidance.
- Constraints such as tone, length, channel, deadline, region, or approval requirements.
- A clear definition of what a good final answer should look like.

## Step-By-Step Workflow
1. State the job clearly: "Use the Session end guide to help me with..."
2. Add context: audience, goal, offer, channel, source material, and constraints.
3. Ask the assistant to identify missing inputs before producing the final output.
4. Have the assistant follow the skill-specific guidance below.
5. Review the result against the final checklist and ask for revisions where needed.

## Skill-Specific Guidance
- **Key levers moved:** 1-3 decisions or strategic shifts that matter
- **Open loops:** blockers, pending items carrying forward
- **Next focus:** priority for next session
- **Projects touched:** for knowledge-base links
- **People mentioned:** for knowledge-base links
- Add it to the matching domain map-of-content (MOC) index.
- Make sure the daily-log block forward-links it under Projects touched or a References touched line.
- The memory index stays small; one line per file, kept short
- Check for existing memory before creating new
- Update the index when files are added or removed
- Decision logged with explicit rationale
- New or updated `feedback_*` file

## Decision Points And Nuance
The original skill emphasizes: How this skill relates to a memory plugin, Step 1: Gather curated session context, Step 2: Daily log (primary record), [HH:MM], [workspace], [Brief title], Step 3: Thin local pointer, [HH:MM], [Brief title], Step 4: Update agent state, Step 5: Memory files + knowledge-base mirror, Step 6: Candidate detection, [YYYY-MM-DD workspace] {short title}.

Use these questions to steer the work:
- What is the intended audience or buyer?
- What source material must be preserved?
- What should the assistant optimize for: clarity, persuasion, accuracy, speed, creativity, or conversion?
- What examples represent the desired quality bar?
- What should the assistant avoid?

## Common Mistakes
- Don't narrate the whole session, the memory plugin has that. Extract:
- **Connect it, don't just drop it.** After writing a mirror, link it so it is not an orphan:
- User said "remember this," "important," or "worth noting"
- Apply mechanical AI-tell strips only (no em dashes); never rephrase the quote.
- **Never re-synthesize the full session narrative.** The memory plugin has the semantic summary. Extract key levers only.
- **Never auto-write permanent voice notes.** Those are the user's voice only, via a dedicated promotion pass.
- **Never auto-edit the MOC index files.** That is a separate synthesis step.
- **Never rephrase memory file content when mirroring.** Verbatim copy preserves voice.

## Copy-And-Paste Prompt
```text
Use the Session end human guide.

My goal:
[Describe the business outcome]

Audience:
[Describe who this is for]

Context and source material:
[Paste notes, examples, links, or existing copy]

Constraints:
[Tone, length, channel, timeline, must-include items, must-avoid items]

Before producing the final output, ask me for any missing information that would materially improve the result.
```

## Final Checklist
- [ ] The output matches the original goal.
- [ ] The audience and context are reflected in the answer.
- [ ] Important constraints and source material were preserved.
- [ ] The assistant made the relevant decisions explicit.
- [ ] The final artifact is ready to use, review, or hand to the next person.

## Source
This guide was generated from the Marketing Engineering Podcast skill entry for `wispr-flow-session-end`.

## Source Skill Notes
These notes preserve the nuance from the original skill. Use them as supporting reference when the workflow above feels too generic.

# Session End: Knowledge Base Sync + Memory Capture

Captures curated learnings and mirrors them into a linked knowledge base (for example, an Obsidian vault organized Zettelkasten-style).

> Adapt the paths and tool names below to your own setup. This skill assumes a daily-log knowledge base, a cross-session memory layer, and an optional memory plugin. The `<vault>/` placeholder is wherever your knowledge base lives.

## How this skill relates to a memory plugin

A memory plugin (for example, Claude Mem) automatically generates a semantic session summary at session end and stores it in its own database. **This skill does not duplicate that synthesis.** Instead it captures *curated* signal: decisions that matter, memory updates, knowledge-base mirrors, and promotion candidates. The rich observation log stays in the memory plugin (query it with its search tool).

## Step 1: Gather curated session context

Don't narrate the whole session, the memory plugin has that. Extract:

- **Key levers moved:** 1-3 decisions or strategic shifts that matter
- **Open loops:** blockers, pending items carrying forward
- **Next focus:** priority for next session
- **Projects touched:** for knowledge-base links
- **People mentioned:** for knowledge-base links

## Step 2: Daily log (primary record)

Write or append to `<vault>/daily/YYYY-MM-DD.md`. Create the file if missing with frontmatter:

```yaml
---
type: session-log
date: YYYY-MM-DD
---
```

Append a block for this session:

```markdown
## [HH:MM], [workspace], [Brief title]

**Focus:** [one-line]

**Key levers:**
- [Decision or shift that matters]

**Open loops:**
- [Items carrying forward]

**Projects touched:** [[projects/slug-1]], [[projects/slug-2]]
**People:** [[name-1]], [[name-2]]

**Next focus:** [One line]

---
```

Keep it tight. If nothing moved, write one line: `No significant levers, routine execution session.`

## Step 3: Thin local pointer

Append a short pointer to your local session log at `logs/sessions/YYYY-MM-DD.md` so a weekly review tool can still find it without re-synthesizing what the memory plugin already stored:

```markdown
## [HH:MM], [Brief title]

**Focus:** [one-line]

**Key levers:**
- [Top 1-3 items, verbatim copy from the daily log above]

**Next:** [Next focus]

_(Full session history in the memory plugin. Curated atoms live in the knowledge base.)_

---
```

## Step 4: Update agent state

Resolve the current user, then update the per-user state file (NOT the shared one):

```json
{
  "last_updated": "YYYY-MM-DD",