Claude Skill

foundation-meeting-recap

Produces a topic-segmented post-meeting summary for attendees with decisions highlighted and actions captured inline per topic (plus a consolidated action view at the end). Auto-populates topic skeleton from a sibling meeting-agenda when available and reconciles planned vs. actua

LLM Mart · 0 points · 4 0 0

Virus-scanned Reviewed automatically before listing.

Full trust report

Download product-on-purpose-pm-skills-skills_foundation-meeting-recap-d85a31b.zip · 12 KB

product-on-purpose/pm-skills 697 88 forks Apache-2.0 Updated 8d ago

Part of product-on-purpose/pm-skills — 27 skills

Install

skills CLI npx skills add https://github.com/product-on-purpose/pm-skills/tree/main/skills/foundation-meeting-recap

Claude Code

claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install product-on-purpose-pm-skills@llmmart

Git git clone https://github.com/product-on-purpose/pm-skills.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole product-on-purpose/pm-skills collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Files (pm-skills)

evals

trigger-fixtures.json 4.5 KB

{
  "schema": 1,
  "skill": "foundation-meeting-recap",
  "runs_per_query": 3,
  "trigger_threshold": 0.5,
  "queries": [
    {
      "q": "Write a recap of today's product sync with decisions highlighted and actions grouped by owner",
      "expect": "trigger",
      "split": "train"
    },
    {
      "q": "Here is the Otter transcript from our quarterly planning meeting; turn it into a topic-segmented summary for attendees",
      "expect": "trigger",
      "split": "train"
    },
    {
      "q": "Summarize this morning's standup-turned-debate so the team has the outcomes in writing",
      "expect": "trigger",
      "split": "train"
    },
    {
      "q": "We had the API deprecation meeting an hour ago; capture what was decided and who owes what by when",
      "expect": "trigger",
      "split": "train",
      "notes": "Intent-only phrasing, no recap keyword"
    },
    {
      "q": "Reconcile the agenda we planned against what we actually covered in the roadmap review, and list the actions",
      "expect": "trigger",
      "split": "train"
    },
    {
      "q": "Turn these messy notes from the pricing discussion into a clean summary the attendees can reference",
      "expect": "trigger",
      "split": "train"
    },
    {
      "q": "Generate the post-meeting summary from this Google Meet transcript, flagging actions that have no owner",
      "expect": "trigger",
      "split": "validation"
    },
    {
      "q": "After that two hour architecture meeting nobody remembers what we agreed; write it up",
      "expect": "trigger",
      "split": "validation",
      "notes": "Intent-only phrasing"
    },
    {
      "q": "Produce a recap of the launch go/no-go meeting with the decision bolded and follow-ups consolidated",
      "expect": "trigger",
      "split": "validation"
    },
    {
      "q": "Take the Fireflies transcript from the vendor evaluation call and give the team a topic-organized writeup",
      "expect": "trigger",
      "split": "validation"
    },
    {
      "q": "Synthesize the patterns across our 9 customer discovery interviews into insights and recommendations",
      "expect": "no-trigger",
      "split": "train",
      "near_miss_of": "discover-interview-synthesis",
      "notes": "Aggregating research conversations across participants is the partner's job"
    },
    {
      "q": "Aggregate what we heard in this round of usability tests into evidence-backed findings",
      "expect": "no-trigger",
      "split": "train",
      "near_miss_of": "discover-interview-synthesis",
      "notes": "Research session synthesis, not an internal meeting summary"
    },
    {
      "q": "These are transcripts from user research sessions with 7 participants; extract the cross-participant themes with quotes",
      "expect": "no-trigger",
      "split": "validation",
      "near_miss_of": "discover-interview-synthesis",
      "notes": "Transcript input tempts this skill, but multi-participant research belongs to synthesis"
    },
    {
      "q": "Identify trends across the last month of team meetings, not just one of them",
      "expect": "no-trigger",
      "split": "train",
      "near_miss_of": "foundation-meeting-synthesize",
      "notes": "Cross-meeting synthesis is out of scope for a single recap"
    },
    {
      "q": "Draft the agenda for next week's quarterly planning meeting with time-boxed topics",
      "expect": "no-trigger",
      "split": "train",
      "near_miss_of": "foundation-meeting-agenda",
      "notes": "Pre-meeting artifact, not post-meeting"
    },
    {
      "q": "Write an update on the project for execs who were not in the room",
      "expect": "no-trigger",
      "split": "validation",
      "near_miss_of": "foundation-stakeholder-update",
      "notes": "Non-attendee communication; recap assumes reader context"
    },
    {
      "q": "Help me prepare privately for tomorrow's tense roadmap negotiation: stakes, positions, and asks",
      "expect": "no-trigger",
      "split": "train",
      "near_miss_of": "foundation-meeting-brief"
    },
    {
      "q": "Debug why my Express server returns 502s behind nginx",
      "expect": "no-trigger",
      "split": "train",
      "notes": "Unrelated engineering ask"
    },
    {
      "q": "Write a SQL query listing meetings per attendee from this events table",
      "expect": "no-trigger",
      "split": "validation",
      "notes": "Unrelated; meeting keyword but a SQL task"
    },
    {
      "q": "Recommend a sci-fi novel similar to Project Hail Mary",
      "expect": "no-trigger",
      "split": "validation",
      "notes": "Unrelated"
    }
  ]
}

references

EXAMPLE.md 8 KB

---
artifact_type: meeting-recap
version: 1.0
generated_at: 2026-04-18T09:15:00Z
generated_by_skill: foundation-meeting-recap

meeting_title: "Search Feature Kickoff"
meeting_date: 2026-04-17
meeting_start_time: "14:00 EST"
meeting_type: project-kickoff

project: search-feature
topics:
  - scope
  - capacity
  - timeline

attendees:
  - name: jonathan
    role: decision-maker
  - name: maria
    role: contributor
  - name: alex
    role: contributor
  - name: sarah
    role: informed
attendees_absent: []

related_agenda: 2026-04-17_14-00EST_search-feature-kickoff_agenda.md
related_brief: 2026-04-17_14-00EST_search-feature-kickoff_brief.md

agenda_reconciliation:
  topics_planned: [scope, capacity, timeline, next-steps]
  topics_hit: [scope, capacity]
  topics_skipped: [timeline]
  topics_emerged: [vendor-contract-review]

meeting_quality:
  outcomes_achieved: "2/3"
  started_on_time: true
  ended_on_time: false
  key_attendees_present: true

input_quality: high
confidence: high
visibility: team
status: draft
---

# Meeting recap: Search Feature Kickoff

## Shareable summary

**Search Feature Kickoff** | 2026-04-17
Scope and capacity agreed; timeline deferred to a follow-up next week due to emergent vendor-contract question on the search provider.

**Key decisions**:
- MVP scope: autocomplete + filters IN; saved searches OUT (defer to v2)
- Q2 eng capacity: 8 sprint-weeks committed; alex owns staffing plan

**Top actions**:
- alex: publish sprint-week staffing plan (Due: 2026-04-24)
- maria: investigate vendor contract constraints on search provider (Due: 2026-04-22)
- jonathan: schedule follow-up for timeline commitment after vendor answer (Due: 2026-04-25)

**Full recap below**

---

## Full recap

### Meeting details

- **Date**: 2026-04-17
- **Actual duration**: 68 min (overran by 8 min)
- **Attendees present**: jonathan, maria, alex, sarah
- **Attendees absent**: none
- **Recording**: https://meet.example/search-kickoff/recording

### Overall summary

Agreed on MVP scope (autocomplete + filters in; saved searches deferred) and Q2 engineering capacity (8 sprint-weeks). Timeline commitment deferred to next week because an emergent question on the search-provider vendor contract needs resolution before a date can be committed. Meeting ran 8 minutes over due to the vendor-contract tangent.

### Agenda reconciliation

- **Planned topics**: scope, capacity, timeline, next-steps
- **Topics addressed**: scope, capacity (2 of 4)
- **Topics skipped**: timeline. deferred because vendor contract question blocks commitment; next-steps. absorbed into emergent vendor-contract discussion
- **Topics that emerged**: vendor-contract-review. alex raised a prior email from the search-provider indicating potential licensing limits on usage; needs investigation before timeline is committable

### Topics

#### Scope

*Type: Decision (from agenda)*

**Discussion**

Walked the scope draft together. Autocomplete and filters had clear customer-research backing; saved searches was the contested line. Agreed that saved searches solves a narrower user need and can be deferred without losing the MVP value prop.

**Decisions made**

- **MVP scope: autocomplete IN, filters IN, saved searches OUT (defer to v2)**. rationale: autocomplete + filters cover 80% of the research-identified user need; saved searches adds complexity (accounts, persistence) that costs Q2 engineering time without proportional customer-value gain

**Actions**

- [ ] maria: update scope doc to reflect decision; circulate for final sign-off by EOD Friday | Due: 2026-04-18 | Dependencies: none
- [ ] jonathan: add saved-searches to v2 backlog with rationale link | Due: 2026-04-18

**Open questions**

- None on scope itself; vendor contract issue (see below) may force scope reconsideration if licensing blocks autocomplete

---

#### Capacity

*Type: Decision (from agenda)*

**Discussion**

Alex walked the Q2 capacity model. 8 sprint-weeks available for search; no backfill needed if scope holds. Flagged that saved-searches would have required 3 additional sprint-weeks, reinforcing the scope decision.

**Decisions made**

- **Q2 engineering capacity: 8 sprint-weeks committed to search feature**. rationale: fits within scope agreed in prior topic; no backfill required

**Actions**

- [ ] alex: publish detailed sprint-week staffing plan (who, which sprint) | Due: 2026-04-24
- [ ] alex: flag dependencies on design-system team if any emerge | Due: 2026-04-24

**Open questions**

- None

---

#### Vendor-contract-review (emergent)

*Type: Discussion (emergent. not on agenda)*

**Discussion**

Alex surfaced a prior email from the search-provider (Algolia) indicating possible licensing limits on query volume at our projected usage. Raised concern that if limits trigger, we could be forced to renegotiate or re-architect. Decision was to investigate before committing to a ship timeline.

**Decisions made**

- **Defer timeline commitment until vendor contract is reviewed** [confidence: high]. rationale: committing a date before vendor-licensing risk is known would create rework

**Actions**

- [ ] maria: investigate vendor contract constraints (read licensing terms; query legal if needed) | Due: 2026-04-22 | Dependencies: legal review if terms are ambiguous
- [ ] jonathan: schedule 30-min follow-up for the week of 2026-04-21 once maria has vendor answer | Due: 2026-04-25

**Open questions**

- Does vendor licensing support our projected Q2 query volume? [confidence: high. specific question]
- If limits apply, are they negotiable or hard? [confidence: medium. depends on legal review]

---

### All actions (consolidated by owner)

#### maria

- [ ] Update scope doc to reflect decision; circulate for final sign-off | Due: 2026-04-18 | Topic: scope
- [ ] Investigate vendor contract constraints (licensing limits on query volume) | Due: 2026-04-22 | Topic: vendor-contract-review

#### alex

- [ ] Publish detailed sprint-week staffing plan | Due: 2026-04-24 | Topic: capacity
- [ ] Flag dependencies on design-system team if any emerge | Due: 2026-04-24 | Topic: capacity

#### jonathan

- [ ] Add saved-searches to v2 backlog with rationale link | Due: 2026-04-18 | Topic: scope
- [ ] Schedule 30-min follow-up for week of 2026-04-21 once vendor answer is in | Due: 2026-04-25 | Topic: vendor-contract-review

### Meeting quality signals

- **Outcomes achieved**: 2 of 3 stated outcomes met (scope, capacity; ship-date deferred pending vendor review)
- **Time management**: Started on time; ended 8 min over due to emergent vendor-contract discussion
- **Key attendee presence**: All attendees present; decision-maker (jonathan) engaged throughout

### Next steps

- **When we reconvene**: week of 2026-04-21 (30 min, narrow focus: vendor answer + timeline commitment)
- **What needs to happen first**: maria completes vendor contract investigation

---

## Sources & References

### Primary inputs

- Transcript: zoom-recording-2026-04-17 via Otter (68 min, speaker-attributed)
- jonathan's live notes (supplementary, used for context where transcript was ambiguous on speaker attribution)

### Referenced artifacts

- Agenda: 2026-04-17_14-00EST_search-feature-kickoff_agenda.md. used for topic skeleton and desired-outcomes reconciliation
- Brief: 2026-04-17_14-00EST_search-feature-kickoff_brief.md (consulted for stakeholder context)
- Prior recaps on this topic: none (this is a kickoff)

### External references

- [Scope draft](https://notion.example/search-scope)
- [Capacity model](https://sheets.example/q2-capacity)
- [Algolia licensing email (internal)](https://email.internal/algolia-licensing-2026-03-15)

### Generation context

- **Generated**: 2026-04-18T09:15:00Z
- **Skill version**: 1.0.0
- **Input quality**: high. transcript plus live notes; all speakers identifiable
- **Overall confidence**: high. decisions, actions, owners, dates all directly supported in transcript
- **Known gaps**: None identified
- **Inferences applied**: topic "vendor-contract-review" emerged during meeting and was not in agenda; labeled as emergent [confidence: high. explicit in transcript]
- **Fabrication check**: all action owners (maria, alex, jonathan) appear in attendees list; no unassigned actions

TEMPLATE.md 4.9 KB

---
artifact_type: meeting-recap
version: 1.0
generated_at: {{ISO 8601 timestamp}}
generated_by_skill: foundation-meeting-recap

meeting_title: "{{Meeting title}}"
meeting_date: {{YYYY-MM-DD}}
meeting_start_time: "{{HH:MM timezone}}"
meeting_type: {{type or null}}

project: {{project-slug or null}}
topics:
  - {{topic-slug}}

attendees:
  - name: {{name}}
    role: {{role or null}}
attendees_absent:
  - {{name}}

related_agenda: {{filename if exists, else null}}
related_brief: {{filename if exists, else null}}

agenda_reconciliation:
  topics_planned: [{{list from agenda or empty}}]
  topics_hit: [{{list}}]
  topics_skipped: [{{list or empty}}]
  topics_emerged: [{{list or empty}}]

meeting_quality:
  outcomes_achieved: "{{N/M or null}}"
  started_on_time: {{true | false | null}}
  ended_on_time: {{true | false | null}}
  key_attendees_present: {{true | false | null}}

meeting_type_source: {{explicit | inferred | null}}   # v1.1.0
unassigned_action_ratio: {{0.0 to 1.0}}               # v1.1.0. ratio of ownerless actions to total actions

input_quality: {{high | medium | low}}
confidence: {{high | medium | low}}
visibility: team
status: draft
---

# Meeting recap: {{Meeting title}}

## Shareable summary

> [guidance (v1.1.0 errata): 3-5 short lines, no mini-headers, Slack/email copy-safe. Lead with outcome, inline key decisions, inline top actions. Plain prose + simple bullets only. no nested markdown.]

**{{Meeting title}}** | {{Date}}
{{1-sentence accomplishment summary, optionally naming 1-2 key decisions inline.}}
Top actions: {{Owner 1}}: {{action}} ({{due}}); {{Owner 2}}: {{action}} ({{due}}); {{Owner 3}}: {{action}} ({{due}}).
{{if unassigned_action_ratio > 0.3 or any high-priority action unassigned:}} ⚠ {{N}} of {{M}} actions need owners. see Ownership reconciliation section.
Full recap linked below.

---

## Full recap

### Meeting details

- **Date**: {{Date}}
- **Actual duration**: {{Duration}} min
- **Attendees present**: {{Names}}
- **Attendees absent**: {{Names or "none"}}
- **Recording**: {{Link or "none"}}

### Overall summary

> [guidance: 2-3 sentences capturing what this meeting accomplished in plain language]

{{Summary text}}

### Agenda reconciliation

> [guidance: explicit report of what was planned vs. what actually happened. If no agenda existed, note "no prior agenda loaded"]

- **Planned topics**: {{list or "no agenda"}}
- **Topics addressed**: {{list}} ({{N}} of {{M}})
- **Topics skipped**: {{list or "none"}}. {{brief reason per skip}}
- **Topics that emerged**: {{list or "none"}}. {{brief context}}

### Topics

#### {{Topic 1}}

*Type: {{Discussion | Decision | Information | Working}} (from agenda, if available)*

**Discussion**

{{Summary of what was discussed}}

**Decisions made**

- **{{Decision 1}}**. {{brief rationale}}
- **{{Decision 2}}**. {{brief rationale}} [confidence: {{level}} if inferred]

**Actions**

- [ ] {{Owner}}: {{Action}} | Due: {{Date or "not specified"}} | Dependencies: {{any or "none"}}
- [ ] {{Owner or "unassigned"}}: {{Action}} | Due: {{Date or "not specified"}}

**Open questions**

- {{Unresolved question}} [confidence: {{level}}]

---

#### {{Topic 2}}

> [guidance: repeat structure]

---

### All actions (consolidated by owner)

#### {{Owner 1}}

- [ ] {{Action}} | Due: {{Date}} | Topic: {{Topic}}
- [ ] {{Action}} | Due: {{Date}} | Topic: {{Topic}}

#### {{Owner 2}}

- [ ] {{Action}} | Due: {{Date}} | Topic: {{Topic}}

#### Unassigned

- [ ] {{Action}} | Topic: {{Topic}} | **Needs owner**

### Meeting quality signals

> [guidance: lightweight signals supporting downstream retrospective use]

- **Outcomes achieved**: {{N of M or "no agenda outcomes to reconcile"}}
- **Time management**: {{brief note on start/end and pacing}}
- **Key attendee presence**: {{brief note on who was needed and whether they were there}}

### Next steps

- **When we reconvene**: {{Date or cadence}}
- **What needs to happen first**: {{Critical path items}}

---

## Sources & References

### Primary inputs

- {{Source type}}: {{Source name}} (e.g., "transcript via Otter, 48 minutes")
- {{Source type}}: {{Source name}} (e.g., "user live notes")

### Referenced artifacts

- Agenda: {{filename or "none loaded"}}. {{if loaded, note: used for topic skeleton and desired-outcomes reconciliation}}
- Brief: {{filename if applicable}}
- Prior recaps on this topic: {{filenames or "none"}}

### External references

- {{Links mentioned in meeting}}

### Generation context

- **Generated**: {{Timestamp}}
- **Skill version**: 1.0.0
- **Input quality**: {{high | medium | low}}. {{rationale}}
- **Overall confidence**: {{high | medium | low}}. {{rationale}}
- **Known gaps**: {{list of topics with insufficient detail, or "None identified"}}
- **Inferences applied**: {{list of inferred values with confidence, e.g., "decision on X inferred from 'let's go with X' [confidence: medium]"}}
- **Fabrication check**: {{"all action owners appear in attendees list or are explicitly unassigned" | or list of failures}}

HISTORY.md 3.4 KB

# foundation-meeting-recap - Version History

| Version | Date | Release | Effort | Type | Summary |
|---------|------|---------|--------|------|---------|
| 1.2.0 | 2026-08-08 | v2.32.0 | F-54 | minor | Project Memory Contract: writes stated decisions to the Decisions section and the recap as a decision artifact. |
| 1.1.0 | 2026-07-05 | v2.31.0 | WS-Z5 | minor | Reciprocal When NOT to Use pointers to `foundation-meeting-agenda` and `foundation-meeting-brief`; collision pairs declared with new trigger fixtures. |
| 1.0.3 | 2026-07-04 | v2.30.0 | M-35 | patch | Heading normalized to the skeleton-canon spelling ("Quality checklist" to "Quality Checklist"). |
| 1.0.2 | 2026-06-14 | - | C-5 | patch | Added reciprocal "When NOT to Use" body bullet pointing to discover-interview-synthesis (closes the C-5 reciprocity gap; 1.0.1 added only the description sentence) |
| 1.0.1 | 2026-06-10 | v2.26.0 | F-12-batch-0 | patch | Boundary sentence appended pointing to discover-interview-synthesis (2026-06-09 audit, v2.26.0 Batch 0) |
| 1.0.0 | 2026-04-17 | - | - | baseline | Prior published version |


## 1.2.0 (2026-08-08)

Released in v2.32.0. Effort: F-54 (memory-aware cohort, B2).

Adds a `## Project Memory Contract` section declaring what this skill reads from and appends to
`.claude/pm-skills.local.md`. Additive and inert: with no memory file the skill behaves exactly as
before. Writes are proposed for confirmation unless `memory_auto_append: true` is set.

### Changes
- Declared the project-memory read/write contract.
## 1.1.0 (2026-07-05)

Released in [v2.31.0](../../site/src/content/docs/releases/Release_v2.31.0.md). Effort: WS-Z5 (eval backfill wave 1, R-16).

The WS-Z5 fixture backfill declared both `foundation-meeting-agenda` and `foundation-meeting-brief` as new collision pairs for this skill in `scripts/trigger-eval-roster.yaml`, but neither reciprocal "When NOT to Use" pointer was added. The enforcing `check-reciprocal-boundary-pointers` gate caught both gaps. Adds one bullet pointing to `foundation-meeting-agenda` (pre-meeting structure) and one bullet pointing to `foundation-meeting-brief` (pre-meeting private prep), both distinguishing this skill's post-meeting scope. No other content change.

## 1.0.3 (2026-07-04)

Released in [v2.30.0](../../site/src/content/docs/releases/Release_v2.30.0.md). Effort: M-35 (trust repair sweep).

Heading-normalization sweep (WS-T8b): the 2026-07-04 deep audit found "Quality checklist" (lowercase c) as one of 11 catalog instances of the canon "Quality Checklist" heading drifting to a lowercase variant that evaded case-sensitive tooling. No content or behavior change.

## 1.0.2 (2026-06-14)

Reciprocity patch (C-5): added a "When NOT to Use" body bullet pointing to discover-interview-synthesis, the reciprocal of that skill's existing back-pointer. The 1.0.1 patch added only the description sentence; the C-5 reciprocal-boundary-pointer validator reads the body section, so the body bullet was still missing. Closing it lets the C-5 gate promote advisory -> enforcing. No template or behavior changes.

## 1.0.1 (2026-06-10)

Description-only patch (F-12 Batch 0, from the 2026-06-09 repo audit): one boundary sentence appended, pointing cross-participant research synthesis to discover-interview-synthesis. No body, template, or behavior changes.

## 1.0.0 (2026-04-17)

Baseline row for the prior published version; see git history for its changes.

SKILL.md 10.1 KB

---
name: foundation-meeting-recap
description: Produces a topic-segmented post-meeting summary for attendees with decisions highlighted and actions captured inline per topic (plus a consolidated action view at the end). Auto-populates topic skeleton from a sibling meeting-agenda when available and reconciles planned vs. actual topics. Accepts transcripts from Zoom, Meet, Otter, Fireflies, Krisp MCP, or manual notes; runs on variable-quality input without blocking. For synthesizing user research interviews across participants, use discover-interview-synthesis.
license: Apache-2.0
metadata:
  classification: foundation
  version: "1.2.0"
  updated: 2026-07-05
  category: meeting
  frameworks: [meeting-skills-family]
  author: product-on-purpose
---
<!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->
# Meeting Recap

A meeting recap is a post-meeting topic-segmented summary produced for attendees and light distribution. It organizes content by topic rather than chronology, highlights decisions visually, and captures actions inline (with owner, due date, dependencies) per topic segment, plus a consolidated actions view at the end for scannability.

This skill absorbs what would otherwise be a separate "meeting-actions" skill. Actions in this family live alongside the context that makes them meaningful, not in a sibling artifact.

This skill belongs to the Meeting Skills Family. It conforms to the [Meeting Skills Family Contract](../../docs/reference/skill-families/meeting-skills-contract.md).

## When to Use

- After any internal meeting that produces decisions or actions affecting attendees
- When a sibling `foundation-meeting-agenda` exists and needs reconciliation (planned vs. actual topics)
- When the team needs a topic-organized reference rather than a chronological transcript dump
- When inputs include a transcript (Zoom, Meet, Otter, Fireflies, Krisp MCP) or mixed notes and transcript

## When NOT to Use

- Setting the pre-meeting structure attendees will see (topics, owners, time boxes) before the meeting happens. Use `foundation-meeting-agenda`. recap summarizes what happened after a meeting; agenda sets expectations before it.
- Preparing the user's private strategic positioning before a meeting that matters. Use `foundation-meeting-brief`. recap is a shared post-meeting record; brief is pre-meeting tactical prep never shown to attendees.
- Communicating outcomes to non-attendees. Use `foundation-stakeholder-update`. recap assumes reader context; stakeholder-update translates to readers without it.
- Cross-meeting synthesis (patterns across multiple meetings). Use `foundation-meeting-synthesize`.
- Synthesizing user research interviews across participants, not one meeting's attendees. Use `discover-interview-synthesis`. recap organizes a single meeting by topic; interview-synthesis finds patterns across many research conversations.
- Live meeting note-taking. This skill consumes finished inputs; it does not transcribe live.

## Zero-friction execution

Per the family contract, this skill never blocks on interrogation. Default flow:

1. Read all provided inputs (transcript, notes, or hybrid) and note input quality upfront
2. Auto-discover related agenda via filename-prefix match on same-directory `*_{title}_agenda.md`
3. Run inference: meeting metadata from content, decisions from language markers, actions from imperative-future patterns, owners from attendee context
4. Present a brief inference summary and accept one-word `go` or corrections
5. Produce the recap

If invoked with `--go`, skip the inference summary. If the user provides all metadata upfront, no checkpoint appears.

## Fabrication prohibition

This skill never fabricates owners, decisions, or actions. When an action lacks an explicit owner, it is captured as `[owner: unassigned, needs confirmation]` not invented. When a decision is implicit ("it sounded like we decided X"), it is flagged with a confidence marker rather than stated as fact. Trust decay from fabrication is worse than the mild friction of flagging.

## Ownership reconciliation threshold (v1.1.0)

When the ratio of unassigned actions to total actions exceeds **0.3** (30%), OR when any high-priority action lacks an owner, the skill surfaces a dedicated `## ⚠ Ownership reconciliation required` section at the top of the recap (above the topic segments) listing:

- All unassigned actions
- A suggested next step for each (who should probably own this based on topic context, flagged as inference)
- A recommended follow-up action (Slack thread, 15-min sync, async survey)

The shareable summary also leads with this flag when triggered: `⚠ Ownership reconciliation required: N of M actions lack owners.`

The `unassigned_action_ratio` frontmatter field (float 0.0-1.0) records the ratio for downstream tools.

Rationale: a recap with 60% ownerless actions is "non-fabricated" (per the prohibition above) but operationally broken. a pile of broken tickets. The threshold makes this visible instead of silently shipping.

## Instructions

When asked to create a meeting recap, follow these steps:

1. **Parse inputs and detect type**
   Transcript (timestamped speaker-attributed lines), notes (bullet or prose), or hybrid. Note input quality upfront. transcript plus structured notes is high; scrappy bullets is low.

2. **Auto-discover related agenda**
   Look in the same directory for a file matching the pattern `{YYYY-MM-DD}_{HH-MMtimezone}_{title-slug}_agenda.md`. If found, load it. its topic list is the recap's topic skeleton and its `desired_outcomes` drive the meeting-quality reconciliation.

3. **Present go-mode inference summary**
   Show detected meeting date, title, attendees (if inferred), input quality assessment. Accept `go` or corrections.

4. **Topic-segment the content**
   - If agenda was loaded, use its topic list as scaffold (plus any emergent topics)
   - If no agenda, identify topics from transcript discourse markers ("moving on to", "the other thing")

5. **Per topic segment, extract**
   - **Discussion summary**: 2-3 sentences capturing what was discussed
   - **Decisions made**: bold-flagged visually. Never fabricate. if uncertain, flag "appears to have decided X [confidence: medium]"
   - **Actions**: owner + due date + dependencies. Flag missing owners as `[owner: unassigned]` and missing dates as `[due: not specified]`. Never invent.
   - **Open questions**: unresolved items with confidence marker on whether they are truly unresolved or simply not re-raised

6. **Consolidate actions by owner**
   Regroup all actions under each owner. Enables single-owner scan ("what do I owe after this meeting?").

7. **Reconcile agenda** (if agenda loaded)
   - `topics_planned`: from agenda topic list
   - `topics_hit`: topics actually discussed
   - `topics_skipped`: planned but not discussed, with brief reason
   - `topics_emerged`: discussed but not on agenda

8. **Assess meeting quality signals**
   - `outcomes_achieved`: N/M ratio of agenda `desired_outcomes` met (when agenda present)
   - `started_on_time` / `ended_on_time`: from timestamps when available; skipped when not
   - `key_attendees_present`: flag if decision-makers were absent

9. **Surface next steps**
   When we reconvene, what needs to happen on the critical path before that.

10. **Render TEMPLATE.md and validate**
    - Every action's owner appears in `attendees` or is explicitly `unassigned`
    - `meeting_quality.outcomes_achieved` matches `N/M` pattern when populated
    - `agenda_reconciliation` fields present even when empty lists

## Project Memory Contract

Active only when `.claude/pm-skills.local.md` exists. With no file, ignore this section entirely
and behave exactly as described above.

- **Reads:** `active_initiative`, so decisions are recorded against the initiative they belong to.
- **Writes:** each decision actually reached in the meeting to the `## Decisions` section, dated and attributed, plus the recap itself as a `decision` artifact.
- **Posture:** propose the entry and wait for confirmation before writing, unless
  `memory_auto_append: true` is set, in which case append and echo what was written.
- **Write discipline:** re-read the file immediately before writing, never from the copy that
  produced the proposal. If it changed in between, merge your entry into the current state and
  re-propose rather than overwriting; add only your own entry and leave every other field and
  section byte-identical. Nothing enforces this at runtime and the file is gitignored, so a
  careless whole-file write loses another session's work with no way to recover it.

The fabrication prohibition above governs this write without exception: record only decisions that were stated. An unrecorded decision is recoverable; an invented one in durable memory is not. This complements the family's filename-based chaining rather than replacing it: filenames still locate the sibling artifacts of one meeting, while project memory carries the durable product context across meetings.
## Quality Checklist

- [ ] Input quality flagged honestly (high / medium / low)
- [ ] Agenda auto-discovery attempted; result noted in Generation context
- [ ] Every topic segment has Discussion / Decisions / Actions / Open questions subsections
- [ ] Decisions are bold-flagged; never invented; confidence marked when inferred
- [ ] Every action has owner (or explicit `unassigned`) + due date (or explicit `not specified`)
- [ ] Consolidated actions view regrouped by owner
- [ ] Agenda reconciliation populated when agenda was loaded
- [ ] Meeting quality signals populated with data available; skipped fields flagged
- [ ] Shareable summary 5-6 lines, lead with decisions and top actions
- [ ] Sources and References Generation context notes transcript source and any missing owners/dates

## See also

- [Meeting Skills Family Contract](../../docs/reference/skill-families/meeting-skills-contract.md)
- [`foundation-meeting-agenda`](../foundation-meeting-agenda/SKILL.md). upstream: provides topic skeleton and desired-outcomes
- [`foundation-meeting-synthesize`](../foundation-meeting-synthesize/SKILL.md). downstream: consumes recaps for cross-meeting synthesis
- [`foundation-stakeholder-update`](../foundation-stakeholder-update/SKILL.md). downstream: translates recap outcomes to non-attendees