agentleFS
product-on-purposeproduct-on-purpose/pm-skills/skills/foundation-meeting-synthesize/SKILL.md

foundation-meeting-synthesize

Skill777 starsChanged 10 months agoApache-2.0View on GitHub

Cross-meeting archaeology skill. Consumes multiple meeting recaps (or raw notes) over a period and surfaces patterns invisible in any single meeting. Shows how decisions evolved, who has been saying what, where threads are stalling, and where contradictions have emerged. Produces a plain-text timeline, themes with confidence markers, stakeholder position tracking, consolidated decision list, contradiction flags, open items, narrative summary, and prioritized follow-ups.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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
  1. Distinctive:

    Run inference on themes, stakeholder evolution, contradictions

    line 43
  2. Very specific:

    If invoked with --go, skip the inference summary.

    line 48
  3. Distinctive:

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

    line 52
  4. Very specific:

    Read all provided recap filenames or note files.

    line 55
  5. Very specific:

    If time range, topic, or stakeholder filter provided, narrow the source set before proceeding.

    line 60
  6. Distinctive:

    Every theme has a confidence marker

    line 109
  7. Distinctive:

    Every contradiction has before/after source citations

    line 110

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->

Meeting Synthesize

Meeting synthesis is the archaeology skill for multi-meeting initiatives. It consumes a set of meeting recaps (and optionally raw notes) over a period, and surfaces patterns that no single meeting reveals: how decisions evolved, how stakeholder positions shifted, where threads are stalling, where contradictions have emerged.

Distinct from /discover-interview-synthesis: that skill works on user-research conversations with research-specific frameworks (jobs-to-be-done, buying insights). This skill works on internal org meetings with org-specific patterns (stakeholder alignment, decision evolution, project history).

This skill belongs to the Meeting Skills Family. It conforms to the Meeting Skills Family Contract.

When to Use

  • Board prep or exec-brief preparation across a meeting sequence
  • Onboarding a new team member into the history of an initiative
  • Project retrospective input (the story of how we got here)
  • Investigating why a multi-meeting initiative has stalled
  • Quarterly review of a topic that has crossed many meetings
  • Surfacing contradictions that no single-meeting reviewer caught

When NOT to Use

  • Single-meeting summary. Use foundation-meeting-recap instead.
  • Communicating outcomes outward. Use foundation-stakeholder-update.
  • User research conversation synthesis. Use discover-interview-synthesis.

Zero-friction execution

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

  1. Load all provided source files (recaps preferred, raw notes accepted with lower input-quality flag)
  2. Apply any filters (time range, topic, stakeholder)
  3. Run inference on themes, stakeholder evolution, contradictions
  4. Present a brief inference summary (meeting count after filter, time range detected, per-source input quality, scope filter applied)
  5. Accept go or corrections
  6. Produce the synthesis

If invoked with --go, skip the inference summary. Format hints (board-prep, onboarding, retro-input, exec-brief) control output presentation without changing the underlying process.

Instructions

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

  1. Load sources Read all provided recap filenames or note files. Parse frontmatter to extract meeting metadata. Note per-source input quality (recap frontmatter's input_quality if available; otherwise assess from content).

    Metadata source tracking (v1.1.0): for each recap, also note the meeting_type_source field (explicit | inferred | null). When synthesizing across mixed sources, the synthesis must document the mix explicitly in the Scope section: "meeting_type values: N explicit, M inferred, K null." This prevents non-reproducible results when filtering by meeting_type across a mix of confidence levels. If filtering by meeting_type, state whether the filter includes inferred values and how null values are handled.

  2. Apply filters If time range, topic, or stakeholder filter provided, narrow the source set before proceeding. Record the filter applied in frontmatter scope_filter.
  3. Present go-mode inference summary Meeting count after filter, time range detected from source metadata, per-source input quality levels, scope filter description.
  4. Build the plain-text timeline Chronological order by meeting_date. Each entry shows date, meeting name, key decision or shift, and confidence or contradiction flag if applicable. Render as markdown (no binary images. must render everywhere).
  5. Extract themes Cluster recurring topics across sources. For each theme, record description, sources where it appeared, and confidence marker tied to frequency ("appears in 5/5 meetings" → high; "appears in 2/5 meetings" → medium; "mentioned in 1 meeting" → low).
  6. Track stakeholder positions For each named stakeholder across sources, record initial position → current position, alignment state (aligned / divergent / shifting), and key statements with dates. Flag confidence on each position based on whether it was direct-quoted or paraphrased.
  7. Consolidate decisions Cross-meeting, sorted chronologically. Table format: Date | Decision | Context | Meeting | Confidence.
  8. Separate decision evolution from unresolved contradictions (v1.1.0) Two distinct outputs, not one combined "contradictions" section:

    • Decision evolution (resolved): earlier decision → later decision on the same topic, where the later one supersedes. This is historical context, not a red flag. No ⚠ emphasis.
    • Unresolved contradictions: decisions or positions currently in conflict that need reconciliation. Use ⚠ visual emphasis. For each:
      • Earlier reference (meeting + date + decision)
      • Later reference (meeting + date + decision that conflicts)
      • Status: unresolved / needs reconciliation

    The distinction matters because v1.0.0 conflated them, creating false-positive "contradictions" in exec contexts where the "contradiction" was actually intentional scope evolution.

  9. Identify open items and stalled threads Topics surfacing 2+ times without resolution. When they last appeared.
  10. Draft narrative summary 2-3 paragraphs: what happened, what changed, where we are, what is at stake. The "story" of the meeting set.
  11. Prioritize follow-up suggestions
    • High: unblocking now; suggested owner or forum
    • Medium: important but not blocking
    • Low: monitor Each with rationale.
  12. Apply format hint (if provided) One process generates the full synthesis data. The hint controls section ordering and truncation for the specific use case:
    • board-prep: lead with narrative + contradictions + prioritized follow-ups; shorter timeline
    • onboarding: lead with narrative + stakeholder tracking; full timeline
    • retro-input: lead with themes + stalled threads + meeting-quality aggregate
    • exec-brief: TL;DR + top 3 items only
  13. Render TEMPLATE.md and validate
    • source_meetings list is non-empty
    • time_range.start ≤ time_range.end
    • Every theme has a confidence marker
    • Every contradiction has before/after source citations
    • At least 1 prioritized follow-up

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 and prior interpretation artifacts on the same topic, so the synthesis shows movement rather than restating what is already recorded.
  • Writes: the synthesis as an interpretation 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.

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

  • Source meetings listed with filename + date + per-source input quality
  • Time range populated and sensible
  • Scope filter described (or "none applied")
  • Timeline is plain-text markdown (no binary images)
  • Themes include confidence markers tied to frequency
  • Stakeholder position tracking shows evolution (initial → current), not just snapshot
  • Consolidated decision list is chronological with source citations
  • Contradictions are flagged in their own first-class section (not buried)
  • Narrative summary is 2-3 paragraphs, not bullets
  • Follow-ups are prioritized (High / Medium / Low) with rationale
  • Frontmatter omits single-meeting fields (meeting_title, meeting_date, etc.)
  • Sources and References weights input quality across sources

See also

  • Meeting Skills Family Contract
  • foundation-meeting-recap. upstream: primary input source
  • /discover-interview-synthesis. sibling pattern for user-research conversations (different domain)

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.