Skip to content
Skills Library
Personal productivity · Research

transcripted-search-memory

/transcripted-search-memory

Search Transcripted meeting and dictation history for what was said, when it happened, who mentioned it, where an idea came from, or how a topic changed over time. Use for memory, recall, provenance, timeline, source-finding, and "what did I say about" questions.

Licence
MIT
Last repository change
26.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
2
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 26.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Search Transcripted meeting and dictation history for what was said, when it happened, who mentioned it, where an idea came from, or how a topic changed over time. Use for memory, recall, provenance, timeline, source-finding, and "what did I say about" questions.

Triggers from the description

what did I say about
Original author description

Search Transcripted meeting and dictation history for what was said, when it happened, who mentioned it, where an idea came from, or how a topic changed over time. Use for memory, recall, provenance, timeline, source-finding, and "what did I say about" questions.

How it works

  1. Purpose
  2. Workflow
  3. Default Output
  4. Match Format
  5. Rules
  6. Quality Check
Original SKILL.md headings · 76 lines, 332 words
SKILL.md preview
---
name: transcripted-search-memory
description: Search Transcripted meeting and dictation history for what was said, when it happened, who mentioned it, where an idea came from, or how a topic changed over time. Use for memory, recall, provenance, timeline, source-finding, and "what did I say about" questions.
---

# Transcripted Search Memory

Version: 0.1.0

## Purpose

Find evidence across Transcripted meetings and dictations, then answer with source-backed memory. Search first, synthesize second.

## Workflow

1. Restate the query as a search target: topic, person, project, phrase, decision, action, or date range.
2. Prefer Transcripted MCP tools when available. Fall back to local meeting and dictation markdown files only when MCP is unavailable.
3. Combine available retrieval modes:
   - exact search
   - relevant context search
   - recency
   - date filters
   - people or speaker names
   - topic/project terms
4. Show the best matches before or alongside the answer.
5. Synthesize only from the evidence found.
6. If the topic appears over time, include a short timeline.
7. If evidence is thin or missing, say so plainly.

## Default Output

Use these sections when relevant:

```md
## Answer

## Best Matches

## Timeline

## Related Threads

## Confidence

## Sources

## Uncertainty
```

## Match Format

For each strong match, include as much of this as is available:

```md
- Source:
- Date:
- Speaker:
- Timestamp:
- Snippet:
- Why this surfaced:
```

## Rules

- Do not answer from vague memory when sources are available.
- Do not hide weak evidence. Use `low confidence` when matches are sparse, old, ambiguous, or conflicting.
- If nothing relevant is found, say `not found` and list what was searched.
- If the user asks for "when", prefer a timeline over a prose-only answer.
- If the user asks "where did this come from", prioritize the earliest strong source.
- Keep snippets short and cite the original capture instead of pasting large transcript chunks.

## Quality Check

Before answering, check:

- The answer has at least one source unless explicitly reporting no results.
- Important claims point to filenames, dates, speakers, or timestamps when available.
- Conflicting or evolving decisions are described as a timeline, not flattened into one claim.
- Search scope is clear enough that the user can ask a better follow-up.
Files in this package (2)
  • SKILL.md 2 KB
  • agents/openai.yaml 1 KB

Versions

The database has no other skills named transcripted-search-memory.

Database snapshot: 13.11.2026 · package version 3cf472b9a841 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100transcripted-summarize
    Create cited summaries, recaps, briefs, daily reviews, weekly reviews, and "what did I do" answers from Transcripted meetings and dictations. Use when the user asks to summarize one capture, a date range, a person, a project, a topic, or mixed meeting and dictation history.
  • 100minutes-search
    Search past meeting transcripts and voice memos for specific topics, people, decisions, or ideas. Use this whenever the user asks "what did we discuss about X", "find that meeting where we talked about Y", "what did Alex say", "did we decide on", "what was that idea about", or…
  • 95memory-search
    Search conversation history and semantic memory to recall previous discussions, decisions, and context. Use when the user asks to "search memory", "what did we discuss", "remember when", "find previous conversation", "check history", or before starting work to recall prior decisions.
  • 100recall
    Searching your old conversations with __OWNER__ and your diary. Load it when __OWNER__ asks about something from another day ("what did I tell you about…?", "when did we talk about…?", "that thing last week", a fact, price, link or decision that is not in your memory or in…
  • 90memory-recall
    Search the Obsidian vault for prior knowledge, decisions, and connections. Use for "do I have notes on", "what did I write or decide", "find in my vault", "what do I know about", or requests to connect topics using personal knowledge.
  • 100search
    Use when the user wants to find something across their Claude Code history — e.g. 'find where I discussed X', 'search for Y', 'when did I work on Z

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.