Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Wispr Setup

ASecurity

Connect Wispr Flow so meeting captures arrive in your vault on their own. Use when the user says 'connect Wispr', 'set up Wispr Flow', 'my Wispr meetings aren't in Dex'. Not for Granola; use `granola-setup`. Not for processing meetings already in the vault; use `process-meetings`.

489 stars
0 votes
0 copies
1 views
Added 9/24/2026
ai-agentspythongobash

Works with

claude codecursorclimcp

Security Analysis

A100/100

Scanned 9/24/2026

$npx -y skills add davekilleen/Dex --skill wispr-setup --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Wispr Setup?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Wispr Setup
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/davekilleen-wispr-setup-dex/badge)](https://www.skillsdirectory.com/skills/davekilleen-wispr-setup-dex)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: wispr-setup
description: "Connect Wispr Flow so meeting captures arrive in your vault on their own. Use when the user says 'connect Wispr', 'set up Wispr Flow', 'my Wispr meetings aren't in Dex'. Not for Granola; use `granola-setup`. Not for processing meetings already in the vault; use `process-meetings`."
integration:
  id: wispr
  name: Wispr Flow
  auth: oauth2
  credential: dex-held
  transport: remote-mcp
  enhances:
    - skill: process-meetings
      capability: "Wispr captures become meeting notes, person page updates and tasks"
    - skill: daily-plan
      capability: "Yesterday's captures are already in the vault before the day starts"
  entities: meetings, transcripts, calendar events
---

# Connect Wispr Flow

Wispr Flow records meetings and writes a summary. This connects it to Dex so
those captures arrive in `00-Inbox/Meetings/` by themselves, and `/process-meetings`
treats them exactly like any other meeting note.

## What makes this connection different, and why it matters to you

Dex holds the credential itself rather than borrowing one from whichever app you
happen to be running. That is the difference between a source that works while
you are sitting in a session and one that works overnight. Once connected:

- Captures can be fetched on a schedule, so they are in the vault before you
  open Dex in the morning.
- The connection follows the vault. It works the same in Claude Code, Cursor, or
  anything else that runs Dex, because nothing depends on that app's own
  connector store.

## Before you start

You need a Wispr Flow account with the notetaker enabled. There is no key to
paste and nothing to copy: you authorise once in a browser.

## Step 1: Run the connection

```bash
python3 -c "from pathlib import Path; from core.meeting_sources.wispr_setup import connect; print(connect(Path('.')))"
```

This registers Dex with Wispr, opens your browser, and waits for you to approve.
When you do, it stores the credential in `System/.dex/wispr-credential.json`
with owner-only permissions.

**If the browser does not open**, the command prints the URL. Open it yourself.

## Step 2: Confirm it worked

```bash
python3 -c "from pathlib import Path; from core.meeting_sources import wispr_client; print(wispr_client.list_tools(Path('.')))"
```

You should see the tools Wispr exposes. If this fails, say what the error was
rather than assuming the connection is fine.

## Step 3: Pull your recent captures

```bash
python3 -m core.meeting_sources.wispr_sync
```

It reports what it did in one line. Then run `/process-meetings` to turn the new
notes into person page updates and tasks.

## Step 4: Keep it running (optional)

To have captures arrive on their own, schedule the same command. On macOS that
is a launch agent running `python3 -m core.meeting_sources.wispr_sync` with
`VAULT_PATH` set to your vault.

## Two things to tell the user plainly

**Your captures may arrive without attendee names.** Wispr titles and attributes
a capture from the calendar it is connected to, and its calendar sync is Google
only. On Microsoft 365 the capture arrives with no title and no attendees, so
Dex derives a title from the summary and marks the note as unresolved. Speaker
labels in the summary are turns in a recording, not people. Do not let anything
downstream assign an action or a quote on the strength of that note alone;
match it against the calendar entry for that time first.

**The credential is in your vault.** `System/.dex/wispr-credential.json` holds a
refresh token. If your backups include `System/`, exclude that file, in the same
way `.env` is excluded. Anyone who can read it can read your meetings.

## If it stops working

Wispr's access tokens last five minutes and the refresh token is replaced every
time it is used, so the stored file is rewritten constantly. If the credential
is lost or corrupted, re-run Step 1: there is nothing to recover and
re-authorising takes one browser click.

Say plainly when the connection is broken. A meeting source that quietly returns
nothing looks exactly like a quiet week, and that is the failure this setup is
built to avoid.

Attribution

davekilleendavekilleen
View sourceSee grades on GitHubMore from davekilleen →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →