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

Voice Notes

ASecurity

Handle a voice note or audio attachment the hermit cannot read, and set up transcription when the operator wants it. Activates when a channel message carries an audio attachment (Telegram voice message, Discord voice-message.ogg), or on "can you understand voice notes", "transcribe my voice message", "set up voice notes".

74 stars
0 votes
0 copies
0 views
Added 9/20/2026
ai-agentsbashdocker

Works with

cli

Security Analysis

A100/100

Scanned 9/20/2026

$npx -y skills add gtapps/claude-code-hermit --skill voice-notes --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Voice Notes?

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

Security grade badge for Voice Notes
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/gtapps-voice-notes/badge)](https://www.skillsdirectory.com/skills/gtapps-voice-notes)

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: voice-notes
description: Handle a voice note or audio attachment the hermit cannot read, and set up transcription when the operator wants it. Activates when a channel message carries an audio attachment (Telegram voice message, Discord voice-message.ogg), or on "can you understand voice notes", "transcribe my voice message", "set up voice notes".
---
# Voice Notes

The channel plugin downloads the audio; the model cannot read it. Transcription is an operator choice, not a shipped default. The recipe lives in `${CLAUDE_PLUGIN_ROOT}/docs/voice-notes.md`; route to it, do not repeat it.

## Step 0 — Channel reply

If this skill was invoked from a channel-arrived message (the inbound prompt contains a `<channel source="...">` tag), reply via that channel's reply tool. Otherwise emit to conversation. On a channel-tagged turn, step 1's bounded ask also queues a durable micro-proposal entry via `proposal.ts queue-micro` (see `channel-responder` § Channel-safe ask bridge), so the answer re-enters this skill in a later turn instead of stranding the setup half-done.

## An audio attachment arrives

With no standing role covering it, reply: you received a voice note, you cannot listen to it yet, and you can set that up if they want. Do not guess at the content or ask them to retype it unless they decline setup.

## The operator asks to set it up

Read `.claude-code-hermit/config.json`: no channel with `enabled !== false` means no audio ever arrives (the Claude app transcribes before sending), so say so and stop.

Otherwise walk them through the doc from chat:

1. Settle one thing: should the audio stay on this machine, or is uploading it to a transcription provider acceptable? Self-hosted is the default. Then read only the matching doc section, self-hosted or hosted, plus its step 2.

   **Channel-tagged turn:** send the question via the reply tool, queue the bridge entry below, and stop. The answer comes back as a `--answer self-hosted` / `--answer hosted` re-entry, which skips the ask and resumes here.
   ```bash
   bun ${CLAUDE_PLUGIN_ROOT}/scripts/proposal.ts queue-micro .claude-code-hermit <<'HERMIT_MP'
   {"tier":1,"question":"Voice notes: should the audio stay on this machine, or is sending it to a transcription provider acceptable?","options":["self-hosted","hosted"],"on_resolve":"/claude-code-hermit:voice-notes setup --answer {answer}"}
   HERMIT_MP
   ```
2. Install: read `runtime_mode` from `.claude-code-hermit/state/runtime.json`. On `docker`, delegate to `/claude-code-hermit:docker-customize` with the tool the doc names; otherwise name the host install for the operator rather than running it yourself. A hosted provider needs its key in `.env`, never in the role text or `config.json`.
3. Role: save the standing role from the doc through the ordinary "remember" path, substituting the command they ended up with. Offer "for this channel" if they only want it in one chat.
4. Verify: have them send a voice note and confirm the reply addresses what they said.

On a prompting permission mode, mention the doc's allow rules after the first run raises an approval.

Attribution

gtappsgtapps
View sourceSee grades on GitHubMore from gtapps →
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 →