edit-speak
Skill1 starsChanged 58 days agoMITView on GitHub
Update an existing agent speech configuration without re-running engine setup. Check for existing configuration in this order: If neither file exists, inform the user: No speak configuration found. Run /setup-speak first to install a TTS engine and create an initial configuration. Otherwise, read the YAML frontmatter and display the current settings: Ask the user what they would like to adjust: Update the YAML frontmatter in the active configuration file. Keep existing comments and structure intact. Confirm the changes with a…
In this repository2 other files it gives its agents.
- setup-speakSkill
- speakSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 4 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 7
Update an existing agent speech configuration without re-running engine setup.
- Distinctive: line 11
Check for existing configuration in this order:
- Very specific: line 16
If neither file exists, inform the user: No speak configuration found.
- Distinctive: line 30
Ask the user what they would like to adjust:
- Distinctive: line 41
Update the YAML frontmatter in the active configuration file.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
Files
Update an existing agent speech configuration without re-running engine setup.
Step 1: Locate and Read Active Configuration
Check for existing configuration in this order:
./.speak.mdin the current repository root.~/.config/speak/config.mdin the user home directory.
If neither file exists, inform the user:
No speak configuration found. Run /setup-speak first to install a TTS engine and create an initial configuration.
Otherwise, read the YAML frontmatter and display the current settings:
Active Voice: <voice> (<engine>)
Tone: <tone>
Frequency: <frequency>
Volume Multiplier: <volume>Step 2: Prompt for Changes
Ask the user what they would like to adjust:
- Change Voice: Present available voices for the currently active engine. Offer to play a short preview if requested.
- Change Tone: Switch between
conversational,formal, orminimal. - Change Frequency: Switch between
completions-and-errors,all-milestones,errors-only, orsilent. - Volume Adjustment: Adjust audio gain (e.g. 1.0 for default, 1.5 for moderate boost, 2.5 for noisy environments).
- Toggle Task Triggers: Enable or disable speech for specific categories (builds, tests, reviews, research).
- Mute / Unmute: Temporarily set frequency to
silentor restore previous frequency.
Step 3: Write Updates and Confirm
Update the YAML frontmatter in the active configuration file. Keep existing comments and structure intact.
Confirm the changes with a short 1-sentence audible test using the updated settings, then report the updated configuration summary in text.
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
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.

