Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Vocal Session · farandclose | DecimalAI

agent toolingby farandclose

Vocal Session

farandclose/vocal

Source farandclose/speak-skills ↗License Not recorded

Use when the user invokes /vocal to enable auto-speak mode for the current session

SkillScore64Maintained

Automatic

Personal Assistant pack

Last verified 8/6/2026

What it changes

Passed 10 of 15 test cases with the skill, and 9 of 15 without it.

Without skill59%

With skill64%

Checks it passed that the model alone missed

The audio file path points to ~/.agent-speak/audio/.
The spoken narration text contains no markdown formatting.
The command redirects stdout and stderr output to /dev/null.

and 3 more in the full report

4 fixed10 passed either way5 still failing3 broke

Pass-rate lift: +5 pp
Tokens: -18%
Agent turns: 0%
Response time: -46%

Model gemini-3.6-flashMeasured 8/6/2026v114 of 22 cases passed with skill · 15 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/farandclose-vocal/SKILL.md https://app.decimal.ai/s/farandclose-vocal/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add farandclose-vocal, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/farandclose-vocal/ and pins it in .decimal/skills.lock

decimalai skills add farandclose-vocal

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/farandclose-vocal/SKILL.md https://app.decimal.ai/s/farandclose-vocal/SKILL.md

Raw file: /s/farandclose-vocal/SKILL.md ↗ · machine-readable summary at /s/farandclose-vocal.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 3

Prompt

Where are pre-generated audio mp3 files saved on disk during deferred narration sessions?

What was checked, without and with the skill
Checked	Without skill	With skill
The audio file path points to ~/.agent-speak/audio/.	Missed	Passed

case-18 · gemini-3.6-flash · 8/6/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md46 linessingle file

Vocal Session

Auto-speak mode is now active for this session.

Behavior

After each response, judge which mode applies:

Skip audio entirely

Brainstorming, Q&A, rapid back-and-forth where the agent is asking questions
Code output, file listings, diffs, tables
Quick confirmations ("Done", "Updated", "Fixed")
Tool-heavy responses with minimal prose

Deferred narration (all other narration-worthy responses)

Use for task completions, final answers, explanations, insights, analysis, summaries, recommendations.

Rewrite the response as spoken narration (under 150 words, no markdown, no code, conversational tone)
Pre-generate the audio in the background immediately using the speak skill's run.sh (located at ../speak/run.sh relative to this skill):

echo "narration text" | <speak-skill-directory>/run.sh &>/dev/null &

Append the narration text and a playback prompt to the response:

Narration Text:
--------------
<the narration text>

Hear it? (y)

If the user responds with y, play the most recent .mp3 from ~/.agent-speak/audio/:

# macOS

Track record

Benchmark

10 / 15

test cases passed, vs 9 / 15 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

farandclose / speak-skills

skills/vocal/SKILL.md

View on GitHub ↗

Imported 8/2/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Vocal Session

Behavior

Skip audio entirely

Deferred narration (all other narration-worthy responses)

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills