alber70g/skills

notify-user

Speak a short local notification when a task finishes, work is blocked, or the user needs to make a decision, using the installed notify-user script on macOS.

Vedi sorgente

Come usare

  1. Copia il comando e controlla il pacchetto prima di installarlo nel tuo ambiente agente.
  2. Controlla strumenti, credenziali e ambienti richiesti nel documento originale.
  3. Descrivi input e risultato desiderato; confronta l’output con le fonti.
npx skills add https://github.com/alber70g/skills --skill notify-user

Prima di iniziare

  • L’installazione non include abbonamenti, quote API o accesso ai file.
  • Stelle e installazioni indicano attività, non un test indipendente di qualità o sicurezza.
Documento Skill originale

Contenuto dal repository con titoli, esempi, codice, tabelle, link e immagini preservati.

Notify User

Use spoken notifications when the user's attention helps: after substantial work or a milestone, when waiting for input or review, or when a blocker requires their help. For long unattended work, announce a meaningful phase change. Skip routine tool updates and fast back-and-forth conversation when the user is already watching.

Check that $HOME/.codex/notify-user.ts exists and Bun and soprano-webui are available. If either is missing, read references/installation.md, which includes setup instructions and links to the executable files. Do not claim a notification succeeded if the command failed.

Compose one short sentence, two for a blocker. Name the project, say what happened, and state the decision, review, or awareness needed. Spell spoken acronyms with spaces, such as “A P I” or “M C P”. Speak only the context needed to bring the user back to the task.

sh
"$HOME/.codex/notify-user.ts" --text "In the skills project, the notification skill is ready for your review." >/tmp/notify-user.log 2>&1 &

The script also accepts --project "Project Name", repeatable --did "work completed", and repeatable --need "help needed" to construct a message. Prefer --text for natural wording. Use --help to inspect the installed interface.

Use Soprano, the default backend. The user prefers its voice; do not silently substitute macOS speech when Soprano is missing or broken. Read the installation reference to set up or repair Soprano. Use --backend say only when the user explicitly requests built-in speech. The first Soprano call can take up to three minutes while the server starts and the model downloads, so send routine notifications in the background. For setup verification, run in the foreground and inspect its exit status.

Keep the ordinary written response: speech supplements it. Avoid duplicate notifications when an existing completion hook already covers the same event.

Correlati per attività

dallo stesso repository

Altri Skills

Tutti gli Skills
alber70g
Community

general-guidelines

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, define verifiable success criteria, keep a WORKLOG.md so work can be continued across sessions, and write research to research/ and plans for review to docs/.

Installazioni / 1h
2
GitHub Stars
0
Aggiornato
18 ott
alber70g
Community

orchestrator

Session mode where the main thread orchestrates: subagents on a cheaper model do research and execution, the main thread plans and validates. Use when the user runs /orchestrator, asks you to act as an orchestrator, asks to keep the main thread token-efficient, requests a large implementation plan or a large research task, or wants you to work toward an overarching goal.

Installazioni / 1h
1
GitHub Stars
0
Aggiornato
18 ott
alber70g
Community

turn-based-discovery

Use the AskUserQuestion tool (the same multiple-choice mechanism plan mode uses) to get clarity from the user. Each question is multiple-choice plus a free-format "Other" escape. Ask in small batches — up to 4 questions per call (the tool's max), more if needed across calls. Use when scoping work, resolving ambiguity, or surfacing answers a research pass already raised. Triggers: /turn-based, ask me, clarify, discovery mode, interview me.

Installazioni / 1h
2
GitHub Stars
0
Aggiornato
18 ott
alber70g
Community

autoresearch

Autonomous experimentation skill — agent interviews the user, sets up a lab, then explores freely (think, test, reflect) until stopped or a target is hit. Works for any domain where you can measure or evaluate a result.

Installazioni / 1h
1
GitHub Stars
0
Aggiornato
18 ott