SA

say-to-clip-maintenance

Manages configuration and maintenance for the dictation tool.

Install

mkdir -p .claude/skills/say-to-clip-maintenance && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12638" && unzip -o skill.zip -d .claude/skills/say-to-clip-maintenance && rm skill.zip

Installs to .claude/skills/say-to-clip-maintenance

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Use when editing or reviewing this repository's say_to_clip Bash dictation pipeline, provider configuration, privacy behavior, runtime files, transcript cleanup, clipboard handling, or README/brief guidance for those features.
226 chars✓ has a “when” trigger
Intermediate

Key capabilities

  • Maintain the `say_to_clip` Bash dictation pipeline.
  • Update provider configurations.
  • Manage privacy behaviors for runtime files.
  • Handle transcript cleanup and clipboard operations.
  • Preserve the hotkey flow for dictation.

How it works

The skill guides maintenance tasks for the `say_to_clip` project, ensuring changes adhere to project shape and maintenance rules, including privacy and hotkey flow.

Inputs & outputs

You give it
Changes to `say_to_clip` configuration or scripts.
You get back
Updated `say_to_clip` functionality, configuration, or documentation.

When to use say-to-clip-maintenance

  • Updating dictation config
  • Maintaining CLI scripts
  • Managing API provider settings

About this skill

say_to_clip Maintenance

This repo is a DIY/reference Linux dictation project, not a packaged product. Keep changes plain, inspectable, and easy to adapt.

Project Shape

  • say_to_clip is the main Bash implementation.
  • say_to_clip.env.example documents safe config defaults.
  • smoke-test validates the live configured provider path.
  • README.md, CONTRIBUTING.md, and local-dictation-agent-brief.md set the project framing.
  • ollama-manager is only a Docker helper for local Ollama.

Maintenance Rules

  • Preserve the hotkey flow: toggle starts recording when idle and stops, transcribes, cleans, and copies when recording.
  • Preserve explicit commands: start, stop, toggle, status, transcribe FILE, and help.
  • Keep provider selection split-friendly: DICTATE_PROVIDER, DICTATE_TRANSCRIBE_PROVIDER, and DICTATE_CLEAN_PROVIDER.
  • When adding config, update CONFIG_ENV_NAMES, defaults in say_to_clip, usage, and say_to_clip.env.example together.
  • Preserve env precedence: command environment overrides survive loading ~/.config/say_to_clip/env.
  • Use jq for JSON payload construction/parsing; avoid hand-built JSON.
  • Keep Groq API keys out of visible command arguments; use temporary curl config files or another non-leaky mechanism.
  • Keep runtime files private: umask 077, $XDG_RUNTIME_DIR when available, per-user /tmp fallback, and chmod 700 workdirs.
  • Keep transcript/API payload logging opt-in. SAY_TO_CLIP_LOG=1 is operational logging; SAY_TO_CLIP_LOG_CONTENT=1 is sensitive content logging.
  • When logging is off, successful runs should remove recordings, transcripts, cleaned output, and provider response temp files.
  • Preserve notification lifecycle behavior: recording start creates a persistent red-light notification with live mic-level status when supported, recording stop dismisses it by ID, progress handoff notifications remain ordinary text notifications, and completion uses the green ready-light notification.
  • Keep clipboard behavior compatible with Wayland: wl-copy --foreground stays alive and its pid is stored so later copies can replace it.
  • Do not add product-style install machinery unless the user explicitly asks; this repo is meant as a reference springboard.

Checks

Run syntax checks for script edits:

bash -n say_to_clip ollama-manager smoke-test

Run ShellCheck when available:

shellcheck say_to_clip ollama-manager smoke-test

Run ./smoke-test only when a live provider validation is appropriate. It may call local Ollama/Whisper or Groq based on the user's config.

When not to use it

  • When the task is not related to the `say_to_clip` project.
  • When adding product-style install machinery without explicit user request.

Limitations

  • Keep Groq API keys out of visible command arguments.
  • Keep runtime files private.
  • Keep transcript/API payload logging opt-in.

How it compares

This skill provides specific rules and checks for maintaining the `say_to_clip` dictation project, ensuring consistency and privacy, unlike general script editing.

Compared to similar skills

say-to-clip-maintenance side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
say-to-clip-maintenance (this skill)02moCautionIntermediate
windows-ui-automation178moReviewAdvanced
linux-production-shell-scripts76moReviewIntermediate
cursor-prod-checklist427dReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

windows-ui-automation

martinholovsky

Expert in Windows UI Automation (UIA) and Win32 APIs for desktop automation. Specializes in accessible, secure automation of Windows applications including element discovery, input simulation, and process interaction. HIGH-RISK skill requiring strict security controls for system access.

17126

linux-production-shell-scripts

davila7

This skill should be used when the user asks to "create bash scripts", "automate Linux tasks", "monitor system resources", "backup files", "manage users", or "write production shell scripts". It provides ready-to-use shell script templates for system administration.

746

cursor-prod-checklist

jeremylongshore

Execute production readiness checklist for Cursor IDE setup. Triggers on "cursor production", "cursor ready", "cursor checklist", "optimize cursor setup". Use when working with cursor prod checklist functionality. Trigger with phrases like "cursor prod checklist", "cursor checklist", "cursor".

434

openevidence-prod-checklist

jeremylongshore

Production readiness checklist for OpenEvidence clinical AI deployments. Use when preparing for production launch, conducting pre-deployment reviews, or auditing OpenEvidence integration for compliance. Trigger with phrases like "openevidence production", "openevidence go-live", "openevidence checklist", "deploy openevidence", "openevidence readiness".

13

posthog-enterprise-rbac

jeremylongshore

Configure PostHog enterprise SSO, role-based access control, and organization management. Use when implementing SSO integration, configuring role-based permissions, or setting up organization-level controls for PostHog. Trigger with phrases like "posthog SSO", "posthog RBAC", "posthog enterprise", "posthog roles", "posthog permissions", "posthog SAML".

13

prowler-provider

prowler-cloud

Creates new Prowler cloud providers or adds services to existing providers. Trigger: When extending Prowler SDK provider architecture (adding a new provider or a new service to an existing provider).

13

Search skills

Search the agent skills registry