wispr-fix/SKILL.md
--- name: wispr-fix description: Queue and batch-apply Wispr Flow dictation corrections. Use when the user invokes /wispr-fix or writes "wispr fix: X -> Y" to correct a speech-to-text mishear. --- # Wispr Fix: Dictation Correction Queue Queue dictation corrections instantly during work. Apply them all at once when convenient. ## Invocation Patterns ### Explicit add User says: `/wispr-fix "Clauthe Code" "Claude Code"` Action: Run the add command. ### Auto-detect pattern User writes: `wispr f
npx skillsauth add glebis/claude-skills wispr-fixInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Queue dictation corrections instantly during work. Apply them all at once when convenient.
User says: /wispr-fix "Clauthe Code" "Claude Code"
Action: Run the add command.
User writes: wispr fix: X -> Y
Action: Parse X and Y, run the add command.
User says: /wispr-fix flush, /wispr-fix dry-run, /wispr-fix list
Action: Run the corresponding command.
All commands use the script at ~/.claude/skills/wispr-fix/scripts/wispr-fix.sh.
~/.claude/skills/wispr-fix/scripts/wispr-fix.sh add "<mishear>" "<correction>"
Use --exact to skip case variant generation (auto-applied for single words).
~/.claude/skills/wispr-fix/scripts/wispr-fix.sh list
~/.claude/skills/wispr-fix/scripts/wispr-fix.sh remove "<mishear>"
Supports fuzzy matching on the mishear string.
~/.claude/skills/wispr-fix/scripts/wispr-fix.sh dry-run
~/.claude/skills/wispr-fix/scripts/wispr-fix.sh flush
Options: --force-quit (force-kill Wispr if graceful quit fails), --no-restart (don't restart Wispr after).
IMPORTANT: Flush will quit Wispr Flow, apply all corrections to the SQLite database, and restart it. Always inform the user before running flush.
~/.claude/skills/wispr-fix/scripts/wispr-fix.sh restore latest
When the user invokes /wispr-fix with arguments:
| Input | Action |
|-------|--------|
| "X" "Y" or X Y (two quoted/unquoted args) | add "X" "Y" |
| flush | flush |
| flush --force-quit | flush --force-quit |
| dry-run | dry-run |
| list | list |
| remove "X" | remove "X" |
| restore latest | restore latest |
| (no args) | list (show current queue) |
When you see wispr fix: X -> Y in user text (the wispr fix: prefix is required):
wispr fix: and ->)->)add "X" "Y"~/.claude/skills/wispr-fix/queue.jsonlqueue.applied.jsonl~/Library/Application Support/Wispr Flow/backups/ (last 10 retained)development
Create Tufte-inspired data reports and infographic dashboards as standalone HTML files. Uses EB Garamond for text, Monaspace Argon for numbers, Chart.js for interactive charts, and inline SVG sparklines. Produces publication-quality reports with 2-column narrative+data layouts, status dashboards, scroll animations, and responsive mobile support. Use this skill whenever the user wants to create a data report, activity dashboard, infographic, personal analytics page, health tracker visualization, or any document that combines narrative text with interactive charts and tables. Also triggers for "make a report like Tufte", "create an infographic", "build a dashboard", "visualize my data", or requests for beautiful data-driven documents.
documentation
Cut a software release and maintain a tiered compatibility policy. Use when the user wants to release, ship a version, bump the version, tag a release, write a changelog, or update COMPATIBILITY. Config-driven via release.config.json; bumps version files, runs a readiness gate, updates COMPATIBILITY.md tiers and deprecations, tags (→ release workflow), and reports closed issues. Teaches the underlying standards as it runs.
development
Sync and manage bilingual (EN/RU) library content for agency-docs. Use when adding, updating, or reviewing library articles. Handles translation, sync checks, and Russian stylistic review.
development
This skill should be used to watch a long-running background job (ffmpeg/media encode, qmd or other embedding/vector-DB run, batch agent/LLM pipeline, or a real-browser/agent-browser daemon) until it finishes or wedges, then deliver a verdict (done, needs-attention, or blocked) plus the exact next command, without burning dozens of manual poll commands. Triggers on "babysit this job", "watch this until it's done", "ping me when the encode/embed/batch finishes", "is this background process stuck", "monitor this ffmpeg/qmd run", or any request to wait on a long-running process and be told when it's complete or hung.