Agent skill

Wispr Fix

by glebis in glebis/claude-skills

Queue and batch-apply Wispr Flow dictation corrections. An agent skill from glebis/claude-skills.

MITAuto-check passedMedia & Creative

Install Wispr Fix

skills CLI
$ npx skills add glebis/claude-skills --skill wispr-fix -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install glebis/claude-skills wispr-fix --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/glebis/claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/wispr-fix .claude/skills/wispr-fix && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
wispr-fix
GitHub stars
390
Token cost
~727 tokens
SKILL.md length
291 words
Files
2 (incl. scripts)
Skills in repo
92
Repo updated
First seen
Licence
MIT

At a glance

Queue and batch-apply Wispr Flow dictation corrections. An agent skill from glebis/claude-skills.

  • Works in 5 steps: Parse X (everything between wispr fix:… → Parse Y (everything after ->) → Trim whitespace from both → …
  • The user invokes /wispr-fix
  • SKILL.md covers Invocation Patterns, Commands, Argument Parsing and Auto-Detect Pattern, plus 1 more section
  • Runs Shell scripts from its folder

What it does

Wispr Fix is an agent skill from glebis/claude-skills. 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.

Its SKILL.md is about 730 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/wispr-fix.sh`).

It sits in Media & Creative, covering Transcription and Speech recognition and synthesis. The repository describes itself as: Collection of Claude Code skills for enhanced AI workflows. The licence is MIT.

When your agent uses it

  • The user invokes /wispr-fix
  • Writes wispr fix: X - Y to correct a speech-to-text mishear

Example prompts

  • “wispr fix: X - Y”
  • “/wispr-fix”

Requirements

  • A Bash shell

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Parse X (everything between wispr fix: and ->)
  2. Parse Y (everything after ->)
  3. Trim whitespace from both
  4. Run add "X" "Y"
  5. Confirm to the user: "Queued: 'X' -> 'Y'"

What it can do on your machine

Read from SKILL.md and the folder at commit 3b88261. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Shell), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Wispr Fix loads about 727 tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 291 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~727

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from glebis/claude-skills at commit 3b88261, republished under its MIT licence (© glebis). 291 words, ~727 tokens.

Download SKILL.mdSave it as .claude/skills/wispr-fix/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
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" "Codex" Action: Run the add command.

Auto-detect pattern

User writes: wispr fix: X -> Y Action: Parse X and Y, run the add command.

Flush / dry-run / list

User says: /wispr-fix flush, /wispr-fix dry-run, /wispr-fix list Action: Run the corresponding command.

Commands

All commands use the script at ~/.Codex/skills/wispr-fix/scripts/wispr-fix.sh.

Queue a correction
bash
~/.Codex/skills/wispr-fix/scripts/wispr-fix.sh add "<mishear>" "<correction>"

Use --exact to skip case variant generation (auto-applied for single words).

List pending corrections
bash
~/.Codex/skills/wispr-fix/scripts/wispr-fix.sh list
Remove a queued correction
bash
~/.Codex/skills/wispr-fix/scripts/wispr-fix.sh remove "<mishear>"

Supports fuzzy matching on the mishear string.

Preview what flush will do
bash
~/.Codex/skills/wispr-fix/scripts/wispr-fix.sh dry-run
Apply all queued corrections
bash
~/.Codex/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.

Restore from backup
bash
~/.Codex/skills/wispr-fix/scripts/wispr-fix.sh restore latest

Argument Parsing

When the user invokes /wispr-fix with arguments:

InputAction
"X" "Y" or X Y (two quoted/unquoted args)add "X" "Y"
flushflush
flush --force-quitflush --force-quit
dry-rundry-run
listlist
remove "X"remove "X"
restore latestrestore latest
(no args)list (show current queue)

Auto-Detect Pattern

When you see wispr fix: X -> Y in user text (the wispr fix: prefix is required):

  1. Parse X (everything between wispr fix: and ->)
  2. Parse Y (everything after ->)
  3. Trim whitespace from both
  4. Run add "X" "Y"
  5. Confirm to the user: "Queued: 'X' -> 'Y'"

Notes

  • Corrections are queued instantly — no Wispr restart needed
  • Flush quits Wispr, backs up DB, applies corrections, verifies integrity, exports dictionary, restarts Wispr
  • The queue persists between sessions at ~/.Codex/skills/wispr-fix/queue.jsonl
  • Applied corrections are logged in queue.applied.jsonl
  • Backups are stored in ~/Library/Application Support/Wispr Flow/backups/ (last 10 retained)

© glebis, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (scripts) in wispr-fix of glebis/claude-skills.

  • SKILL.md
  • scripts/wispr-fix.sh

Open the folder on GitHubat commit 3b88261

Compare with similar skills

Wispr Fix next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Wispr Fix compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Wispr Fix this skillglebis/claude-skills390—~727Automated safety check: PassMIT
Voxtype Installpchalasani/claude-code-tools2k—~857Automated safety check: NotesMIT
Speech To TextNoizAI/skills526—~917Automated safety check: PassNone
Podcast Transcript FetcherVarnan-Tech/opendirectory674—~1.9kAutomated safety check: NotesMIT
Audio Transcriptionmitsuhiko/agent-stuff3.2k—~1kAutomated safety check: PassApache-2.0
Speech Recognitiondpearson2699/swift-ios-skills1.2k—~3.7kAutomated safety check: PassCustom licence

Similar skills

  • Voxtype Install

    pchalasani/claude-code-tools

    Guide the user through installing, configuring, and launching voxtype — local on-device voice dictation (speech-to-text that types wherever the cursor is).

    2k GitHub stars~857 tokensUpdated yesterday
    Media & CreativeAuto-check: notes
  • Speech To Text

    NoizAI/skills

    A skill your agent uses whenever the user wants to transcribe audio to text, convert speech to text, or get a transcript from an audio or video file.

    526 GitHub stars~917 tokensUpdated 11 days ago
    Media & CreativeAuto-check passed
  • Podcast Transcript Fetcher

    Varnan-Tech/opendirectory

    A skill your agent uses when fetching, searching, or analyzing transcripts from Lenny's Podcast, Dwarkesh Podcast, Cheeky Pint, 20VC, or A16z Podcast.

    674 GitHub stars~1.9k tokensUpdated 1 mo ago
    Media & CreativeAuto-check: notes
  • Audio Transcription

    mitsuhiko/agent-stuff

    Transcribe local audio/video and Apple Voice Memos quickly with cached MLX Whisper models, including bad/low-quality audio.

    3.2k GitHub stars~1k tokensUpdated 12 days ago
    Media & CreativeAuto-check passed
  • Speech Recognition

    dpearson2699/swift-ios-skills

    Transcribe speech to text using Apple's Speech framework. An agent skill from dpearson2699/swift-ios-skills.

    1.2k GitHub stars~3.7k tokensUpdated 2 mo ago
    Media & CreativeAuto-check passed
  • Speech Build

    cnemri/google-genai-skills

    Generate and transcribe speech using Google's Gemini-TTS and Chirp 3 models.

    127 GitHub stars~430 tokensUpdated 8 mo ago
    Media & CreativeAuto-check passed

More from glebis/claude-skills

All 92 skills in this repo
  • Runs a human-first workflow for labeling PII spans in a transcript, then scores inter-annotator agreement and drafts an adjudicated gold set.

    390 GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed
  • Automates a dedicated, logged-in Chrome instance per profile without ever closing the user's own open tabs or browser windows.

    390 GitHub stars~973 tokensUpdated yesterday
    Auto-check passed
  • Deep Research

    glebis/claude-skills

    This skill should be used when conducting comprehensive research on any topic using the OpenAI Deep Research API.

    390 GitHub stars~2.6k tokensUpdated yesterday
    Auto-check: notes
  • Elimination Research

    glebis/claude-skills

    This skill should be used for elimination-style research where the user wants to choose from a shortlist of products, tools, services, vendors, or other options using explicit criteria, numeric…

    390 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed
  • Narrated HTML Presentations

    glebis/claude-skills

    Generates a self-contained HTML presentation with article and slides modes, ElevenLabs voiceover narration and optional GPT Image 2 illustrations.

    390 GitHub stars~2.3k tokensUpdated yesterday
    Auto-check: notes
  • Writes fictional but realistic coaching or therapy session transcripts for evals, demos and few-shot examples, in several modalities and export formats.

    390 GitHub stars~2.9k tokensUpdated yesterday
    Auto-check passed

Questions about Wispr Fix

What does Wispr Fix do?

Queue and batch-apply Wispr Flow dictation corrections. An agent skill from glebis/claude-skills. Wispr Fix is an agent skill from glebis/claude-skills. Queue and batch-apply Wispr Flow dictation corrections.

When should I use Wispr Fix?

Wispr Fix fits situations like: the user invokes /wispr-fix; writes wispr fix: X - Y to correct a speech-to-text mishear.

How do I install Wispr Fix in Claude Code?

Run `npx skills add glebis/claude-skills --skill wispr-fix -a claude-code`. Or copy the skill folder (wispr-fix in glebis/claude-skills) into .claude/skills/wispr-fix in your project. Claude Code loads it when a task matches its description.

How do I install Wispr Fix in Codex?

Run `npx skills add glebis/claude-skills --skill wispr-fix -a codex`. Or copy the skill folder (wispr-fix in glebis/claude-skills) into .agents/skills/wispr-fix in your project. Codex loads it when a task matches its description.

Can I use Wispr Fix in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add glebis/claude-skills --skill wispr-fix -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/wispr-fix, .gemini/skills/wispr-fix, .github/skills/wispr-fix and .opencode/skills/wispr-fix in your project.

What does Wispr Fix need to run?

Going by SKILL.md and its folder, Wispr Fix needs a shell for the scripts in its folder. Our summary lists: A Bash shell.

Does Wispr Fix access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Wispr Fix safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Wispr Fix use?

Wispr Fix is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Wispr Fix use?

About 727 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Wispr Fix?

Skills that share tags, products or a category with Wispr Fix: Voxtype Install (pchalasani/claude-code-tools, 2k stars), Speech To Text (NoizAI/skills, 526 stars), Podcast Transcript Fetcher (Varnan-Tech/opendirectory, 674 stars) and Audio Transcription (mitsuhiko/agent-stuff, 3.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Wispr Fix?

glebis (a GitHub user) maintains it in glebis/claude-skills, which has 390 GitHub stars. The repository holds 92 skills in this directory. The repository was last updated on October 8, 2026.

Source: glebis/claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.