New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Voice Dump To Todo

by FAIRY123456789 in FAIRY123456789/human-edge-agent-skills

Convert a long, messy, repetitive, speech-recognition-heavy task dump into a precise executable to-do list.

MITAuto-check passedAI & LLM Engineering

Install Voice Dump To Todo

skills CLI
$ npx skills add FAIRY123456789/human-edge-agent-skills --skill voice-dump-to-todo -a claude-code

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

GitHub CLI
$ gh skill install FAIRY123456789/human-edge-agent-skills voice-dump-to-todo --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/FAIRY123456789/human-edge-agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/voice-dump-to-todo .claude/skills/voice-dump-to-todo && 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
voice-dump-to-todo
GitHub stars
103
Token cost
~1.1k tokens
SKILL.md length
495 words
Files
4 (incl. scripts, references)
Skills in repo
18
Repo updated
First seen
Licence
MIT

At a glance

Convert a long, messy, repetitive, speech-recognition-heavy task dump into a precise executable to-do list.

  • Works in 10 steps: Read the whole dump before extracting… → Build a small active glossary from terms… → Resolve suspicious ASR terms using… → …
  • The user speaks tasks in inaccurate ASR language
  • SKILL.md covers Purpose, This skill is not vibe-to-spec, Instructions and Requirements, plus 6 more sections
  • Runs Python scripts from its folder; calls python

What it does

Voice Dump To Todo is an agent skill from FAIRY123456789/human-edge-agent-skills. Convert a long, messy, repetitive, speech-recognition-heavy task dump into a precise executable to-do list. Use when the user speaks tasks in inaccurate ASR language, changes priorities mid-sentence, mixes ideas with actions, or wants a downloadable standalone interactive HTML to-do that can be saved or dragged to the desktop. Use context-aware named-entity repair when a recurring term is clearly misrecognized, preserve uncertain corrections, and produce concrete definitions of done.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts and reference files (for example `README.md`, `references/asr-context-resolution.md` and `scripts/render_todo.py`).

It sits in AI & LLM Engineering, covering Speech recognition and synthesis and HTML artifacts. The repository describes itself as: 18 portable Agent Skills for voice-native AI, human judgment, microbets, social tact, writing, life systems, and safe deployment. The licence is MIT.

When your agent uses it

  • The user speaks tasks in inaccurate ASR language
  • Changes priorities mid-sentence
  • Mixes ideas with actions
  • Wants a downloadable standalone interactive HTML to-do that can be saved

Example prompts

  • “/voice-dump-to-todo”

Requirements

  • Python 3

Workflow steps

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

  1. Read the whole dump before extracting tasks. Later sentences may correct earlier ASR errors, dates, priorities, or scope.
  2. Build a small active glossary from terms already established in the current conversation or project, explicit user glossaries, repeated…
  3. Resolve suspicious ASR terms using references/asr-context-resolution.md. Do not “correct” a rare unknown name just because a familiar name…
  4. Split content into
  5. For every Action, produce
  6. Merge duplicates and use later explicit corrections to override earlier versions.
  7. Preserve task order when it encodes dependency. Otherwise rank by consequence and timing.
  8. Keep the active list small. Do not convert every reflection into a P0 task.
  9. When file output is requested, write a JSON task file and run scripts/render_todo.py to create a standalone interactive HTML file using…
  10. End with a short Needs confirmation section only when unresolved details materially affect execution.

What it can do on your machine

Read from SKILL.md and the folder at commit 31a0a16. 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/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    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

Voice Dump To Todo loads about 1.1k tokens when it runs, and up to ~1.5k if it reads all its reference files. Until then it costs about 127 tokens; SKILL.md has 495 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~127
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.5k

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 FAIRY123456789/human-edge-agent-skills at commit 31a0a16, republished under its MIT licence (© FAIRY123456789). 495 words, ~1,117 tokens.

Download SKILL.mdSave it as .claude/skills/voice-dump-to-todo/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
voice-dump-to-todo
description
Convert a long, messy, repetitive, speech-recognition-heavy task dump into a precise executable to-do list. Use when the user speaks tasks in inaccurate ASR language, changes priorities mid-sentence, mixes ideas with actions, or wants a downloadable standalone interactive HTML to-do that can be saved or dragged to the desktop. Use context-aware named-entity repair when a recurring term is clearly misrecognized, preserve uncertain corrections, and produce concrete definitions of done.
license
MIT
metadata.author
Joy T <101039451+FAIRY123456789@users.noreply.github.com>
metadata.tags
task-management, voice-input, productivity

Voice Dump to Todo

Purpose

The input can be chaotic. The output must be executable. Recover real commitments without converting every reflection into urgent work.

This skill is not vibe-to-spec

Use voice-dump-to-todo when the destination is a personal or team action list: what to do, decide, wait for, schedule, or park.

Use vibe-to-spec when the voice dump describes a product, system, feature, code change, webpage, API, or technical build and the destination is an implementation specification.

Instructions

  1. Read the whole dump before extracting tasks. Later sentences may correct earlier ASR errors, dates, priorities, or scope.
  2. Build a small active glossary from terms already established in the current conversation or project, explicit user glossaries, repeated names in the transcript, and host-provided memory only when it is legitimately available and relevant.
  3. Resolve suspicious ASR terms using references/asr-context-resolution.md. Do not “correct” a rare unknown name just because a familiar name exists in memory.
  4. Split content into:
    • Action — something someone should do;
    • Decision — a choice that must be made;
    • Waiting — blocked by another person or event;
    • Later — useful idea with no current commitment;
    • Background — context that should not become a task.
  5. For every Action, produce:
    • concise verb-first title;
    • concrete definition of done;
    • owner when known;
    • priority;
    • due date or time window only if actually stated or safely derived from an explicit relative date;
    • dependency;
    • uncertainty note when needed.
  6. Merge duplicates and use later explicit corrections to override earlier versions.
  7. Preserve task order when it encodes dependency. Otherwise rank by consequence and timing.
  8. Keep the active list small. Do not convert every reflection into a P0 task.
  9. When file output is requested, write a JSON task file and run scripts/render_todo.py to create a standalone interactive HTML file using localStorage.
  10. End with a short Needs confirmation section only when unresolved details materially affect execution.
Show full SKILL.md (187 more words)Show less

Requirements

The optional HTML renderer requires Python 3 and a local UTF-8 JSON task file. It uses only the Python standard library and does not require an API key or network access.

Available Scripts

ScriptPurposeArguments
scripts/render_todo.pyRender a reviewed JSON task list as standalone HTMLtasks.json [output.html]

Default task schema

json
{
  "title": "Verb-first task",
  "details": "Definition of done",
  "owner": "",
  "priority": "P1",
  "due": "",
  "status": "todo",
  "depends_on": [],
  "uncertainty": ""
}

Output modes

  • Compact Markdown checklist
  • Structured JSON
  • Standalone interactive HTML using localStorage

Do not turn reflective thoughts into tasks unless an action is explicitly implied.

Examples

  • Input: “Send the revised deck Thursday—actually Friday—then wait for Chen's budget number; the podcast idea can stay for later.”
  • Output: one Friday delivery action, one waiting item with dependency, and one later idea; the superseded Thursday date is not retained.

To render an approved task file locally:

bash
python scripts/render_todo.py tasks.json todo.html

Limitations

Do not invent owners or dates. File creation is optional and should happen only when requested; external task-manager updates require separate authorization.

Troubleshooting

If a transcript contains conflicting dates, prefer the latest explicit correction and flag unresolved timezone ambiguity. If an item has no action or decision, keep it as background or later rather than forcing it into the active list.

© FAIRY123456789, 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 3 other files (scripts, references) in skills/voice-dump-to-todo of FAIRY123456789/human-edge-agent-skills.

  • SKILL.md
  • README.md
  • references/asr-context-resolution.md
  • scripts/render_todo.py

Open the folder on GitHubat commit 31a0a16

Compare with similar skills

Voice Dump To Todo 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.

Voice Dump To Todo compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Voice Dump To Todo this skillFAIRY123456789/human-edge-agent-skills103—~1.1kAutomated safety check: PassMIT
Lark Minutesappleweiping/WEIPING_WIKI119—~1.6kAutomated safety check: PassMIT
TriageTalAter/annyang6.8k—~810Automated safety check: NotesMIT
Yichen Asrmcncarl/yichen-skills4.4k—~780Automated safety check: PassCustom licence
Dingtalk MinutesDingTalk-Real-AI/dingtalk-workspace-cli3.2k—~2.3kAutomated safety check: PassApache-2.0
Youtube FetcherJimmySadek/youtube-fetcher-to-markdown485—~3.1kAutomated safety check: PassMIT

Similar skills

  • Lark Minutes

    appleweiping/WEIPING_WIKI

    飞书妙记：妙记相关基本功能。1.查询妙记列表（按关键词/所有者/参与者/时间范围）；2.获取妙记基础信息（标题、封面、时长 等）；3.下载妙记音视频文件；4.获取妙记相关 AI 产物（总结、待办、章节）；5.上传音视频生成妙记，也支持将本地音视频文件转成纪要、逐字稿、文字稿、撰写文字等产物。遇到这类请求时，应优先使用本 skill，而不是尝试 ffmpeg、whisper…

    119 GitHub stars~1.6k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

  • Triage

    TalAter/annyang

    Triage and close GitHub issues on TalAter/annyang. An agent skill from TalAter/annyang.

    6.8k GitHub stars~810 tokensUpdated 4 days ago
    AI & LLM EngineeringAuto-check: notes

  • Yichen Asr

    mcncarl/yichen-skills

    逸尘自用的统一音视频转写入口，在 StepFun Step ASR 与火山引擎豆包 ASR 之间按输出需求、安全边界和可用状态路由。用于本地音频或视频的纯文本转写、时间戳、SRT 字幕、口播粗剪，以及转写前体检；用户明确指定服务商时不得静默切换。Use when a local audio or video file needs transcription and the correct…

    4.4k GitHub stars~780 tokensUpdated 7 days ago
    AI & LLM EngineeringAuto-check passed

  • Dingtalk Minutes

    DingTalk-Real-AI/dingtalk-workspace-cli

    钉钉 AI 听记。Use when 查询或修改听记摘要、完整逐字稿、关键词、标签、行动项、录音、上传、思维导图、发言人洞察、ASR 热词/识别词配置或分享权限。写文档走 dingtalk-doc；建待办走 dingtalk-todo；日程走 dingtalk-calendar。命令前缀：dws minutes。

    3.2k GitHub stars~2.3k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Youtube Fetcher

    JimmySadek/youtube-fetcher-to-markdown

    Retrieve transcripts from YouTube, Instagram, TikTok, X, Vimeo and other video sites, summarize or analyze what was said (and shown on screen), or save an Obsidian-ready Markdown knowledge-base note…

    485 GitHub stars~3.1k tokensUpdated 4 days ago
    AI & LLM EngineeringAuto-check passed

  • Yichen Web Research

    mcncarl/yichen-skills

    逸尘自用的互联网研究总入口。用于跨平台且跨阶段、用户尚未确定工具，或明确要求对公司、产品、人物、技术、行业和领域做横纵分析、发展史加现状对比或有来源约束的系统深度研究；先生成有截止日期和证据闸门的计划，再把搜索发现、候选核验、有限归档、按需转写和证据综合路由到…

    4.4k GitHub stars~1.9k tokensUpdated 7 days ago
    AI & LLM EngineeringAuto-check passed

More from FAIRY123456789/human-edge-agent-skills

All 18 skills in this repo

  • Aliyun Fullstack Deploy

    FAIRY123456789/human-edge-agent-skills

    Deploy full-stack apps to user-authorized Alibaba Cloud ECS or comparable Linux VPS hosts with preflight, canary verification, and rollback.

    103 GitHub stars~2.7k tokensUpdated yesterday
    Auto-check passed

  • Skill From Scars

    FAIRY123456789/human-edge-agent-skills

    Mine repeated pain from transcripts, project retrospectives, debugging logs, failed prompts, deployment notes, or work history and decide whether it deserves to become a reusable Agent Skill.

    103 GitHub stars~856 tokensUpdated yesterday
    Auto-check passed

  • Deployment Proof

    FAIRY123456789/human-edge-agent-skills

    Convert deployment logs, validation reports, Git history, and comparison notes into a redacted GitHub case study, portfolio entry, interview story, and evidence-backed resume bullets.

    103 GitHub stars~980 tokensUpdated yesterday
    Auto-check passed

  • Vibe To Spec

    FAIRY123456789/human-edge-agent-skills

    Convert messy voice input, imperfect speech recognition, half-formed product ideas, and iterative corrections into an implementation-ready software specification for Codex, Claude Code, Copilot…

    103 GitHub stars~997 tokensUpdated yesterday
    Auto-check passed

  • Build In Public Launcher

    FAIRY123456789/human-edge-agent-skills

    Turn a finished or nearly finished Skill, plugin, repository, micro-tool, research utility, or AI project into a credible public launch that can earn real users and feedback.

    103 GitHub stars~708 tokensUpdated yesterday
    Auto-check passed

  • Small Server Fit

    FAIRY123456789/human-edge-agent-skills

    Assess whether a web application and its build and runtime plan fit a low-cost Linux VPS or Alibaba Cloud ECS before purchase, implementation, or deployment.

    103 GitHub stars~1k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Voice Dump To Todo

What does Voice Dump To Todo do?

Convert a long, messy, repetitive, speech-recognition-heavy task dump into a precise executable to-do list. Voice Dump To Todo is an agent skill from FAIRY123456789/human-edge-agent-skills. Convert a long, messy, repetitive, speech-recognition-heavy task dump into a precise executable to-do list.

When should I use Voice Dump To Todo?

Voice Dump To Todo fits situations like: the user speaks tasks in inaccurate ASR language; changes priorities mid-sentence; mixes ideas with actions; wants a downloadable standalone interactive HTML to-do that can be saved.

How do I install Voice Dump To Todo in Claude Code?

Run `npx skills add FAIRY123456789/human-edge-agent-skills --skill voice-dump-to-todo -a claude-code`. Or copy the skill folder (skills/voice-dump-to-todo in FAIRY123456789/human-edge-agent-skills) into .claude/skills/voice-dump-to-todo in your project. Claude Code loads it when a task matches its description.

How do I install Voice Dump To Todo in Codex?

Run `npx skills add FAIRY123456789/human-edge-agent-skills --skill voice-dump-to-todo -a codex`. Or copy the skill folder (skills/voice-dump-to-todo in FAIRY123456789/human-edge-agent-skills) into .agents/skills/voice-dump-to-todo in your project. Codex loads it when a task matches its description.

Can I use Voice Dump To Todo 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 FAIRY123456789/human-edge-agent-skills --skill voice-dump-to-todo -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/voice-dump-to-todo, .gemini/skills/voice-dump-to-todo, .github/skills/voice-dump-to-todo and .opencode/skills/voice-dump-to-todo in your project.

What does Voice Dump To Todo need to run?

Going by SKILL.md and its folder, Voice Dump To Todo needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Voice Dump To Todo 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 Voice Dump To Todo 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 Voice Dump To Todo use?

Voice Dump To Todo is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Voice Dump To Todo use?

About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 392 tokens, read only when the agent opens those files.

What are the alternatives to Voice Dump To Todo?

Skills that share tags, products or a category with Voice Dump To Todo: Lark Minutes (appleweiping/WEIPING_WIKI, 119 stars), Triage (TalAter/annyang, 6.8k stars), Yichen Asr (mcncarl/yichen-skills, 4.4k stars) and Dingtalk Minutes (DingTalk-Real-AI/dingtalk-workspace-cli, 3.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Voice Dump To Todo?

FAIRY123456789 (a GitHub user) maintains it in FAIRY123456789/human-edge-agent-skills, which has 103 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on October 10, 2026.

Source: FAIRY123456789/human-edge-agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.