Agent skill

Email To Tasks

by mohitagw15856 in mohitagw15856/pm-claude-skills

Convert an email (or a whole thread) into real tasks — the actual asks extracted from the prose, each with owner, deadline, and the done-test, so nothing lives in the inbox as its own reminder.

MITAuto-check passedAgent Workflows

Install Email To Tasks

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill email-to-tasks -a claude-code

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

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills email-to-tasks --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/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/email-to-tasks .claude/skills/email-to-tasks && 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
email-to-tasks
GitHub stars
1.4k
Token cost
~1.2k tokens
SKILL.md length
610 words
Files
1
Skills in repo
1,348
Repo updated
First seen
Licence
MIT

At a glance

Convert an email (or a whole thread) into real tasks — the actual asks extracted from the prose, each with owner, deadline, and the done-test, so nothing lives in the inbox as its own reminder.

  • Works in 5 steps: Hunt four ask-shapes: direct requests… → Quote or it doesn't exist: every task… → Owner-verb-deadline or it's not a task:… → …
  • Asked what am I actually being asked to do here
  • SKILL.md covers What This Skill Produces, Required Inputs, Framework: The Extraction Rules and Output Format, plus 8 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Email To Tasks is an agent skill from mohitagw15856/pm-claude-skills. Convert an email (or a whole thread) into real tasks — the actual asks extracted from the prose, each with owner, deadline, and the done-test, so nothing lives in the inbox as its own reminder. Use when asked what am I actually being asked to do here, turn this thread into a task list, extract the action items from this email, or I keep re-reading this thread. Produces the ask extraction with quoted sources, the task list in owner-verb-deadline form, and the reply that confirms the commitments.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Task breakdown and Email management. The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.

When your agent uses it

  • Asked what am I actually being asked to do here
  • Turn this thread into a task list
  • Extract the action items from this email
  • I keep re-reading this thread

Example prompts

  • “/email-to-tasks”

Workflow steps

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

  1. Hunt four ask-shapes: direct requests ("please send…") · questions requiring work ("could you find out…") · implied ownership ("someone…
  2. Quote or it doesn't exist: every task cites its source line. Extraction that paraphrases invents asks; the quote discipline keeps the list…
  3. Owner-verb-deadline or it's not a task: "the report" is a topic; "Mira sends the Q3 report to finance by Thursday EOD" is a task. Unstated…
  4. The done-test: each task states what done observably looks like ("the deck is in the shared folder and Ana is told"). Tasks without…
  5. Ambiguity gets a question, not a guess: "handle the vendor situation" doesn't decompose — it generates the clarifying question ("by…

What it can do on your machine

Read from SKILL.md and the folder at commit 1cbf1f0. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Email To Tasks loads about 1.2k tokens when it runs. Until then it costs about 129 tokens; SKILL.md has 610 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~129
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 610 words, ~1,186 tokens.

Download SKILL.mdSave it as .claude/skills/email-to-tasks/SKILL.md (or your agent's skills folder).
name
email-to-tasks
description
Convert an email (or a whole thread) into real tasks — the actual asks extracted from the prose, each with owner, deadline, and the done-test, so nothing lives in the inbox as its own reminder. Use when asked what am I actually being asked to do here, turn this thread into a task list, extract the action items from this email, or I keep re-reading this thread. Produces the ask extraction with quoted sources, the task list in owner-verb-deadline form, and the reply that confirms the commitments.

Email To Tasks Skill

Long emails and longer threads hide their asks: three requests buried in paragraph four, a soft deadline in the sign-off, an implied "you'll handle this?" nobody confirmed. Until the asks are extracted, the thread itself becomes the task — re-read five times, actioned zero. This skill mines the actual requests (quoted, so nothing is invented), converts each into owner-verb-deadline form with a done-test, and drafts the confirming reply that turns assumptions into commitments.

What This Skill Produces

  • The ask extraction — every explicit and implied request, quoted from the source text
  • The task list — each: owner · verb-first action · deadline (stated or proposed) · the done-test
  • The ambiguity list — asks too vague to action, each with the clarifying question that fixes it
  • The confirming reply — the short message that locks owners and dates before anyone's assumption diverges

Required Inputs

Ask for these if not provided:

  • The email/thread — verbatim; extraction quotes its sources
  • Who the user is in it — extraction is role-relative: their tasks, tasks they're delegating, and tasks that are someone else's problem are three different lists
  • The task system — where tasks live (tool or list), so the output lands in import-ready shape

Framework: The Extraction Rules

  1. Hunt four ask-shapes: direct requests ("please send…") · questions requiring work ("could you find out…") · implied ownership ("someone should…" in a thread addressed to you) · and commitments the user made ("I'll get back to you on…") — the last category is the most-dropped and most reputation-expensive.
  2. Quote or it doesn't exist: every task cites its source line. Extraction that paraphrases invents asks; the quote discipline keeps the list honest and makes the confirming reply defensible.
  3. Owner-verb-deadline or it's not a task: "the report" is a topic; "Mira sends the Q3 report to finance by Thursday EOD" is a task. Unstated deadlines get proposed ones marked as proposals — the confirming reply makes them real.
  4. The done-test: each task states what done observably looks like ("the deck is in the shared folder and Ana is told"). Tasks without done-tests get re-litigated at review time.
  5. Ambiguity gets a question, not a guess: "handle the vendor situation" doesn't decompose — it generates the clarifying question ("by 'handle,' do you mean renegotiate or terminate?") and parks until answered. Guessed interpretations of vague asks are how work gets done twice.
Show full SKILL.md (227 more words)Show less

Output Format

Tasks From: [thread subject]

Your Tasks

Task (owner-verb-deadline)Source (quoted)Done-test

You're Delegating / Others Own

[Same table — the confirming reply assigns these explicitly]

Commitments You Made

[The "I'll…" list — these outrank inbound asks reputationally]

Too Vague To Action

[Each: the quoted ask + the clarifying question]

The Confirming Reply

[Short draft: "Confirming: I'll do X by [date], Y by [date]. Assuming Z is with Priya — flag if not. On the vendor question: [the clarifier]."]

Quality Checks

  • Every task quotes its source line
  • Every task has owner, verb, deadline (stated or labeled-proposed), and done-test
  • The user's own outbound commitments were mined, not just inbound asks
  • Vague asks became questions, never guesses
  • The confirming reply covers every owner assumption the extraction made

Anti-Patterns

  • Do not paraphrase asks into existence — quote or drop
  • Do not leave deadlines unproposed — "no deadline" means "never" in practice; propose and confirm
  • Do not skip the confirming reply — unconfirmed extraction is a private theory about shared work
  • Do not action vague asks by interpretation — the clarifying question costs one line; the wrong guess costs the work
  • Do not leave the thread as backup storage — once tasks are filed and confirmed, the thread archives

Example Trigger Phrases

  • "What am I actually being asked to do here?"
  • "Turn this thread into a task list."
  • "Extract the action items from this email."
  • "I keep re-reading this thread."

© mohitagw15856, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/email-to-tasks of mohitagw15856/pm-claude-skills.

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Email To Tasks 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.

Email To Tasks compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Email To Tasks this skillmohitagw15856/pm-claude-skills1.4k—~1.2kAutomated safety check: PassMIT
agtx One-Shot Project Runnerfynnfluegge/agtx1.7k—~3.8kAutomated safety check: PassApache-2.0
PrepAIOSAI/AIPass288—~880Automated safety check: PassMIT
Using Agent RelayAgentWorkforce/relay8721 repos~2.1kAutomated safety check: PassApache-2.0
GSD Quick Batchopen-gsd/gsd-core10k—~1.4kAutomated safety check: NotesMIT
Procrastination Busterhidai25/eval-view1371 repos~837Automated safety check: PassApache-2.0

Similar skills

  • Runs a whole project unattended on an agtx kanban board, decomposing the goal, starting tasks, unblocking workers and merging each result.

    1.7k GitHub stars~3.8k tokensUpdated 8 days ago
    Agent WorkflowsAuto-check passed
  • Prep

    AIOSAI/AIPass

    Session wrap-up. An agent skill from AIOSAI/AIPass.

    288 GitHub stars~880 tokensUpdated 6 days ago
    Agent WorkflowsAuto-check passed
  • Using Agent Relay

    AgentWorkforce/relay

    A skill your agent uses when you are a registered relay agent (a spawned worker, or a lead that called registeragent) coordinating with peers in real time over current Agent Relay MCP tools -…

    872 GitHub starsUsed in 1 repo~2.1k tokens
    Agent WorkflowsAuto-check passed
  • GSD Quick Batch

    open-gsd/gsd-core

    Runs several small /gsd-quick tasks as one batch, with a single coordinator that plans them, dispatches workers per item and owns all shared writes and worktree merges.

    10k GitHub stars~1.4k tokensUpdated yesterday
    Agent WorkflowsAuto-check: notes
  • Procrastination Buster

    hidai25/eval-view

    Beat procrastination with task breakdown, 2-minute starts, and accountability tracking

    137 GitHub starsUsed in 1 repo~837 tokens
    Agent WorkflowsAuto-check passed
  • Interlinked Coordination

    QuentinCody/interlinked-cli

    Coordinate with other agents/humans via the optional Interlinked MCP Server, and use local checkpoints & file reservations.

    178 GitHub stars~2.9k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from mohitagw15856/pm-claude-skills

All 1,348 skills in this repo
  • Car Tco

    mohitagw15856/pm-claude-skills

    Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Cs Health Scorecard

    mohitagw15856/pm-claude-skills

    Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.

    1.4k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • Exit Waterfall

    mohitagw15856/pm-claude-skills

    Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Feature Prioritisation

    mohitagw15856/pm-claude-skills

    Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.

    1.4k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • Fire Number

    mohitagw15856/pm-claude-skills

    Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Freelance Rate

    mohitagw15856/pm-claude-skills

    Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.

    1.4k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

Questions about Email To Tasks

What does Email To Tasks do?

Convert an email (or a whole thread) into real tasks — the actual asks extracted from the prose, each with owner, deadline, and the done-test, so nothing lives in the inbox as its own reminder. Email To Tasks is an agent skill from mohitagw15856/pm-claude-skills. Convert an email (or a whole thread) into real tasks — the actual asks extracted from the prose, each with owner, deadline, and the done-test, so nothing lives in the inbox as its own reminder.

When should I use Email To Tasks?

Email To Tasks fits situations like: asked what am I actually being asked to do here; turn this thread into a task list; extract the action items from this email; I keep re-reading this thread.

How do I install Email To Tasks in Claude Code?

Run `npx skills add mohitagw15856/pm-claude-skills --skill email-to-tasks -a claude-code`. Or copy the skill folder (skills/email-to-tasks in mohitagw15856/pm-claude-skills) into .claude/skills/email-to-tasks in your project. Claude Code loads it when a task matches its description.

How do I install Email To Tasks in Codex?

Run `npx skills add mohitagw15856/pm-claude-skills --skill email-to-tasks -a codex`. Or copy the skill folder (skills/email-to-tasks in mohitagw15856/pm-claude-skills) into .agents/skills/email-to-tasks in your project. Codex loads it when a task matches its description.

Can I use Email To Tasks 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 mohitagw15856/pm-claude-skills --skill email-to-tasks -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/email-to-tasks, .gemini/skills/email-to-tasks, .github/skills/email-to-tasks and .opencode/skills/email-to-tasks in your project.

What does Email To Tasks need to run?

SKILL.md names no scripts, command-line tools or credentials: Email To Tasks is instructions for the agent only.

Does Email To Tasks 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 Email To Tasks 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. Review the folder before installing.

What licence does Email To Tasks use?

Email To Tasks 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 Email To Tasks use?

About 1.2k tokens (SKILL.md is roughly 4.7k 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 Email To Tasks?

Skills that share tags, products or a category with Email To Tasks: agtx One-Shot Project Runner (fynnfluegge/agtx, 1.7k stars), Prep (AIOSAI/AIPass, 288 stars), Using Agent Relay (AgentWorkforce/relay, 872 stars) and GSD Quick Batch (open-gsd/gsd-core, 10k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Email To Tasks?

mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 2026.

Source: mohitagw15856/pm-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.