gmail
Skill1 starsChanged 3 months agoMITView on GitHub
Read-only Gmail source-material retrieval for agents. Use when you need to find relevant newsletters, reports, receipts, or topic-related emails without dumping the mailbox into context.
28 other projects use a version of this.
Adopted by
Most recently taken up by
- Banzamel/Achaja-Voice-Assistanttheir own version, first seen Nov 8, 2026
- Banzamel/AchajaVAtheir own version, first seen Nov 8, 2026
- sidmanale643/pekka-bottheir own version, first seen Nov 8, 2026
- codewhale-hq/codewhale-plugin-marketplacetheir own version, first seen Nov 8, 2026
- chnlich/charlie-bottheir own version, first seen Nov 1, 2026
- obra/muse-skillstheir own version, first seen Oct 13, 2026
Used with
Projects with it also use google_sheets, google-chat and 7 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Shugar86Skillgoogle_sheets
Google Sheets read/write integration
Also in 3 projects that use this
antoniolgSkillgoogle-chat
Read Google Chat spaces/threads via the Chat API, create/refresh OAuth tokens, parse Gmail Chat URLs, and list spaces. Use when asked to look up or verify messages in Google Chat or when you need API access to Chat from the CLI.
Also in 3 projects that use this
ansvisorSkillshopping
Checks product pages and feed for ChatGPT Shopping (US) and Google Shopping (EU).
Also in 3 projects that use this
ourinesSkillforget
Delete saved knowledge from ~/.claude/learnings/ and optionally clean up knowledge graph.
Also in 3 projects that use this
G-HunterAiSkilltiktok
TikTok platform integration. Manage videos, view analytics, and track engagement.
Also in 3 projects that use this
toolittlecakesSkilltelegram
Read Telegram messages and chats. Use when the user wants to search Telegram chats, list dialogs, or get messages from a chat. Requires authentication on first use.
Also in 4 projects that use this
Other versions28 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 28
- vellum-ai/vellum-assistant★ 1.5ksame name
- gemini-cli-extensions/workspace★ 646same name
- sanjay3290/ai-skills★ 452same name
- greatSumini/cc-system★ 438same name
- glebis/claude-skills★ 410same name
- refly-ai/refly-skills★ 204same name
- hyperfx-ai/marketing-skills★ 112same name
- obra/muse-skills★ 20same name
- AbdullahMalik17/malikclaw★ 16same name
- pbc-os/smb-starter-kit★ 10same name
18 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository29 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docxSkill
- pdfSkill
- app-icon-studioSkill
- audit-promptSkill
- bootstrap-goal-projectSkill
- boy-scoutSkill
- brand-namingSkill
- create-engineering-skillSkill
- create-prSkill
- elevenlabsSkill
- firebase-adminSkill
- firebase-hosting-basicsSkill
- linearSkill
- nano-banana-app-iconSkill
- new-projectSkill
- plainSkill
- product-researchSkill
- pr-qa-browserSkill
- publish-researchSkill
- readme-best-practicesSkill
- researchSkill
- ripple-checkSkill
- roadmap-pageSkill
- scopeSkill
- searchexaSkill
- slackSkill
- triage-pr-commentsSkill
- write-loopSkill
The file
We split this skill into the rules it gives an agent
11 rules. 0 are common, 7 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 24 edited versions we read keep these.
7
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Read-only Gmail source-material retrieval through the Gmail Read CLI.
- Distinctive: line 12
Use this skill to find and read a narrow set of relevant Gmail messages as source material for research, summarization, or evidence …
- Very specific: line 40
Run config to see which credential sources loaded and whether required variables are present.
- Very specific: line 42
Run doctor to verify read-only IMAP connectivity without returning email content.
- Distinctive: line 46
Before running broad mailbox searches, narrow the request by at least one of:
- Very specific: line 54
Do not use this as a mailbox dump tool.
- Distinctive: line 58
Read-only v1: no sending, replying, deleting, archiving, labeling, or mark-read/unread operations.
- Distinctive: line 59
Search returns metadata and snippets by default, not full bodies.
- Very specific: line 63
Do not run live Gmail tests in normal development workflows.
- Distinctive: line 79
Read one selected message from search results:
- Distinctive: line 85
Read a selected conversation with sent replies included and direction markers:
“Common” is measured: kept by at least 6 in 10 of the 24 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
<objective>
Read-only Gmail source-material retrieval through the **Gmail Read CLI**.Use this skill to find and read a narrow set of relevant Gmail messages as source material for research, summarization, or evidence gathering. Do not use it as a mailbox dump tool.
</objective>
<cli_cheatsheet>
Script path: ~/.claude/skills/gmail/scripts/gmail.py
Run with: uv run <script> <command> [options]
uv run <script> search [--from X] [--after YYYY-MM-DD] [--before YYYY-MM-DD] [--subject TEXT] [--text TEXT] [--query RAW] [--label LABEL] [--mailbox all|inbox] [--limit N] [--snippet-chars N] [--include-sent] [--include-spam-trash] [--load-shell-env]
uv run <script> get <message-id> [--max-chars N] [--load-shell-env]
uv run <script> thread <thread-id> [--max-messages N] [--max-chars-per-message N] [--load-shell-env]
uv run <script> labels [--load-shell-env]
uv run <script> config [--load-shell-env]
uv run <script> doctor [--load-shell-env]Defaults: search uses All Mail, received mail only, excludes spam/trash, returns bounded snippets rather than full bodies, and applies conservative result limits. </cli_cheatsheet>
<configuration>
Required credentials:GMAIL_USERGMAIL_APP_PASSWORD
Provide these variables through the agent environment, process environment, or the CLI's supported credential files.
Run config to see which credential sources loaded and whether required variables are present. Secret values are never printed. If credentials are exported only from shell startup files, use --load-shell-env.
Run doctor to verify read-only IMAP connectivity without returning email content.
</configuration>
<guardrails>
Before running broad mailbox searches, narrow the request by at least one of:- Sender or domain (
--from) - Topic/body text (
--text) or subject (--subject) - Label (
--label) - Timeframe (
--after,--before) - Raw Gmail query (
--query)
Do not use this as a mailbox dump tool. Search first, inspect metadata/snippets, then fetch only selected messages or threads with get or thread.
</guardrails>
<privacy_rules>
- Read-only v1: no sending, replying, deleting, archiving, labeling, or mark-read/unread operations.
- Search returns metadata and snippets by default, not full bodies.
getandthreadreturn normalized plain text with explicit truncation metadata.- Attachment handling is metadata-only: filename, content type, and approximate size when available. Attachment contents are not downloaded, written, or parsed.
- The CLI does not cache or log email bodies, snippets, subjects, senders, or results.
- Do not run live Gmail tests in normal development workflows; use
doctormanually when credentials are available. </privacy_rules>
<examples>
Newsletter research from a domain:uv run ~/.claude/skills/gmail/scripts/gmail.py search --from example.com --after 2026-01-01 --text "pricing" --limit 5Find recent finance reports without reading bodies yet:
uv run ~/.claude/skills/gmail/scripts/gmail.py search --label Finance --subject "monthly report" --after 2026-01-01Read one selected message from search results:
uv run ~/.claude/skills/gmail/scripts/gmail.py get <message-id> --max-chars 8000Read a selected conversation with sent replies included and direction markers:
uv run ~/.claude/skills/gmail/scripts/gmail.py thread <thread-id> --max-messages 10 --max-chars-per-message 6000</examples>Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.