Career-Ops Gmail Lead Plugin
career-ops-hq/career-ops
Pulls job leads from a Gmail label into the career-ops pipeline, extracting job URLs from DMARC-passing emails and de-duplicating against existing leads.
Process the user's email inbox: triage everything unread, classify by importance, draft replies for things that need one, and produce an HTML report of what was handled.
Install Inbox Triage
$ npx skills add TheCraigHewitt/skills --skill inbox-triage -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install TheCraigHewitt/skills inbox-triage --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/TheCraigHewitt/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cowork/inbox-triage .claude/skills/inbox-triage && rm -rf skills-srcUse ~/.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/
Install the "inbox-triage" agent skill from https://github.com/TheCraigHewitt/skills/tree/main/cowork/inbox-triage into .claude/skills/inbox-triage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "inbox-triage", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/TheCraigHewitt/skills/tree/main/cowork/inbox-triageType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add TheCraigHewitt/skills --skill inbox-triage -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install TheCraigHewitt/skills inbox-triage --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/TheCraigHewitt/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/cowork/inbox-triage .agents/skills/inbox-triage && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "inbox-triage" agent skill from https://github.com/TheCraigHewitt/skills/tree/main/cowork/inbox-triage into .agents/skills/inbox-triage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "inbox-triage", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add TheCraigHewitt/skills --skill inbox-triage -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install TheCraigHewitt/skills inbox-triage --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/TheCraigHewitt/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/cowork/inbox-triage .cursor/skills/inbox-triage && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "inbox-triage" agent skill from https://github.com/TheCraigHewitt/skills/tree/main/cowork/inbox-triage into .cursor/skills/inbox-triage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "inbox-triage", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/TheCraigHewitt/skills.git --path cowork/inbox-triage--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add TheCraigHewitt/skills --skill inbox-triage -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install TheCraigHewitt/skills inbox-triage --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/TheCraigHewitt/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/cowork/inbox-triage .gemini/skills/inbox-triage && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "inbox-triage" agent skill from https://github.com/TheCraigHewitt/skills/tree/main/cowork/inbox-triage into .gemini/skills/inbox-triage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "inbox-triage", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install TheCraigHewitt/skills inbox-triageInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add TheCraigHewitt/skills --skill inbox-triage -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/TheCraigHewitt/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/cowork/inbox-triage .github/skills/inbox-triage && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "inbox-triage" agent skill from https://github.com/TheCraigHewitt/skills/tree/main/cowork/inbox-triage into .github/skills/inbox-triage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "inbox-triage", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add TheCraigHewitt/skills --skill inbox-triage -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install TheCraigHewitt/skills inbox-triage --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/TheCraigHewitt/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/cowork/inbox-triage .opencode/skills/inbox-triage && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "inbox-triage" agent skill from https://github.com/TheCraigHewitt/skills/tree/main/cowork/inbox-triage into .opencode/skills/inbox-triage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "inbox-triage", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
inbox-triage- GitHub stars
- 159
- Token cost
- ~1.4k tokens
- SKILL.md length
- 793 words
- Files
- 2
- Skills in repo
- 65
- Repo updated
- First seen
- Licence
- MIT
At a glance
Process the user's email inbox: triage everything unread, classify by importance, draft replies for things that need one, and produce an HTML report of what was handled.
- Works in 4 steps: Scan the user's last 50 sent emails to… → Scan the last 100 received emails to… → Ask the user to confirm: VIPs, urgent… → …
- Says triage my inbox
- SKILL.md covers Before you start, The triage pass, Reply drafting rules and The report, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Inbox Triage is an agent skill from TheCraigHewitt/skills. Process the user's email inbox: triage everything unread, classify by importance, draft replies for things that need one, and produce an HTML report of what was handled. Use this whenever the user says 'triage my inbox,' 'process my email,' 'clean up my inbox,' 'go through my emails,' 'draft replies for me,' 'inbox zero,' 'what emails need a reply,' or asks you to handle, scan, summarize, or respond to email. Also use when the user wants to set this up as a recurring scheduled task (e.g., 3x a day inbox sweeps)…
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `evals/evals.json`).
It sits in Productivity & Automation, covering Email management. It works with Gmail. The repository describes itself as: AI skills for founders, sales teams, and creators. 47 skills across CEO, Sales, YouTube, and General categories. Works with Claude Code, Cursor, Codex, and any agent that reads… The licence is MIT.
When your agent uses it
- Says triage my inbox
- Process my email
- Clean up my inbox
- Go through my emails
Example prompts
- “triage my inbox,”
- “process my email,”
- “clean up my inbox,”
- “/inbox-triage”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Scan the user's last 50 sent emails to learn voice and typical reply length
- Scan the last 100 received emails to identify top senders and patterns
- Ask the user to confirm: VIPs, urgent triggers, skip list
- Write inbox-config.md so this only runs once
What it can do on your machine
Read from SKILL.md and the folder at commit fdbf39b. 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
Inbox Triage loads about 1.4k tokens when it runs. Until then it costs about 139 tokens; SKILL.md has 793 words of instructions outside code blocks.
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 TheCraigHewitt/skills at commit fdbf39b, republished under its MIT licence (© TheCraigHewitt). 793 words, ~1,373 tokens.
Download SKILL.mdSave it as
.claude/skills/inbox-triage/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- inbox-triage
- description
- Process the user's email inbox: triage everything unread, classify by importance, draft replies for things that need one, and produce an HTML report of what was handled. Use this whenever the user says 'triage my inbox,' 'process my email,' 'clean up my inbox,' 'go through my emails,' 'draft replies for me,' 'inbox zero,' 'what emails need a reply,' or asks you to handle, scan, summarize, or respond to email. Also use when the user wants to set this up as a recurring scheduled task (e.g., 3x a day inbox sweeps). Requires Gmail connector.
Inbox Triage
You process the user's email inbox, draft replies for what needs them, and produce a report. The goal: the user opens Gmail, finds drafts waiting in everything that mattered, and can spend 10 minutes on email instead of 90.
Before you start
Check for inbox-config.md in the working folder. If it exists, it should define:
- The user's voice (samples of past replies, tone preferences)
- Sender importance tiers (VIPs, clients, internal, vendors, newsletters, cold)
- What "urgent" means (client issues? investor asks? family?)
- Rules for what to skip (newsletters, auto-receipts, no-reply addresses)
- Reply length defaults (short by default, long for specific senders)
If it doesn't exist, run a one-time setup:
- Scan the user's last 50 sent emails to learn voice and typical reply length
- Scan the last 100 received emails to identify top senders and patterns
- Ask the user to confirm: VIPs, urgent triggers, skip list
- Write
inbox-config.mdso this only runs once
The triage pass
For each unread email in the last 24 hours (or the time window the user specifies), classify it:
- Reply — needs a real response
- Quick reply — needs a short acknowledgment (1–3 lines)
- Flag — user must read but doesn't need to reply
- FYI — informational, no action
- Archive — newsletters, receipts, notifications, anything safely ignored
- Spam / suspicious — flag separately, don't draft anything
For each "Reply" and "Quick reply," draft a response in the user's voice and save it as a Gmail draft. Do not send. The user reviews and sends.
Reply drafting rules
- Match their voice. Read sent-email samples first. If they write short, you write short. If they sign off "—C", you sign off "—C". Don't add "Best regards" or other patterns that aren't in their samples.
- Be specific. Generic "Thanks for reaching out" replies are worse than no draft. If you don't have enough context to draft a real reply, classify as Flag instead.
- Move things forward. Every reply should either answer a question, propose a next step, or buy time with a specific commitment ("I'll come back to this by Friday").
- Don't commit on their behalf. If a reply requires the user to actually decide something (yes/no on a deal, agreeing to a meeting, approving a budget), draft a placeholder that they can fill in — don't put words in their mouth.
- Note when you punted. In the report, flag any email you couldn't draft a reply for and explain why.
The report
Save to inbox-report-YYYY-MM-DD-HHMM.html. Structure:
Top strip: counts — total processed, drafts created, flagged for read, archived.
Drafts created — table: | Sender | Subject | Why it matters | Your draft (preview) |
Flagged for your attention — emails that need the user to read but you didn't draft (because they need to decide something only they can).
Pattern observations — once a week or so, surface things like: "You've been flagging emails from [sender] for 3 weeks and not replying — want me to send a holding email?" or "5 emails this week mention [topic] — worth a single broadcast reply?"
What I skipped — counts only, no detail (newsletters, receipts, etc.)
Show full SKILL.md (286 more words)Show less
Running on a schedule
This is one of the best skills to schedule. Suggest:
"Want me to run this 2–3 times a day — say 9am, 1pm, and 5pm? You'll have drafts waiting whenever you open Gmail."
If the user agrees, set up a recurring task and have it post to Slack on completion (e.g., "Inbox triage done — 12 drafts in your Gmail, 3 flagged for read").
Edge cases
- Thread context — if an email is part of a long thread, read the last 3–5 messages before drafting so the reply lands in the right beat.
- Attachments — if an email has an attachment that affects the reply (a contract, a deck, a spreadsheet), pull it in and read it before drafting.
- People you haven't replied to in a while — if the sender is someone the user has previously prioritized but the relationship has gone cold, flag it explicitly.
- Sensitive senders — for emails from family, investors, board members, or anyone in a small "draft for me only with extreme care" list defined in config, draft very briefly and flag for user review rather than producing a polished reply.
Rules
- Never send. Always draft. The user sends.
- Speed matters. A same-day triage with 80% accuracy beats a perfect one that arrives a day late.
- Match length to sender. Cold outreach gets 2 lines. Best customer gets a real reply. Investor update gets thought.
- Don't apologize in drafts. Skip "Sorry for the delay" unless it's literally a month overdue — it sets a bad pattern.
- Stay calm under volume. If there are 200 unread emails, don't try to process all of them — pick the most recent + the highest-priority senders, and tell the user you batched the rest.
© TheCraigHewitt, 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 in cowork/inbox-triage of TheCraigHewitt/skills.
- SKILL.md
- evals/evals.json
Open the folder on GitHubat commit fdbf39b
Compare with similar skills
Inbox Triage 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Inbox Triage this skillTheCraigHewitt/skills | 159 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Career-Ops Gmail Lead Plugincareer-ops-hq/career-ops | 74k | — | ~233 | Automated safety check: Notes | MIT | |
| Gmailteam-attention/plugins-for-claude-natives | 827 | — | ~967 | Automated safety check: Pass | MIT | |
| Connect Apps with ComposioComposioHQ/awesome-claude-skills | 77k | 3 repos | ~557 | Automated safety check: Pass | None | |
| Gmail Emailopen-gitagent/gitagent | 714 | — | ~235 | Automated safety check: Notes | MIT | |
| Google Workspaceyc-software/qm | 15k | — | ~1.8k | Automated safety check: Pass | MIT |
Similar skills
Gmail
team-attention/plugins-for-claude-natives
This skill should be used when the user asks to "check email", "read emails", "send email", "reply to email", "search inbox", or manages Gmail.
Connect Apps with Composio
ComposioHQ/awesome-claude-skills
Connects an agent to 1000+ external apps through the Composio Tool Router plugin, so it can actually send emails, create issues and post messages instead of only drafting them.
Gmail Email
open-gitagent/gitagent
Send emails via Gmail SMTP using App Password authentication.
Google Workspace
yc-software/qm
Read and act on the user's Gmail, Google Calendar, and Google Tasks through per-user OAuth.
Gmcli
badlogic/pi-skills
Gmail CLI for searching emails, reading threads, sending messages, managing drafts, and handling labels/attachments.
More from TheCraigHewitt/skills
All 65 skills in this repoCarousels
TheCraigHewitt/skills
Turns a piece of Craig's content (an email, a YouTube script, an essay, or pasted text) into a polished image carousel publishable to both LinkedIn and Instagram from one set of 1080x1350 slides.
Audience Research
TheCraigHewitt/skills
When the user wants to understand their YouTube audience, mine viewer psychology, analyze demographics, or find content-market fit signals.
Brain Dump
TheCraigHewitt/skills
Take a messy stream-of-consciousness dump from the user (typed or transcribed from voice) and turn it into a structured set of projects, tasks, and connections to existing work.
Channel Audit
TheCraigHewitt/skills
When the user wants a full YouTube channel health check, growth diagnosis, strategic review, or wants to identify why their channel is stalling.
Channel Strategy
TheCraigHewitt/skills
When the user wants to define or refine their YouTube channel strategy, niche positioning, content pillars, or growth plan.
Cold Call
TheCraigHewitt/skills
When the user wants to write cold call scripts, handle phone objections, plan dial blocks, or craft voicemails.
Related
Works with
Categories
Questions about Inbox Triage
What does Inbox Triage do?
Process the user's email inbox: triage everything unread, classify by importance, draft replies for things that need one, and produce an HTML report of what was handled. Inbox Triage is an agent skill from TheCraigHewitt/skills. Process the user's email inbox: triage everything unread, classify by importance, draft replies for things that need one, and produce an HTML report of what was handled.
When should I use Inbox Triage?
Inbox Triage fits situations like: says triage my inbox; process my email; clean up my inbox; go through my emails.
How do I install Inbox Triage in Claude Code?
Run `npx skills add TheCraigHewitt/skills --skill inbox-triage -a claude-code`. Or copy the skill folder (cowork/inbox-triage in TheCraigHewitt/skills) into .claude/skills/inbox-triage in your project. Claude Code loads it when a task matches its description.
How do I install Inbox Triage in Codex?
Run `npx skills add TheCraigHewitt/skills --skill inbox-triage -a codex`. Or copy the skill folder (cowork/inbox-triage in TheCraigHewitt/skills) into .agents/skills/inbox-triage in your project. Codex loads it when a task matches its description.
Can I use Inbox Triage 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 TheCraigHewitt/skills --skill inbox-triage -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/inbox-triage, .gemini/skills/inbox-triage, .github/skills/inbox-triage and .opencode/skills/inbox-triage in your project.
What does Inbox Triage need to run?
SKILL.md names no scripts, command-line tools or credentials: Inbox Triage is instructions for the agent only.
Does Inbox Triage 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 Inbox Triage 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 Inbox Triage use?
Inbox Triage 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 Inbox Triage use?
About 1.4k tokens (SKILL.md is roughly 5.5k 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 Inbox Triage?
Skills that share tags, products or a category with Inbox Triage: Career-Ops Gmail Lead Plugin (career-ops-hq/career-ops, 74k stars), Gmail (team-attention/plugins-for-claude-natives, 827 stars), Connect Apps with Composio (ComposioHQ/awesome-claude-skills, 77k stars) and Gmail Email (open-gitagent/gitagent, 714 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Inbox Triage?
TheCraigHewitt (a GitHub user) maintains it in TheCraigHewitt/skills, which has 159 GitHub stars. The repository holds 65 skills in this directory. The repository was last updated on May 22, 2026.
Source: TheCraigHewitt/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.