Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add boshi-xixixi/TraeSkill --skill email-draftergit clone --depth 1 https://github.com/boshi-xixixi/TraeSkillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/boshi-xixixi/traeskill/email-drafter)<a href="https://agentmods.dev/skills/boshi-xixixi/traeskill/email-drafter"><img src="https://agentmods.dev/badge/skills/boshi-xixixi/traeskill/email-drafter/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/boshi-xixixi/traeskill/email-drafter"><img src="https://agentmods.dev/badge/skills/boshi-xixixi/traeskill/email-drafter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00073 | $0.01003 |
| Opus 5 | $0.00036 | $0.00502 |
| Sonnet 5 | $0.00015 | $0.00201 |
| Haiku 4.5 | $0.00007 | $0.00100 |
Grade A, and why
email-drafter scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Email Drafter
Draft professional emails that match your established writing style and tone. Uses WorkIQ to analyze your sent emails and prior correspondence with recipients, then produces context-aware drafts you can review and refine.
When to Use
- "Draft an email to [person] about [topic]"
- "Write a follow-up email to [customer] regarding [project]"
- "Reply to [person]'s email about [subject]"
- "Compose a proposal email for [initiative]"
- "Analyze my email tone with [recipient]"
Workflow
Step 1 — Gather Context
Before drafting, collect:
- Recipient(s) — who is the email for?
- Purpose — what is the email about? (proposal, follow-up, technical guidance, introduction, status update, etc.)
- Key points — what needs to be communicated?
- Relationship context — use WorkIQ to check prior email history with the recipient if available
If the user provides all of these upfront, proceed directly. Otherwise, ask clarifying questions (max 3).
Step 2 — Analyze Tone
When drafting for a recipient, use WorkIQ to understand the user's established communication patterns:
- Pull 3–5 recent sent emails from the user to the same recipient or similar recipients
- Identify patterns:
- Greeting style — formal ("Dear"), standard ("Hello"), casual ("Hi"), or direct (no greeting)
- Structure — short paragraphs vs. bullet lists vs. numbered steps
- Sign-off — what closing and name format the user typically uses
- Formality level — professional, friendly-professional, casual
- Language — which language the user writes in with this recipient
- Apply those patterns to the draft
If WorkIQ is unavailable or no prior emails exist, use sensible professional defaults and note that the tone was inferred.
Step 3 — Draft the Email
Apply the discovered (or default) style rules:
Greeting:
- Match whatever greeting style was found in Step 2
- Default: "Hello [FirstName]," for external, "Hi [FirstName]," for internal
- For multiple recipients: "Hello [Name1], [Name2],"
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 101 lines · 73 tokens per session scan A c3324d26f899
email-drafter is a skill published in the GitHub repository boshi-xixixi/TraeSkill (263 stars, last pushed 4mo ago), licensed MIT. It adds 73 tokens to every session and 1,003 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
vaultr-notes
Guide for working with Vaultr, an AI-native personal note-taking system. Use this skill whenever the user wants to search, find, read, write, save, create, modify, delete, or capture notes — including journal entries, research notes, quick thoughts, knowledge retrieval, or any note-taking task. Trigger when the user…
break-big-questions-into-steps
Divide a complex question into manageable subtasks with clear dependencies and intermediate results.
iterate-step-by-step
How to use the 4-Turn Conversational Scaffolding framework to build complex code, strategy, and content incrementally without token exhaustion or quality degradation.
notion
Notion API via curl: pages, databases, blocks, search.
stream-chain
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows. Use when piping output between agents/tools as streaming JSON or building a sequential transform pipeline.
knowledge-discovery
Discover relevant skills and knowledge using tiered approach. SKIP for simple tasks, QUICK for single-skill, STANDARD for multi-skill, DEEP for full feature implementation. Auto-selects tier based on task complexity.