一键导入
email-drafting
Draft professional emails in the appropriate tone and format for the recipient and desired outcome
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Draft professional emails in the appropriate tone and format for the recipient and desired outcome
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Host the memory-of-use ledger's schema/counting/status-vocabulary convention and the confirmed-proposal apply/verify/rollback/SECGATE machinery — the single, mandatory, deny-listed skill so this governing prose is reliably present from setup (Mode A + Mode B) and can never itself be an apply's target (ADR-061)
Host the skill-content pull flow — classify every installed curated skill via fresh-bytes-on-both-sides against the on-disk pool and the workspace's own install manifest, offer per-component updates with no silent overwrite, and stand as the mechanism that backfills the three mandatory safety skills (self-apply, self-archive, self-upgrade) into any workspace that runs this flow — Face 1 of the v2.19 Persistency Layer (KDQ-PULL), kept textually distinct from self-upgrade's engine-version Face 2 (ADR-072/073)
Host the auto-cleaning move-eligibility gate, destination gating, reversible-move-log rollback, and reference-integrity verification for proposing a stale/superseded file's relocation into the local archive convention — the sibling, mandatory, deny-listed skill to self-apply, holding the PATH-relocation operation type separately so neither module carries two verification concerns (ADR-066)
Host the kit-version walk-forward contract and the two-write-class self-integrity invariant (verify-then-swap on safety machinery) for replacing a workspace's own engine/framework machinery across kit versions — the third deny-listed sibling to self-apply/self-archive, dormant at v2.19 (zero real forward-walk targets) but installed and reachable now so no future rung has to backfill the gate (ADR-071)
[one sentence describing what this skill enables Cowork to do]
Run a periodic Collect, Process, Review, and Plan pass across workspace files to surface what's stalled, due, and worth prioritizing next week
| name | email-drafting |
| description | Draft professional emails in the appropriate tone and format for the recipient and desired outcome |
| tools | ["claude-code"] |
| trigger_examples | ["Draft an email declining the vendor's proposal professionally","Follow-up email after the meeting with the client team","Sensitive email to a client about a late delivery","Reply to this thread — match the tone"] |
Use email-drafting when the user needs a professional email written for a specific recipient and purpose: declining a request, following up, communicating a decision, handling sensitive correspondence, or matching an existing thread's tone. This skill calibrates formality to the recipient relationship and ensures the email structure serves the desired outcome. Use it any time the user has the intent but not the words — or when they have the words but not the structure.
Gather the three essential inputs. Before drafting, confirm: (a) the recipient and their relationship to the sender (internal colleague, external client, executive, vendor, someone you've never met); (b) the desired outcome — what should happen after the recipient reads the email; (c) any constraints on tone (e.g., "keep it warm but direct", "formal only", "can't seem defensive"). If the relationship and desired outcome are clear from context, proceed without asking.
Calibrate formality to the recipient relationship. Internal peer → conversational and direct. Executive → brief and outcome-focused. External client → professional but not stiff. Cold outreach → respectful and to-the-point. Vendor → transactional and clear. Do NOT over-formalize a casual recipient or under-formalize an executive.
For sensitive communications, flag before drafting. If the email involves difficult news, an apology, an escalation, or any content that could affect the relationship, state the tone choice you are making and ask for confirmation before presenting the draft. Do NOT draft sensitive content and present it as final without flagging.
Pre-send verification (4 items — check before presenting draft):
Draft with this structure. Subject line (output separately, before the body): specific and clear — not "Quick follow-up" or "Checking in". Opening: get to the point in the first sentence — state the purpose without preamble. Body: only what the recipient needs to act. Keep under 200 words unless the content requires more. Closing: clear call to action or next step — one specific ask, not a list.
Output subject line separately. Present the subject line on its own line before the email body. Label it Subject:. Do NOT embed the subject in the email body.
Offer a shorter variant if the draft exceeds 150 words. After the primary draft, offer a version trimmed to under 100 words unless brevity would omit essential information. Let the user choose.
Plain text formatted as an email draft. Structure: Subject: [line] → blank line → salutation → body → closing → signature placeholder. No JSON, no YAML, no markdown headers inside the email body. Output is copy-paste-ready for any email client.
Input: "Draft a follow-up email to a client who hasn't responded to our proposal in two weeks. Keep it warm but professional — they're a long-term relationship."
Output:
Subject: Following up on the [Project Name] proposal
Hi [Name],
I wanted to follow up on the proposal I sent two weeks ago. I know things get busy, so I wanted to make sure it didn't get buried.
Happy to answer any questions or adjust anything based on how your priorities have shifted. Let me know if now is still a good time to move forward, or if a quick call would help.
[Your name]
Shorter variant (82 words):
Subject: Quick follow-up — [Project Name] proposal
Hi [Name], following up on the proposal from two weeks ago — want to make sure it didn't get lost in the shuffle. Happy to answer questions or revisit the scope. Just let me know. [Your name]
Email-drafting consults context/writing-profile.md for two purposes: (1) applying documented register preferences to the email body (e.g., a profile that says "avoid hedging" produces a more direct draft); (2) matching documented phrase preferences or anti-patterns (e.g., "never start with 'I hope this email finds you well'"). The pre-send verification step and subject line are always profile-neutral — these are structural requirements, not voice choices.