skills/scientific-email-polishing/SKILL.md
Composes and polishes professional scientific correspondence -- emails to collaborators, journal cover letters, and responses to peer reviewers -- ensuring clear communication, appropriate tone, explicit asks, and professional formatting for academic contexts. Use when writing or polishing scientific emails, cover letters to editors, reviewer responses, or when user mentions email to collaborator, cover letter to journal, reviewer response, or professional scientific correspondence.
npx skillsauth add lyndonkl/claude scientific-email-polishingInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Related skills for other document types:
academic-letter-architectcareer-document-architectgrant-proposal-assistant1. One email, one purpose: Each email should have a clear, single objective
2. Explicit asks: State exactly what you need from the recipient and by when
3. Context first: Open with enough context for the reader to understand immediately
4. Professional but warm: Formal doesn't mean cold; collegial is appropriate
5. Scannable format: Busy recipients skim; use structure to aid quick reading
Copy this checklist and track your progress:
Email Polishing Progress:
- [ ] Step 1: Identify purpose and desired outcome
- [ ] Step 2: Draft subject line (clear, specific)
- [ ] Step 3: Write opening (context in first sentence)
- [ ] Step 4: Compose body (organized, scannable)
- [ ] Step 5: State explicit ask (what, by when)
- [ ] Step 6: Close professionally (next steps, sign-off)
- [ ] Step 7: Review tone (polite, appropriate)
Step 1: Identify Purpose and Outcome
What action do you want the recipient to take? What decision do you need? By when? If you can't state this clearly, the email isn't ready to send.
Step 2: Draft Subject Line
Subject should preview content and signal urgency/type. Be specific: "Meeting request: Collaboration on X project" not "Quick question". See resources/template.md for examples.
Step 3: Write Opening
First sentence should establish context. Who are you (if unknown), why are you writing, what's this about? No need for extensive pleasantries. See resources/template.md for openers.
Step 4: Compose Body
Organize information logically. Use short paragraphs. Consider bullets for multiple points. Bold key information if needed. Keep under 3-4 paragraphs for most emails.
Step 5: State Explicit Ask
Be clear about what you need. Include timeline if relevant. Make it easy to say yes. Don't bury the ask.
Step 6: Close Professionally
Thank them, indicate next steps, offer to provide more info. Use appropriate sign-off for relationship level. See resources/template.md for sign-offs.
Step 7: Review Tone
Read aloud. Is it polite but efficient? Not too casual, not too stiff? Appropriate for your relationship with recipient? Validate using resources/evaluators/rubric_email.json.
Purpose: Introduce manuscript, explain significance, suggest reviewers
Structure:
Subject: Submission: [Manuscript Title] - [Type: Original Research/Review/etc.]
Dear Dr. [Editor] / Dear Editors,
[PARAGRAPH 1: What and why]
Please find attached our manuscript entitled "[Title]" for consideration
as a [Article Type] in [Journal Name]. This work [brief significance statement].
[PARAGRAPH 2: What's new]
Our study [key finding/contribution]. This advances the field by [impact].
We believe this work will interest readers of [Journal] because [fit with
journal scope].
[PARAGRAPH 3: Practicalities]
The manuscript is [X] words with [Y] figures. All authors have approved
the submission and there are no conflicts of interest to declare. This
work has not been published elsewhere and is not under consideration
at another journal.
[OPTIONAL: Reviewer suggestions]
We suggest the following potential reviewers: [Names with institutions
and emails].
[CLOSING]
Thank you for your consideration. We look forward to hearing from you.
Sincerely,
[Corresponding Author]
Purpose: Address each point thoroughly and professionally
Structure:
Subject: Revised Manuscript [ID]: [Title]
Dear Dr. [Editor],
Thank you for the opportunity to revise our manuscript "[Title]". We
appreciate the thoughtful comments from the reviewers, which have
significantly improved our work. Below we provide point-by-point
responses to each comment. Reviewer comments are in italics, our
responses in plain text, and changes to the manuscript are noted.
---
REVIEWER 1
*Comment 1: [Quote reviewer comment]*
Response: [Your response]. We have [action taken]. This change appears
on page X, lines Y-Z.
*Comment 2: [Quote reviewer comment]*
Response: [Your response].
[Continue for all comments]
---
REVIEWER 2
[Same format]
---
We hope these revisions address the reviewers' concerns and that the
manuscript is now suitable for publication in [Journal]. Please do not
hesitate to contact us if additional revisions are needed.
Sincerely,
[Corresponding Author]
Purpose: Propose collaboration with new contact
Structure:
Subject: Collaboration opportunity: [Brief topic description]
Dear Dr. [Name],
I am [Your Name], a [position] at [Institution], working on [research area].
I am reaching out because [why them specifically - be genuine and specific].
[Brief background on your work and why collaboration makes sense]
I would be interested in [specific collaboration proposal]. This could involve
[what you're proposing - be concrete].
Would you be available for a brief call to discuss? I'm flexible on timing
and happy to work around your schedule.
Thank you for considering this. [Optional: note any mutual connection]
Best regards,
[Your Name]
| Recipient | Tone | Example Sign-off | |-----------|------|-----------------| | Unknown editor/senior | Formal | "Sincerely," "Respectfully," | | Known colleague (distant) | Professional-warm | "Best regards," "Best," | | Known colleague (close) | Warm-professional | "Best," "Thanks," | | Close collaborator | Friendly-professional | "Thanks," "Cheers," |
Too stiff:
"I am writing to inquire as to whether you might be available to provide guidance regarding..."
Too casual:
"Hey! Quick q - you free to chat about that thing?"
Just right:
"I'm reaching out to see if you'd have time to discuss [topic]. Would a brief call work for you next week?"
When declining:
When disagreeing (reviewer response):
When following up:
Key requirements:
Common pitfalls:
Key resources:
Subject line formulas:
Time estimates:
Before sending checklist:
Inputs required:
Outputs produced:
testing
Cluster a conference's event records into a small set of coarse themes with finer sub-clusters, an explicit outlier bucket, and soft (multi-membership) affinities — using the hybrid embed-then-label pipeline (embed abstracts, reduce, density-cluster, then LLM-label the clusters) when embedding libraries are available, and an LLM-reasoned hierarchical fallback when they are not. Embeddings do the grouping; the LLM only names the groups. Conference-agnostic. Use when turning structured event records into a navigable theme map for preference elicitation and scheduling, when you need 6-8 reasonable themes rather than 20 muddy ones, or when overlapping talks must belong to more than one theme. Trigger keywords - theme clustering, cluster talks, embed then label, soft membership, outlier talks, conference themes, topic map.
development
Build a personal conference schedule as a constraint-optimization problem — hard constraints (no time overlap, room-to-room travel time, capacity/registration, the attendee's own must-attends and blackouts) plus a user-owned weighted objective trading interest against breadth, pacing (maximize contiguous free time), and serendipity. Surfaces unbreakable conflicts (two high-value overlapping talks the model cannot rank) as decisions for the human rather than silently picking, and reports what each choice traded away. Conference-agnostic. Use to turn a preference profile plus a theme map into a day-by-day plan, to resolve overlapping sessions, or to balance a packed vs paced schedule. Trigger keywords - schedule optimization, conference schedule, constraint optimization, overlapping talks, contiguous free time, conflict surfacing, packed vs paced.
development
Parse a heterogeneous conference program (markdown, HTML, PDF-derived text, or JSON) into normalized event records with per-field confidence scores and independent classification axes (topic, depth, format, prerequisites, recorded, capacity). Detects the program's format before extracting, treats every inferred field as uncertain (present vs inferred vs missing), and flags thin or missing abstracts so downstream enrichment can target them. Conference-agnostic. Use when ingesting a conference or event schedule into a structured store, normalizing a talk/session list, or extracting per-session metadata with calibrated confidence. Trigger keywords - program ingestion, parse schedule, session extraction, event records, conference program, talk metadata, per-field confidence.
development
Build a personalized preference profile from a small number of well-chosen, cluster-grounded questions instead of a long survey. Represents the person's interests as an uncertainty region over the theme map, picks the single highest-information-gain choice-based question (contrasting real talks from different clusters), balances exploiting known interests against exploring uncertain ones, deliberately injects outlier probes to fight selection bias, and stops as soon as the schedule would be stable. Also elicits the user-owned objective weights and hard constraints. Interactive — runs where it can actually ask the person. Conference-agnostic. Use to turn a theme map into a preference profile, to decide what to ask a conference attendee, or to elicit scheduling priorities. Trigger keywords - preference elicitation, ask few questions, information gain, choice-based questions, selection bias probe, objective weights, attendee preferences.