skills/academic-letter-architect/SKILL.md
Guides the creation of evidence-based academic recommendation letters, reference letters, and award nominations that combine concrete examples, meaningful comparisons, and genuine enthusiasm. Use when writing recommendation letters for students, postdocs, or colleagues, or when user mentions recommendation letter, reference, nomination, letter of support, endorsement, or needs help with strong advocacy and comparative statements.
npx skillsauth add lyndonkl/claude academic-letter-architectInstall 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 (use instead for):
career-document-architectscientific-email-polishinggrant-proposal-assistant1. Show, don't tell: Concrete examples beat adjectives
2. Comparisons give context: Readers need reference points
3. Enthusiasm is evidence: Tone conveys conviction
4. Address what matters: Match content to opportunity
Copy this checklist and track your progress:
Letter Architect Progress:
- [ ] Step 1: Gather context (candidate, opportunity, relationship)
- [ ] Step 2: Collect evidence (specific examples, achievements)
- [ ] Step 3: Draft opening (credibility, relationship, expectation)
- [ ] Step 4: Build body (evidence paragraphs, comparisons)
- [ ] Step 5: Craft closing (strong endorsement, availability)
- [ ] Step 6: Calibrate tone (enthusiasm level, superlatives)
- [ ] Step 7: Final polish (length, format, signature)
Step 1: Gather Context
Identify: Who is the candidate? What opportunity? Your relationship (advisor, collaborator, instructor)? How long have you known them? In what capacity? See resources/methodology.md for information checklist.
Step 2: Collect Evidence
List 3-5 specific examples demonstrating excellence: Research achievements, intellectual contributions, professional qualities, overcoming challenges. Quantify where possible. See resources/methodology.md for evidence types.
Step 3: Draft Opening
Establish your credibility (position, experience). State relationship to candidate (role, duration, context). Set expectation (strong recommendation signal). See resources/template.md for opening structure.
Step 4: Build Body
Structure evidence into 2-4 paragraphs covering different dimensions (research, intellect, character). Include comparative statements ("top 5%", "best I've seen"). Connect evidence to opportunity requirements. See resources/template.md for paragraph templates.
Step 5: Craft Closing
Provide unambiguous endorsement statement. Offer availability for follow-up. Include professional signature with title/contact. See resources/template.md for closing structure.
Step 6: Calibrate Tone
Ensure enthusiasm matches actual assessment. Check superlative use (too many dilutes impact). Verify letter reads as advocacy, not obligation. See resources/methodology.md for calibration guide.
Step 7: Final Polish
Check length (typically 1-2 pages). Ensure formal formatting. Verify all specific claims are accurate. Validate using resources/evaluators/rubric_academic_letter.json. Minimum standard: Average score ≥ 3.5.
Purpose: Establish credibility and relationship
Elements:
1. Your identity and position
2. How you know the candidate (role, context)
3. Duration of relationship
4. Capacity of observation (direct supervision, collaboration)
5. Clear statement of recommendation
Example: "I am writing to provide my strongest recommendation for Dr. Jane Smith for the position of Assistant Professor. As the Director of the Structural Biology Center at X University, I have had the privilege of working closely with Jane for the past four years, first as her postdoctoral mentor and subsequently as a research collaborator. During this time, I have observed her exceptional scientific abilities, intellectual creativity, and professional maturity firsthand."
Purpose: Provide evidence-based assessment
Paragraph 1: Research/Technical Excellence
Paragraph 2: Intellectual Contributions
Paragraph 3: Professional Qualities
Paragraph 4: Comparative Assessment
Purpose: Summarize and endorse
Elements:
1. Overall assessment statement
2. Specific recommendation (enthusiastic, unambiguous)
3. Prediction for future success
4. Offer of availability for follow-up
5. Professional sign-off
Example: "In summary, Jane is an outstanding scientist with exceptional research abilities, intellectual depth, and professional maturity. I give her my highest and most enthusiastic recommendation without reservation. She will make an excellent faculty member and I am confident she will develop an impactful, independent research program. Please do not hesitate to contact me if you require any additional information."
Highest ("absolutely top"):
Strong ("top tier"):
Moderate ("good but not stellar"):
Lukewarm (damaging):
Strong comparisons:
Weak comparisons (avoid):
| Vague (Weak) | Specific (Strong) | |--------------|-------------------| | "Productive researcher" | "Published 5 first-author papers including 2 in Nature journals" | | "Good communicator" | "Regularly invited to present at lab meetings and gave a talk at the Gordon Conference" | | "Works well with others" | "Mentored 3 undergraduate students, all of whom went to top graduate programs" | | "Technically skilled" | "Independently established our lab's CRISPR screening platform" |
Key requirements:
Truthfulness: Only write what you genuinely believe. Dishonest letters harm candidates and your reputation.
Evidence-based: Every claim should have a supporting example. "Smart" means nothing without evidence.
Appropriate comparison: Compare to relevant reference class (other postdocs, not all scientists ever).
Match content to opportunity: Emphasize research for academic jobs, practical skills for industry.
Candidate voice preservation: Reflect the candidate's actual achievements, not fabricated ones.
Cultural awareness: US letters are more superlative than other cultures. Calibrate appropriately.
Common pitfalls:
Key resources:
Letter length guidelines:
Information to gather from candidate:
Time estimates:
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.