skills/career-document-architect/SKILL.md
Guides the creation of career documents for academic advancement including research statements, teaching statements, diversity statements, CVs, and biosketches. Combines strategic positioning, narrative coherence, and institutional alignment with authentic representation of contributions and vision. Use when writing or reviewing faculty applications, fellowship statements, promotion packages, award applications, or when user mentions research statement, teaching philosophy, diversity statement, biosketch, academic CV, or career narrative.
npx skillsauth add lyndonkl/claude career-document-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):
grant-proposal-assistantacademic-letter-architectscientific-manuscript-review1. Vision + Track Record: Show where you're going AND what you've accomplished
2. Coherent Narrative: All pieces should tell a unified story
3. Audience Awareness: Tailor depth and framing to readers
4. Evidence-Based Claims: Support assertions with specifics
5. Future-Oriented: Emphasize trajectory and potential
6. Authentic Voice: Represent yourself genuinely
Copy this checklist and track your progress:
Career Document Progress:
- [ ] Step 1: Identify document type and audience
- [ ] Step 2: Gather raw materials (CV, accomplishments)
- [ ] Step 3: Develop core narrative thread
- [ ] Step 4: Draft document using appropriate framework
- [ ] Step 5: Add evidence and specifics
- [ ] Step 6: Align with institutional expectations
- [ ] Step 7: Polish and format
Step 1: Identify Type and Audience
Determine document type (research/teaching/diversity statement, CV, biosketch). Identify audience (search committee, review panel). Note any specific requirements (page limits, format specifications). See resources/methodology.md for audience considerations.
Step 2: Gather Raw Materials
Compile: Current CV, publications, grants, teaching evaluations, mentorship record, outreach activities, preliminary data, future plans. See resources/methodology.md for comprehensive list.
Step 3: Develop Core Narrative
Identify the through-line connecting your work. What question drives you? What impact do you seek? How does past work connect to future plans? See resources/methodology.md for narrative construction.
Step 4: Draft Using Framework
Select appropriate framework for document type. Follow structure that matches institutional norms. See Document Frameworks for each type.
Step 5: Add Evidence and Specifics
Replace generic claims with specific accomplishments. Quantify where possible (papers, citations, students mentored). Add concrete examples for abstract claims.
Step 6: Align with Institution
Research institution's priorities. Emphasize fit without fabricating. Address how you contribute to their mission. See resources/methodology.md for alignment strategies.
Step 7: Polish and Format
Check length constraints. Ensure consistent formatting. Proofread carefully. Validate using resources/evaluators/rubric_career_document.json. Minimum standard: Average score ≥ 3.5.
Purpose: Articulate research vision, demonstrate independence, show future potential
Length: Typically 2-5 pages (check requirements)
Structure:
OPENING (1 paragraph)
- Hook: Compelling statement of your research focus
- Big picture: Why this matters to the field/society
- Your role: How you contribute to addressing this
PAST RESEARCH (1-2 pages)
- Organize by themes, not chronology
- Highlight key contributions with impact
- Show how past work builds foundation for future
- Include quantifiable outcomes (papers, citations, methods)
CURRENT RESEARCH (0.5-1 page)
- Ongoing projects and preliminary results
- Bridge between past and future
- Show productivity and momentum
FUTURE DIRECTIONS (1-2 pages)
- 2-3 specific research directions
- For each: Why important? What's the approach? What's expected impact?
- Show independence and creativity
- Connect to fundable questions (NIH/NSF relevance)
CLOSING (1 paragraph)
- Synthesis: How pieces fit together
- Why this institution/department
- Broader impact statement
Purpose: Articulate teaching philosophy and demonstrate effectiveness
Length: Typically 1-2 pages
Structure:
PHILOSOPHY (1-2 paragraphs)
- Core beliefs about teaching/learning
- What makes your approach distinctive
- Grounded in evidence or experience
EVIDENCE OF EFFECTIVENESS (1-2 paragraphs)
- Courses taught with enrollments
- Teaching evaluations (quote specific feedback)
- Student outcomes (publications, placements)
- Innovations introduced
METHODS AND APPROACHES (1-2 paragraphs)
- Specific techniques you use
- Active learning strategies
- Assessment approaches
- Technology integration
MENTORSHIP (1 paragraph)
- Undergraduate/graduate mentoring
- Student achievements
- Mentoring philosophy
FUTURE TEACHING (1 paragraph)
- Courses you could teach
- New courses you'd develop
- Curricular contributions
Purpose: Demonstrate commitment to diversity, equity, and inclusion
Length: Typically 1-2 pages
Structure:
INTRODUCTION (1 paragraph)
- Your understanding of DEI in academia
- Why it matters to you
- Preview of your contributions
PAST ACTIONS (1-2 paragraphs)
- Specific activities promoting DEI
- Mentoring underrepresented students
- Curriculum development
- Outreach activities
- Quantify impact where possible
PERSONAL CONTEXT (optional, 1 paragraph)
- Your own background if relevant
- Experiences informing your commitment
- Only include if comfortable and genuine
FUTURE PLANS (1 paragraph)
- How you'll contribute at this institution
- Specific programs or initiatives
- Connection to institutional DEI priorities
CLOSING
- Synthesis of commitment
- Why this matters for your field
Standard Sections:
CONTACT INFORMATION
EDUCATION
- Degrees in reverse chronological order
- Institution, degree, year, advisor (for PhD)
POSITIONS
- Academic appointments
- Industry positions (if relevant)
PUBLICATIONS
- Peer-reviewed (mark * for corresponding author)
- Preprints
- Reviews/Book chapters
GRANTS AND FUNDING
- Current and past funding
- Role (PI, Co-PI, etc.)
- Amount and duration
HONORS AND AWARDS
PRESENTATIONS
- Invited talks
- Conference presentations
TEACHING
- Courses taught
- Mentoring record
SERVICE
- Editorial boards
- Review panels
- Committee work
PROFESSIONAL MEMBERSHIPS
Length: 5 pages maximum
Sections:
A. PERSONAL STATEMENT (0.5 page)
- Why you're well-suited for this project
- Relevant experience and expertise
- Key accomplishments that qualify you
- Up to 4 publications supporting this statement
B. POSITIONS, SCIENTIFIC APPOINTMENTS, AND HONORS
C. CONTRIBUTIONS TO SCIENCE (up to 5 contributions, 0.5 page each)
- Contribution 1:
- Description of contribution (1 paragraph)
- Your specific role
- Impact on field
- Up to 4 publications supporting this contribution
- [Repeat for each contribution]
D. RESEARCH SUPPORT
- Current (with role, title, dates, description)
- Completed (last 3 years)
For every claim, ask "so what?" If you can't answer, the claim needs more:
| Claim | So What? | Improved | |-------|----------|----------| | "I published 10 papers" | Impact? | "My 10 papers have been cited 500 times, including 3 that established new methods in the field" | | "I'm passionate about teaching" | Evidence? | "My passion for teaching is reflected in consistent evaluation scores above 4.5/5 and 5 undergraduates who went to PhD programs" | | "I'm committed to diversity" | What have you done? | "I co-founded a mentoring program that has supported 20 students from underrepresented groups" |
| Telling (Weak) | Showing (Strong) | |----------------|------------------| | "I am a productive researcher" | "I have published 15 peer-reviewed articles including 3 in high-impact journals" | | "I am an effective teacher" | "Student evaluations average 4.7/5.0 with comments highlighting my use of active learning" | | "I am committed to mentoring" | "I have mentored 8 undergraduates, 5 of whom are now in PhD programs" |
For each future direction:
Key requirements:
Common pitfalls:
Key resources:
Typical lengths: | Document | Typical Length | |----------|----------------| | Research Statement | 2-5 pages | | Teaching Statement | 1-2 pages | | Diversity Statement | 1-2 pages | | NIH Biosketch | 5 pages max |
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.