AGENT SKILL

biosketch-craft

Writing biosketches that build reviewer confidence — personal statement, contributions, and honest positioning.

License 许可
MIT
所属仓库
TanNhatCMS/jarvis
最近更新
2026-11-07
Stars
★ 0
Forks
1

01 前言 Front Matter

name
biosketch-craft
category
scientific
description
Writing biosketches that build reviewer confidence — personal statement, contributions, and honest positioning.

03 SKILL.md 正文

Overview

The biosketch answers the reviewer's unspoken question: "Can this team actually do this work?" This skill covers the NIH-style biosketch (personal statement, positions, contributions to science, support), writing contribution narratives that show trajectory rather than list papers, and positioning yourself honestly for the proposed project.

When to use

  • Writing or updating an NIH/NSF biosketch for a proposal
  • Crafting the personal statement to connect your history to this project
  • Selecting which contributions and publications to highlight
  • Positioning early-career investigators (and addressing thin track records)
  • Reviewing a team's biosketches for gaps before submission

Core concepts

  • The confidence question: every element should build the case that you have the skills, track record, and resources for this specific project — generic excellence is less persuasive than specific fit.

  • Personal statement as narrative: 1 paragraph connecting your background to the proposed work — not a CV summary, a story: "My lab developed X (refs), which positions us to do Y proposed here because Z."

  • Contributions, not publications: the "Contributions to Science" section wants 3–5 thematic contributions with your role made explicit — what you discovered/built, why it mattered, with 3–4 key citations each.

  • Role clarity: "led", "co-led", "developed the method", "supervised" — reviewers discount middle-author papers without stated roles; claim your actual contribution precisely.

  • Team completeness: the set of biosketches must cover every method in the proposal — a missing expertise area is a feasibility ding; add collaborators or consultants to fill gaps deliberately.

  • Honesty constraints: no embellishment of roles, no double-counting, complete other support (overlap disclosure) — biosketch misrepresentation is misconduct territory, not marketing.

  • The personal statement as narrative: connect the dots — "my work on X led to Y, which positions me to do Z in this proposal" — not a list of positions; reviewers remember stories, not CVs.

  • Contributions over publications: the contributions section should show a trajectory of solving increasingly important problems — five disconnected papers read as five disconnected ideas.

  • Synergistic activities: service, mentoring, software, datasets, and community resources count — especially for early-career applicants, they show you're building the field, not just publishing in it.

Practical workflow

1. Draft the personal statement

  1. Open with your relevant expertise in one sentence; connect 2–3 past achievements to the proposed work's specific demands.
  2. Name the unique assets you bring: methods you pioneered, datasets you control, collaborations you hold.
  3. For early-career: emphasize training, first-author work, and the mentor/collaborator network that de-risks the project — acknowledge the stage, then neutralize it.

2. Write contributions as stories

  1. Pick 4–5 contributions that collectively cover the proposal's methods — each with: the problem, what you did (your role explicit), the outcome/impact, 3–4 citations.
  2. Order by relevance to this proposal, not chronology — the reviewer reads for fit.
  3. Include a methods/tool contribution if the proposal leans on your technical innovation — "I built the instrument this project runs on" is powerful.

3. Assemble the supporting sections

  1. Positions and honors: reverse chronological, complete — gaps invite questions; explain career breaks briefly and factually if needed.
  2. Publications: selected, relevant, with your role clear — quality and relevance beat quantity; don't pad with unrelated papers.
  3. Research support: ongoing and completed (recent 3 years typically) — show it's related but not overlapping; disclose overlaps explicitly with explanations of distinct aims.

4. Review as a team

  1. Lay all key-personnel biosketches side by side: does every proposed method have a named expert? Fill gaps with collaborators now, not after review.
  2. Check consistency: effort levels match the budget; roles match the narrative's description of who does what.
  3. Update or perish: a biosketch more than a year old signals staleness — refresh contributions and support every submission.

5. Tailor the biosketch to the proposal

  1. Reorder contributions to lead with the work most relevant to this proposal — relevance beats chronology.
  2. In the personal statement, name the specific expertise each aim requires and map it to your (or the team's) track record — leave no aim's feasibility to implication.
  3. For team proposals, ensure complementary — not overlapping — expertise across biosketches; redundancy wastes space that could cover gaps.

6. Quick-reference checklist

  • [ ] Personal statement tells the story: X → Y → positions me for Z
  • [ ] Contributions ordered by relevance to this proposal
  • [ ] Track record mapped explicitly to each aim's required expertise
  • [ ] Statement tailored to this proposal (not a generic swap)
  • [ ] Synergistic activities show field-building, not just publishing
  • [ ] Complementary (not overlapping) expertise across team biosketches
  • [ ] Roles clarified on large consortium papers
  • [ ] Current format requirements of the funder followed

Common pitfalls

  • Generic personal statements: "Dr. X is an expert in Y with 50 publications" — says nothing about fit to this project; rewrite as a targeted narrative.
  • Contribution vagueness: listing papers without stating what you contributed — reviewers can't credit what they can't see.
  • Padding: unrelated publications, honorary authorships presented as leadership — dilutes the real signal.
  • Missing expertise: proposing single-cell/spatial/AI methods with no team member who's done them — the #1 feasibility killer.
  • Stale biosketches: 3-year-old support sections, missing recent key papers — suggests the application was assembled carelessly.
  • Overlap blindness: undisclosed scientific/budgetary overlap across grants — disclose and differentiate proactively.
  • The generic personal statement: one statement reused across five proposals with the title swapped — reviewers can tell; tailor it.
  • Padding with minor roles: listing large consortium papers where your role was peripheral without clarifying — it dilutes the real contributions; be honest about roles.

04 同仓库更多 Skills

TanNhatCMS
TanNhatCMS/jarvis

web-scrape

Turn web pages into LLM-ready markdown via the Firecrawl API (renders JS, anti-bot handling). Use when browser_open/fetch fails on JS-heavy pages, or when you need clean markdown/structured extraction from a site. Requires FIRECRAWL_API_KEY.

★ 0
TanNhatCMS
TanNhatCMS/jarvis

design-taste-frontend

tasteskill v2, the anti-slop frontend skill. Art direction for websites, distilled from a study of 247 curated gallery sites (One Page Love, Awwwards Sites of the Day). Deals researched directions (idea, composition, type, palette, photographs, section blueprints) from a library, enforces a strict no-slop house style with a real-browser inspector, and runs a look-and-fix loop on screenshots. Use this whenever you build, design, redesign, restyle, polish or review a landing page, marketing site, portfolio, product page, one-pager, hero or any public-facing web page, in any stack (HTML/CSS, React, Next.js, Vue, Svelte, Astro, Tailwind) — also when the user says a page looks generic, templated, "AI-made", sloppy, or asks to make it look designed, premium, award-level or less like every other site. Not for dashboards or app screens.

★ 0
TanNhatCMS
TanNhatCMS/jarvis

test-driven-development

Use when implementing any feature or bugfix, before writing implementation code

★ 0
TanNhatCMS
TanNhatCMS/jarvis

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

★ 0
TanNhatCMS
TanNhatCMS/jarvis

requesting-code-review

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

★ 0
TanNhatCMS
TanNhatCMS/jarvis

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).

★ 0