Use this skill whenever a user needs help writing, drafting, revising, or structuring a grant proposal, funding application, or dissertation prospectus for anthropological research. Triggers include: any mention of NSF, Wenner-Gren, Fulbright, ERC, SSHRC, Wellcome, or other research funders in the context of anthropology or ethnographic research; requests to write a Project Description, research narrative, budget justification, broader impacts statement, or specific aims page; requests to draft or revise a dissertation prospectus or fieldwork grant; questions about how to frame ethnographic methods for a grant committee; requests to translate a research plan into a funder-specific format. Also use when the user mentions "grant writing," "proposal writing," "funding application," or "fellowship application" in the context of anthropology, sociology, STS, or other social science fieldwork research. Do NOT use for general academic writing (use academic-paper skill), research plan writing without a specific funder (use research-plan skill), or IRB/ethics protocols (use ethics-consent skill).
From ai-anthropologynpx claudepluginhub mattartzanthro/ai-anthropology-toolkit --plugin ai-anthropologyThis skill uses the workspace's default tool permissions.
references/fulbright.mdreferences/nsf-cultural-anthro.mdreferences/wenner-gren.mdGuides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Analyzes BMad project state from catalog CSV, configs, artifacts, and query to recommend next skills or answer questions. Useful for help requests, 'what next', or starting BMad.
Write grant proposals and funding applications for anthropological research that are funder-compliant, methodologically rigorous, and rhetorically persuasive to multidisciplinary review panels. Proposals should read as evidentiary contracts — specifying what data will be produced, how it will be analyzed, and how claims will travel beyond a single site — while preserving the interpretive depth and epistemic commitments that distinguish anthropological research.
| Funder / Genre | Reference File |
|---|---|
| NSF Cultural Anthropology (BCS, CA-DDRIG) | Read references/nsf-cultural-anthro.md |
| Wenner-Gren (Dissertation Fieldwork, Post-PhD, Hunt) | Read references/wenner-gren.md |
| Fulbright (IIE, Fulbright-Hays DDRA) | Read references/fulbright.md |
| Dissertation prospectus (committee, not funder) | Use the general workflow below; no funder-specific reference needed |
| Applied / consulting proposal | Use the general workflow below; adapt formality register to client |
For funders not listed above (ERC, SSHRC, Wellcome, etc.), use the general workflow and cross-cutting principles below. The architectural patterns — evidentiary contract structure, methods as feasibility signal, ethics as design — transfer across funders even when specific formatting rules differ.
Determine which funding mechanism the user is targeting. This shapes everything downstream: page/word limits, required sections, evaluation criteria, budget rules, and rhetorical conventions.
Ask the user if not immediately clear:
If a specific funder is identified and a reference file exists, load it now. The reference file contains funder-specific section requirements, page limits, evaluation criteria, budget rules, and common pitfalls. Follow those constraints as hard requirements — they override the general guidance below.
If no funder is specified, proceed with the general workflow. The user may be at the "exploring options" stage, in which case help them identify suitable funders based on their project, career stage, and timeline.
Collect the information needed to write a compelling proposal. Not all of this is needed upfront — gather what you can and note gaps for the user to fill.
Essential context (proposal cannot proceed without these):
Important context (strengthens the proposal significantly):
Helpful context (improves tailoring):
Configure the proposal based on user context. These parameters shape the language, structure, and emphasis of the output.
Epistemic stance — Determines how methods are described, what theoretical vocabulary is appropriate, and how "contribution" is framed. A critical medical anthropologist writing for NSF needs different methods language than an STS scholar or a linguistic anthropologist, even if the proposal structure is identical. Ask the user to identify their primary stance; most researchers work at intersections, so a primary + secondary is common.
Funder register — Each funder has implicit expectations about writing style. NSF panels expect clear, sometimes quasi-positivist framing even for interpretive projects ("testable expectations" rather than "hypotheses" can thread this needle). Wenner-Gren values concise, integrated narratives that foreground the research question's anthropological significance. Fulbright panels include non-specialists and country experts, requiring accessible language and strong country-specific justification. Match the register to the funder.
Risk posture — Projects involving vulnerable populations, politically sensitive contexts, or high-surveillance environments need enhanced ethics framing, explicit safety protocols, and often a Plan B for disrupted access. Wenner-Gren requires Plan B explicitly; other funders reward it implicitly.
Field configuration — Single-site, multi-sited, digital, archival, hybrid, or comparative. This affects how methods are described, how the timeline is structured, and what feasibility concerns reviewers will anticipate.
Compression level — Determined by the funder's page/word limits. A 2-page doctoral fellowship narrative requires radical compression; a 15-page NSF Project Description allows methodological depth. Internal word budgets should be allocated proportionally (see Step 4).
Use the funder-specific reference file for exact section requirements. When no funder-specific reference is available, use the following general architecture. This structure reflects how winning proposals across major anthropology funders organize their narratives — a "why-what-how" macro-structure that minimizes reviewer cognitive load.
General proposal architecture (adapt to funder constraints):
Aims and research question (~10-15% of narrative)
Significance and state of the art (~20-30% of narrative)
Conceptual framework (~10-15% of narrative, often integrated with #2)
Research design and methods (~30-40% of narrative)
Ethics, community engagement, and data governance (~10-15% of narrative, unless externalized into separate form sections)
Broader impacts / dissemination / knowledge mobilization (~10-15%)
Timeline, milestones, and risk management (~5-10%)
Internal word budgets by proposal scale:
| Scale | Total length | Typical funders |
|---|---|---|
| Short (fellowship/small grant) | 900-1,200 words / 2 pages | SSHRC doctoral, some internal fellowships |
| Medium (standard research) | 3,000-5,000 words / 6-15 pages | NSF standard, SSHRC Insight, Wenner-Gren |
| Large (multi-year) | 5,000-10,000 words / 14-20 pages | ERC Starting/Consolidator, Wellcome Discovery |
Generate proposal text that follows these principles:
Write for the review panel, not the discipline. Many funders explicitly instruct applicants to write for broad audiences. Even specialist panels include members from adjacent subfields. Avoid unexplained jargon. Define theoretical terms on first use. Make the research question legible to a political scientist or sociologist, not just another ethnographer of your specific region or topic.
Methods are a credibility device. Reviewers use the methods section as a proxy for competence and feasibility. Specificity builds trust: name the number of interviews (approximate ranges are fine: "n≈30-40"), describe sampling logic, specify analytic steps. Vague methods ("I will conduct participant observation and interviews") are the single most common reviewer red flag in anthropology proposals.
Frame theory as generating analytic expectations. The theoretical framework should end with predictions or discriminating questions that the methods section is organized to answer. This is what funders mean by "empirically driven" research — not that you must test hypotheses, but that your theory does work by directing attention and specifying what evidence would look like.
Treat ethics as design, not compliance. Do not relegate ethics to a paragraph at the end. Integrate ethical considerations into the methods description — consent procedures, data protection, community relationships, and reciprocity should appear where they're relevant in the workflow, not as an appendix.
Budget should shadow the work plan. Each cost line should answer: which activity requires this, why this rate, and what happens if it's reduced. Separate participant compensation from personnel costs. Justify local collaboration labor (research assistants, translators, transcribers) with roles, estimated time, and deliverables.
Epistemic stance shapes everything. An interpretivist proposal emphasizes meaning-making, lived experience, and thick description. A critical proposal foregrounds power relations, structural constraints, and ideological formations. A decolonial proposal centers community governance, reciprocity, and Indigenous knowledge systems. The same methods (e.g., semi-structured interviews) are described differently depending on stance — what you're looking for in the data, how you'll know you've found it, and what kind of claims you'll make.
Before presenting the draft, verify:
Hard stops — refuse to proceed without these:
Soft warnings — flag but proceed:
Generic social science prose. The most common failure. The proposal reads like it could be from any discipline — no ethnographic specificity, no attention to positionality, no thick description of the field context. Anthropology proposals should make the reader feel the site, the stakes, and the researcher's relationship to the community, even within tight page limits.
Methods section as wish list. "I will conduct participant observation, semi-structured interviews, and archival research" — with no sampling logic, no analysis plan, and no account of how these methods produce evidence that bears on the research question. This is the single most common reviewer complaint. Specify what you'll observe and why, who you'll interview and how you'll select them, what you'll look for in the archives and how you'll analyze it.
Theory-method disconnect. The literature review discusses three theoretical frameworks, and the methods section describes generic qualitative procedures. The frameworks should generate specific analytic questions that the methods are designed to answer. If the theory doesn't do work in the methods section, it's decorative.
Ethics as afterthought. A single paragraph at the end saying "I will obtain IRB approval and informed consent." This fails because ethics review is increasingly a feasibility and design question — reviewers want to see that the researcher has thought through consent modalities appropriate to the field context, data protection, community engagement, and reciprocity.
Overclaiming significance. "This project will transform our understanding of X." Reviewers are skeptical of grandiose claims. Be specific about what the project contributes: what analytic uncertainty it resolves, what evidence it produces, who can use the findings and how.
Ignoring the funder's evaluation criteria. Each funder tells you exactly what reviewers are asked to evaluate. NSF's two merit criteria (Intellectual Merit and Broader Impacts), Wenner-Gren's emphasis on well-developed questions and feasible plans, ERC's focus on "beyond the state of the art" — these are not suggestions. Structure the proposal so reviewers can easily find answers to their evaluation questions.
Example 1: NSF CA-DDRIG proposal Input: "I'm writing an NSF cultural anthropology DDRIG about how climate refugees in coastal Bangladesh negotiate relocation decisions. I'm an interpretivist doing 12 months of fieldwork in two villages." Output approach: Load references/nsf-cultural-anthro.md. Set parameters: epistemic stance = interpretive (primary), political ecology (secondary); field configuration = comparative (two sites); risk posture = enhanced (displaced populations); compression = 10 pages single-spaced (DDRIG limit). Structure around NSF's required components: problem, intellectual merit, broader impacts, training, positionality, research design. Frame "relocation decision-making" as a generalizable process (not just a description of one community's experience) to meet NSF's scientific contribution requirement. Methods section specifies participant observation protocols, interview sampling (household heads, community leaders, government officials, NGO workers — ~40-50 interviews), and comparative analytic strategy across the two villages.
Example 2: Wenner-Gren Dissertation Fieldwork Grant Input: "I need to write a Wenner-Gren DFG application. My project is on the everyday ethics of AI-assisted medical diagnosis in urban India. I'm working from a critical medical anthropology perspective." Output approach: Load references/wenner-gren.md. Set parameters: epistemic stance = critical medical (primary), STS (secondary); field configuration = single-site; risk posture = standard (clinical settings require care but are not high-risk); compression = strict per-question word limits (Q1=1000w, Q2=1000w, etc.). Structure each question response as a self-contained mini-argument ending with a sentence that tells the reviewer what to conclude. Include Plan B for disrupted clinical access (pivot to telemedicine consultations, remote interviews with practitioners). Budget under $25,000, no overhead, following Wenner-Gren's explicit exclusions.
Example 3: Fulbright IIE research grant Input: "I'm applying for a Fulbright to Japan to study how aging communities use social robots. Where do I start?" Output approach: Load references/fulbright.md. Set parameters: epistemic stance = STS/actor-network (primary), phenomenological (secondary); field configuration = multi-sited (likely multiple care facilities); risk posture = enhanced (elderly populations); compression = per Fulbright format requirements. Fulbright panels include country experts and non-anthropologists — write the research narrative in accessible language. Emphasize cultural exchange dimensions and host institution relationship (Fulbright's distinctive priority). Address Japanese research ethics requirements and institutional affiliation logistics.
Example 4: Dissertation prospectus (no external funder) Input: "My committee wants a 20-page prospectus. I'm studying gig economy labor organizing in Mexico City from a political economy perspective." Output approach: No funder-specific reference needed. Set parameters: epistemic stance = political economy/Marxian (primary), practice theory (secondary); field configuration = multi-sited (multiple platforms, worker collectives, regulatory spaces); risk posture = enhanced (labor organizing in politically sensitive context). A prospectus is a proposal to the committee: demonstrate command of the literature, justify the methods, and show the project is feasible within the degree timeline. More space for theoretical depth than a typical grant, but the evidentiary contract structure still applies — the committee needs to see that the research design can produce the evidence needed to make the theoretical contribution promised in the framing.