← 返回 Skills 市场
duclawbot

Grant

作者 Duclawbot · GitHub ↗ · v1.0.0
cross-platform ✓ 安全检测通过
356
总下载
0
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install grant
功能描述
Complete grant intelligence system for individuals, nonprofits, startups, researchers, and small businesses. Trigger whenever someone needs to find grants, w...
使用说明 (SKILL.md)

Grant — Complete Grant Intelligence System

What This Skill Does

Grants are the most underutilized source of funding available to small businesses, nonprofits, researchers, and individuals. Billions of dollars go unclaimed every year — not because eligible applicants do not exist, but because the application process is opaque, time-consuming, and written in language designed for bureaucrats rather than the people the funding is meant to help.

This skill navigates that landscape. It finds the funding, builds the case, and writes the application.

Core Principle

Grant applications are not requests. They are arguments. The reviewer is not deciding whether to give you money — they are deciding whether your project best fulfills the grant objectives. Every word in a successful application is written from the reviewer perspective, not the applicant perspective.

Workflow

Step 1: Profile the Applicant

APPLICANT_TYPES = {
  "nonprofit":      { sources: ["government","foundation","corporate"], strengths: ["impact","track_record","partnerships"] },
  "startup":        { sources: ["innovation","R&D","export","accelerator"], strengths: ["innovation","market","team","scale"] },
  "researcher":     { sources: ["research_councils","university","industry"], strengths: ["methodology","significance","collaboration"] },
  "small_business": { sources: ["business_development","export","energy","hiring"], strengths: ["jobs","economic_contribution","innovation"] },
  "individual":     { sources: ["arts","education","community","professional"], strengths: ["story","impact","viability"] }
}

Step 2: Grant Identification

ELIGIBILITY_CHECKLIST = [
  "Organization type matches funder requirements",
  "Geographic location within funded area",
  "Project dates align with grant period",
  "Budget within grant range",
  "Activity type explicitly included in guidelines",
  "No conflict of interest with funder",
  "Organization in good standing"
]

GRANT_SCORING = {
  "eligibility_fit":   "0-3",
  "strategic_fit":     "0-3",
  "competition_level": "0-3",
  "effort_required":   "0-3",
  "funder_relationship": "0-3"
}
# Pursue grants scoring 10+. Below 8, ROI is poor.

Step 3: Application Architecture

Executive Summary

Written last, placed first. Maximum 200 words. If the reviewer reads only this, they should understand and want to fund it.

Problem Statement

PROBLEM_STRUCTURE = [
  "Scale: how many people or how much is affected",
  "Severity: what happens if this is not addressed",
  "Gap: why existing solutions are insufficient",
  "Urgency: why now"
]
# Use data, research citations, community consultation findings.
# Never frame the problem in terms of your organization needs.

Proposed Solution

What specifically will be done. How it addresses root cause not symptoms. Why this approach over alternatives. Your unique capability to deliver it.

Methodology

WORKPLAN_ELEMENTS = [
  "Phase-by-phase milestones with dates",
  "Team roles and relevant experience",
  "Partners and their specific contributions",
  "Risk identification and mitigation",
  "Timeline fits within grant period"
]

Outcomes and Evaluation

OUTCOMES_FRAMEWORK = {
  "outputs":   "Direct products — number trained, events delivered, reports produced",
  "outcomes":  "Changes that result — skills improved, behavior changed, access increased",
  "impact":    "Long-term change in community or sector"
}
# Every outcome needs a measurable indicator with baseline and target.

Budget

BUDGET_RULES = [
  "Every line item justified in narrative",
  "Administration under 15% unless justified",
  "Show co-contribution if required",
  "Costs verified against market rates",
  "No ineligible expenses included"
]

Step 4: Writing for Reviewers

REVIEWER_RULES = {
  "answer_the_question_asked":  "Read each question three times before writing",
  "lead_with_the_answer":       "First sentence answers. Elaboration follows.",
  "use_their_language":         "Mirror exact terminology from grant guidelines",
  "specificity_wins":           "'45 women trained in rural Victoria' beats 'help disadvantaged communities'",
  "evidence_everything":        "Every significant claim needs a source or statistic",
  "no_jargon":                  "Write for intelligent reviewer who is not a specialist"
}

SCORING_OPTIMIZATION = {
  "principle": "Allocate word count proportional to marks available per section",
  "checklist": "Every scoring criterion explicitly addressed before submitting"
}

Step 5: Post-Submission

IF_FUNDED = [
  "Review signed agreement before signing",
  "Enter reporting schedule in calendar",
  "Establish budget tracking system",
  "Document everything during delivery"
]

IF_UNSUCCESSFUL = [
  "Request reviewer feedback",
  "Distinguish fit issues from quality issues",
  "Revise and reapply if quality was the issue",
  "Thank funder and express interest in future rounds"
]

Grant Calendar

WORKBACK_SCHEDULE = {
  "8_weeks_out": "Eligibility confirmed, decision to apply made",
  "6_weeks_out": "Research complete, outline drafted",
  "4_weeks_out": "First draft complete, internal review done",
  "2_weeks_out": "Revised draft, budget finalized, attachments gathered",
  "1_week_out":  "Final review, proofread, technical submission test",
  "day_of":      "Submit by noon — never on deadline day evening"
}

Quality Check

  • Every section directly answers the question asked
  • Problem framed from beneficiary perspective not applicant perspective
  • All outcomes specific and measurable
  • Budget justified line by line
  • All eligibility criteria explicitly demonstrated
  • All reviewer scoring criteria addressed
  • Word limits respected
  • Attachments checklist complete
安全使用建议
This skill appears internally consistent and low-risk because it is instruction-only and asks for no credentials or installs. Before using it, avoid pasting sensitive credentials (API keys, passwords, bank account numbers) into prompts; only provide the project- and budget-related information required for drafting. Treat its outputs as drafting assistance — verify eligibility rules, legal terms, and budget items with official funder documents or professional advisors before submitting. If the agent later asks to upload files or access external services, confirm why that is needed and whether you trust the destination.
功能分析
Type: OpenClaw Skill Name: grant Version: 1.0.0 The skill bundle provides a comprehensive framework and set of instructions for an AI agent to assist users with grant identification and application writing. It contains no executable code, no requests for sensitive information, and no malicious instructions. The content is entirely focused on the legitimate task of grant intelligence and management within the skill.md file.
能力评估
Purpose & Capability
Name and description (grant finding, writing, compliance) align with the SKILL.md content (eligibility checks, scoring, application architecture, calendars). The skill does not request unrelated binaries, environment variables, or config paths.
Instruction Scope
Runtime instructions are templates, checklists, and workflows for profiling applicants, finding grants, scoring fit, and drafting proposals. They do not direct the agent to read system files, call external endpoints, or exfiltrate data. (The document advises using data and citations, which is normal for writing tasks.)
Install Mechanism
No install spec and no code files — this is an instruction-only skill. That minimizes on-disk execution risk and is proportionate to the skill's purpose.
Credentials
The skill declares no required environment variables, credentials, or config paths. Nothing in the instructions justifies access to secrets or unrelated services.
Persistence & Privilege
always is false and the skill is user-invocable. It does not request elevated or persistent privileges or attempt to modify other skill/system configurations.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install grant
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /grant 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release
元数据
Slug grant
版本 1.0.0
许可证
累计安装 2
当前安装数 2
历史版本数 1
常见问题

Grant 是什么?

Complete grant intelligence system for individuals, nonprofits, startups, researchers, and small businesses. Trigger whenever someone needs to find grants, w... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 356 次。

如何安装 Grant?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install grant」即可一键安装,无需额外配置。

Grant 是免费的吗?

是的,Grant 完全免费(开源免费),可自由下载、安装和使用。

Grant 支持哪些平台?

Grant 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Grant?

由 Duclawbot(@duclawbot)开发并维护,当前版本 v1.0.0。

💬 留言讨论