I developed OpenClaw Think-Tank Intelligence, a skill that transforms complex global crises into concise, insightful think-tank memos. These memos include stakeholder maps, scenarios, policy options, tradeoffs, risks, confidence levels, and assumptions. You’ll be amazed by the quality of analytics. https://clawhub.ai/vassiliylakhonin/global-think-tank-analys...

The use case I had in mind was exactly the kind of fast-moving crisis where everyone has opinions, but very few people structure the problem well, for example the Iran war and its second-order effects on escalation, oil, regional actors, sanctions, shipping routes, and policy response options.

This skill is designed to help break that kind of situation into: stakeholder mapping scenarios policy options and trade-offs implementation risks confidence levels and assumptions The goal is not “predict the future,” but force a more disciplined way to think through what might happen and what decisions actually follow from that.

Repo: https://github.com/vassiliylakhonin/global-think-tank-analys...

Example prompt: Use $global-think-tank-analyst to assess escalation scenarios, regional spillover risks, and policy response options related to the Iran war.

Comments URL: https://news.ycombinator.com/item?id=47331007

Points: 1

# Comments: 2

The use case I had in mind was exactly the kind of fast-moving crisis where everyone has opinions, but very few people structure the problem well, for example the Iran war and its second-order effects on escalation, oil, regional actors, sanctions, shipping routes, and policy response options.

This skill is designed to help break that kind of situation into:

stakeholder mapping scenarios policy options and trade-offs implementation risks confidence levels and assumptions The goal is not “predict the future,” but force a more disciplined way to think through what might happen and what decisions actually follow from that.

Repo: https://github.com/vassiliylakhonin/global-think-tank-analys...

Example prompt: Use $global-think-tank-analyst to assess escalation scenarios, regional spillover risks, and policy response options related to the Iran war.

Comments URL: https://news.ycombinator.com/item?id=47323226

Points: 3

# Comments: 1

I'm a Not a developer. I built this over a few weeks with Codex+Claude Code.

What I ended up with: https://vassiliylakhonin.github.io/

The interesting design decisions:

Instead of just a PDF, I have six machine-readable JSON files: - resume.json — standard JSON Resume format - evidence.json — maps each claimed metric to its source and verification method. The theory: AI candidate evaluation will increasingly distinguish evidenced claims from unverified ones. - availability.json, capabilities.json, engage.json, verification.json — availability signals, capability profile, intake schema, identity cross-references

llms.txt points crawlers to the pages that matter. robots.txt explicitly allows GPTBot and OAI-SearchBot. JSON-LD (schema.org ProfilePage/Person) on the homepage.

The most experimental piece: a live MCP server on Railway. In principle, an AI recruiting agent could call it as a tool and get structured answers about my background without scraping HTML. I haven't seen anyone else do this for a personal CV, which either means it's ahead of the curve or completely pointless.

The honest version: I have no idea if any of this actually works. I don't know whether recruiter tooling parses llms.txt or JSON-LD from personal sites, or whether everything still flows through LinkedIn scraping and PDF vision models. I built it because structured reporting systems are literally my job, and this felt like the right way to represent that.

Repo: https://github.com/vassiliylakhonin/vassiliylakhonin.github....

Curious: is anyone building sourcing or screening agents that consume structured data from candidate-owned sites? Or does all candidate data still enter the pipeline through LinkedIn and uploaded PDFs?

Comments URL: https://news.ycombinator.com/item?id=47149842

Points: 1

# Comments: 0

- It’s an MVP and currently optimized for drafting workflow structure, not final donor submission formatting. - Donor coverage is mixed: some donors have specialized strategy behavior, others use shared generic logic with catalog aliases. - RAG ingestion is intentionally simple right now (PDF ingest + namespace isolation); deeper citation traceability is on the roadmap. - Multi-tenant auth/permissions is not implemented yet (API key is service-level).

I’ve been building GrantFlow, an open-source drafting workflow engine for institutional grant proposals.

The problem: many NGOs and implementing organizations spend a huge amount of time/money translating solid program ideas into donor-specific, reviewable proposal artifacts before they can even get meaningful feedback internally.

A lot of that work is not “thinking through the intervention” — it’s reshaping the same idea into structured outputs (ToC, LogFrame, MEL framing), aligning language to donor expectations, and managing review cycles.

GrantFlow is my attempt to reduce that overhead.

It takes structured project inputs and produces donor-aligned draft artifacts through a stateful workflow with review checkpoints (human-in-the-loop), instead of a single “generate everything” prompt.

What it does today (MVP): - Donor-aware drafting strategies (specialized + generic donor coverage) - Human-in-the-loop checkpoints (pause / approve / resume) - Exportable artifacts (.docx / .xlsx / ZIP) - RAG-ready donor knowledge namespaces (ChromaDB) - FastAPI API for integration into internal tools - Optional API key auth - Optional SQLite persistence for jobs + HITL checkpoints

Tech stack: - FastAPI - LangGraph - Pydantic - ChromaDB (with local/in-memory fallback) - Python 3.11+

Recent work I finished before posting: - hardened CI + shell checks - public API response redaction - typed response models for status endpoints - sqlite-backed job/HITL stores + WAL/busy_timeout - protected PDF ingest endpoint (`POST /ingest`) - readiness endpoint (`GET /ready`)

Why I built it this way: - proposal work is iterative and review-heavy - compliance/rules matter, so workflow/state matters - teams need checkpoints and auditability, not just raw text generation

Who I think this may be useful for: - implementing organizations (e.g. firms managing donor-funded programs) - NGOs and local partners - civic-tech / govtech teams building internal proposal tooling - consultants who standardize drafting workflows across donors

Happy to answer questions, especially around workflow design / HITL / donor strategy modeling.

Comments URL: https://news.ycombinator.com/item?id=47136294

Points: 1

# Comments: 2

I started with GPT-assisted drafting, and now I’m piloting the next step with OpenClaw autonomous agents: a focused skill for nonprofit RBM logic model development.

What it generates: -5-level results chain: Inputs -> Activities -> Outputs -> Outcomes -> Impact -Theory of Change (if/then pathway + assumptions + risks) -SMART outcome indicators -SDG alignment -Monitoring and data collection plan

Who it’s for: -nonprofit program managers -MEAL/M&E specialists -grant writers and NGO consultants

This is early-stage and intentionally human-in-the-loop.

Goal: faster structured drafting, but expert validation remains the hard gate for quality decisions.

Main open issues I’m actively thinking about: confidentiality, governance, accountability, and validation quality.

Repo: https://github.com/vassiliylakhonin/Nonprofit-RBM-Skill-For-...

Skill on ClawHub:https://clawhub.ai/vassiliylakhonin/nonprofit-rbm-logic-mode... Install: clawhub install nonprofit-rbm-logic-model More technical experiments: https://github.com/vassiliylakhonin If you work with real RBM/logframe workflows, I’d really value tough feedback and edge cases.

Comments URL: https://news.ycombinator.com/item?id=47073242

Points: 1

# Comments: 1

After that, I began using a dedicated GPT tool to support this work and improve consistency in early-stage analysis and drafting, for example https://Inkd.in/dbmBAXMB

I have now created and am actively piloting the next step with OpenClaw autonomous sub-agents, including this focused skill for nonprofit RBM logic model development: https://Inkd.in/d4dbTz6p https://Inkd.in/dYuhhN8r

This is an early-stage effort, but the objective is practical. Maybe I will build a set of specialized agents for development consulting workflows, with a clear human-in-the-loop approach for expert validation and decision quality.

There are still many unresolved challenges on the horizon, from data confidentiality and security to governance and accountability. At the same time, the direction of development is clear, and this shift is unlikely to stop.

The long-term direction is to help digitize core consulting companies roles and processes, from problem definition and theory of change to indicators, assumptions, risk logic, and adaptation planning, while maintaining methodological rigor.

If you work in nonprofit, development consulting, or simply experimenting with Agentic Al, I would be glad to exchange experience and test relevant use cases.

You can also follow my technical work and experiments here: https://Inkd.in/d_RwMaFp

Comments URL: https://news.ycombinator.com/item?id=47063762

Points: 1

# Comments: 0

What it generates: -A 5-level results chain (Inputs -> Activities -> Outputs -> Outcomes -> Impact) -Theory of Change (if/then pathway + assumptions) -Specific-Measurable-Achievable-Relevant-Time-bound outcome indicators -Sustainable Development Goals alignment -Monitoring and data collection plan

Who it is for: -Nonprofit program managers -Monitoring and Evaluation / Monitoring, Evaluation, Accountability, and -Learning specialists -Grant writers and NGO consultants

Repo: https://github.com/vassiliylakhonin/Nonprofit-RBM-Skill-For-...

I would really value feedback on:

Clarity of outputs for real grant workflows Missing metrics/templates for NGO Monitoring and Evaluation teams Gaps in donor alignment (United States Agency for International Development / United Nations / European Union formats)

Comments URL: https://news.ycombinator.com/item?id=47062912

Points: 1

# Comments: 0

I tried to make it useful for both recruiters and AI tools: -Clear one-page profile + downloadable PDF -Case studies with concrete results -Work samples -Structured files for discovery and parsing (llms.txt, resume.json, evidence.json, availability.json, agent-card.json, engage.json) -Basic indexing and quality checks (sitemap, robots, JSON-LD, GitHub Actions)

Main idea: less friction to evaluate fit, verify claims, and contact me fast.

Would love feedback from HN: If you scanned this in 60 seconds, what would you improve first?

Website: https://vassiliylakhonin.github.io/ Source: https://github.com/vassiliylakhonin/vassiliylakhonin.github....

Comments URL: https://news.ycombinator.com/item?id=47035758

Points: 1

# Comments: 0

This project is a React + TypeScript dashboard that combines:

-KPI/indicator views -qualitative impact stories -psychosocial support case summaries -one-click PowerPoint export (pptxgenjs)

Code: https://github.com/vassiliylakhonin/activity-reporting-for-d...

Technical notes:

Vite build with chunk splitting Type-safe indicator calculations test + typecheck + build scripts included

I’d really value feedback on: -export quality/structure for real donor reporting workflows -what data model would make this easier to adapt across organizations

Comments URL: https://news.ycombinator.com/item?id=47035565

Points: 1

# Comments: 0

One-page profile + downloadable CV 3 case studies (including private-sector SaaS/e-commerce launch) AI-friendly article briefs (summary + source links) llms.txt, capabilities.json, sitemap.xml, robots.txt, JSON-LD Live: https://vassiliylakhonin.github.io/ Repo: https://github.com/vassiliylakhonin/vassiliylakhonin.github....

I’m testing what actually improves discoverability and credibility for program/PMO/compliance roles. Feedback welcome: what should I remove, and what signal is still missing?

Comments URL: https://news.ycombinator.com/item?id=47000663

Points: 2

# Comments: 0

Live: https://vassiliylakhonin.github.io/

What’s inside:

2 case studies with measurable outcomes service scope page (deliverables, timelines, inputs) crawl/index files (llms.txt, robots.txt, sitemap.xml) structured profile metadata (JSON-LD)

Would value blunt feedback on: -What’s still noise? -What proof is missing? -What would make this instantly credible in your eyes?

Comments URL: https://news.ycombinator.com/item?id=46988386

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=46988181

Points: 1

# Comments: 0

Site: https://vassiliylakhonin.github.io/ Repo: https://github.com/vassiliylakhonin/vassiliylakhonin.github....

Comments URL: https://news.ycombinator.com/item?id=46959399

Points: 1

# Comments: 1