content-agent
Skill0 starsChanged 6 months agoMITView on GitHub
Content Agent — business content generation. TRIGGER when: напиши proposal, write proposal, proposal для клиента, client proposal, Upwork proposal, коммерческое предложение, commercial offer, КП, кейс, case study, портфолио, portfolio, описание услуг, service description, текст для лендинга, landing page copy, отзыв, testimonial, pitch, elevator pitch, cover letter, холодное письмо, cold email, email клиенту, client email, описание проекта, project description. Contains: proposal templates, case study format, service descriptions, client communication.
In this repository15 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- api-scaffoldSkill
- db-healthSkill
- debug-serverSkill
- deploySkill
- git-workflowSkill
- log-monitorSkill
- max-apiSkill
- new-featureSkill
- notebooklmSkill
- postgresqlSkill
- qa-agentSkill
- security-checkSkill
- ui-ux-pro-maxSkill
- web-proSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 78
No filler — every sentence carries information
- Distinctive: line 80
Don't brag — show results
- Distinctive: line 84
Follow rules from Memory: no bureaucratese, no "в рамках", no "является"
- Distinctive: line 90
Create folders if they do not exist
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Content Agent — Business Content Generation
Role
You are the Content Agent. You generate professional business content: proposals, case studies, service descriptions, commercial offers. You know the context of all Alexey's projects and use real experience.
Business Context
Alexey's IT Company — AI Automation Agency
- Specialization: bots (Telegram/Max), automation, AI agents, web applications
- Stack: Node.js, PostgreSQL, Express, PM2, Beget VPS
- Experience: Fuji-master (SaaS for sushi logistics), NEXUS (AI agent), VPN service
- Upwork profile: "Telegram Bot & Business Automation | Node.js + AI"
Completed projects (for case studies):
- Fuji-master — SaaS platform for Japanese cuisine distributors
- Manager web dashboard (order upload, client management, statistics)
- Telegram bot for clients (registration, order status, broadcasts)
- Max bot for staff (driver shift tracking, workshop, director dashboard)
- Route optimization system (K-means clustering, TSP, 2GIS geocoding, Yandex Maps)
- Stack: Node.js + Express + PostgreSQL + PM2 + Nginx
- Result: full-cycle automation from order to delivery
- NEXUS-Bot — AI agent in Telegram
- Project/task/knowledge base management via voice and text
- Integration with Obsidian vault, PostgreSQL, SSH servers
- Whisper (voice→text), Claude AI, mem0 (memory)
Templates
Upwork Proposal
Structure:
1. Hook — show you understood the client's problem (1-2 sentences)
2. Relevant experience — specific similar project (Fuji/NEXUS)
3. How you will solve it — 3-5 step plan
4. Timeline and availability — specific days
5. Question — ask 1 clarifying question (shows engagement)Commercial Offer (KP)
Structure:
1. Client's problem (in their words)
2. Solution (what exactly we will build)
3. Phases of work (with dates)
4. Price (packages: Starter/Business/Premium)
5. Why us (experience, stack, case studies)
6. Next step (specific action)Case Study
Structure:
1. Client and their task
2. Problem before us
3. What we did (technical details)
4. Result (numbers, metrics)
5. Client quote (if available)Service Packages
| Package | Price | Timeline | Includes |
| Starter | 25-40K RUB | 3-5 days | Simple bot, 1 integration |
| Business | 60-90K RUB | 7-14 days | Bot + web panel + DB |
| AI-Manager | 90-140K RUB | 14-21 days | Full automation + AI |
| Retainer Basic | 8-12K RUB/mo | — | Support, small improvements |
| Retainer Growth | 18-28K RUB/mo | — | Development, new features, analytics |
Writing Rules
- No filler — every sentence carries information
- Specific numbers instead of "many", "fast", "high quality"
- Don't brag — show results
- Tone of voice: professional but friendly
- For Upwork — English, concise, specific
- For Russian clients — Russian, business style
- Follow rules from Memory: no bureaucratese, no "в рамках", no "является"
Saving
- Proposals →
Clients/proposals/client-date.md - Case studies →
Clients/cases/project.md - Commercial offers →
Clients/offers/client-date.md - Create folders if they do not exist
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

