context
Provides essential project background info, architecture rationale, and operational constraints for developers.
Install
mkdir -p .claude/skills/context-serithemage && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/9535" && unzip -o skill.zip -d .claude/skills/context-serithemage && rm skill.zipInstalls to .claude/skills/context-serithemage
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Loads Serverless OpenClaw project context. Provides background knowledge needed for development including project overview, tech stack, architecture decisions, and data models.Key capabilities
- →Load project architecture overview
- →Access DynamoDB schema details
- →Verify implementation against constraints
- →Check phase status
How it works
Automatically references project documentation and constraints during implementation tasks.
Inputs & outputs
When to use context
- →Reviewing architectural decisions
- →Understanding data flow
- →Checking implementation constraints
- →Onboarding on project architecture
About this skill
Serverless OpenClaw Project Context
This skill provides core project context. It is automatically referenced during implementation tasks.
Project Overview & Key Decisions
See PRD.md for details:
- Project definition, goals, tech stack
- 7 key architecture decisions with rationale
- Monorepo structure (6 packages: cdk, gateway, container, lambda, web, shared)
- DynamoDB 5-table schema
- Core data flows
Phase Status
| Phase | Status |
|---|---|
| Phase 0 (docs + setup) | Complete |
| Phase 1 (MVP — Fargate + Web + Telegram) | Complete (10/10) |
| Phase 2 (Lambda agent migration) | Complete |
AGENT_RUNTIME feature flag: fargate | lambda | both (current default)
Test coverage: 233 unit tests + 35 E2E tests = 268 total
Critical Constraints (Must Follow During Implementation)
- No NAT Gateway — Use Fargate Public IP + VPC Gateway Endpoints
- No secrets on disk — Secrets Manager → environment variables only. Never write API keys/tokens to
openclaw.json - Telegram webhook-only — Long polling not allowed (API mutually exclusive)
- Bridge Bearer token required — Authentication on all endpoints except
/health - IDOR prevention — userId determined server-side (JWT/connectionId reverse lookup). Ignore client input
- RunTask API — Use
capacityProviderStrategyonly. Cannot specifylaunchTypesimultaneously - Cost target — ~$1/month. No ALB, Interface Endpoint, or NAT Gateway creation allowed
Related Documents
- Full PRD: docs/PRD.md
- Architecture: docs/architecture.md
- Implementation plan: docs/implementation-plan.md
- Cost analysis: docs/cost-optimization.md
- Progress: docs/progress.md
- Cold start optimization: docs/cold-start-optimization.md
When not to use it
- →Modifying project architecture without PRD review
- →Writing secrets to disk
Prerequisites
Limitations
- →No NAT Gateway allowed
- →No secrets on disk
- →Telegram webhook-only
How it compares
Provides automated, context-aware architectural guardrails rather than requiring manual documentation lookups.
Compared to similar skills
context side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| context (this skill) | 0 | 4mo | No flags | Beginner |
| jupyter-notebook | 30 | 6mo | Review | Intermediate |
| using-serena-for-exploration | 9 | 8mo | Review | Intermediate |
| cursor-explorer-mcp | 6 | 8mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by serithemage
View all by serithemage →You might also like
jupyter-notebook
davila7
Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.
using-serena-for-exploration
seanGSISG
Use when exploring codebases with Serena MCP tools for architectural understanding and pattern discovery - guides efficient symbolic exploration workflow minimizing token usage through targeted symbol reads, overview tools, and progressive narrowing
cursor-explorer-mcp
sepiabrown
Use for token-expensive operations requiring multi-file analysis - codebase exploration, broad searches, architecture understanding, tracing flows, finding implementations across files. Uses MCP cursor-agent server (company pays) with clean async interface. Do NOT use for single-file analysis, explaining code already in immediate context, or pure reasoning tasks.
lecture-transcript-slide-matcher
az9713
Combines YouTube lecture transcripts with PDF slides to create an interactive HTML page. Matches each slide to corresponding transcript segments, organized by key concepts. Use when users want to create synchronized lecture notes from transcript text files and slide PDFs.
skill-from-github
GBSOSS
Create skills by learning from high-quality GitHub projects
react-expert
reactjs
Use when researching React APIs or concepts for documentation. Use when you need authoritative usage examples, caveats, warnings, or errors for a React feature.