core
(ePost) Use when any agent modifies files, makes architectural decisions, or needs safety and documentation rules
npx skills add majiayu000/claude-skill-registry --skill core-klara-copilot-epost-agent-kit --agent copilot
Same command for any agent — swap --agent for claude-code, codex, cursor.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Core Rules Skill ## Purpose Defines operational boundaries, decision authority, environment safety, and documentation standards for all agents in the Claude Code ecosystem. ## When Active - All agent operations - File creation, modification, or deletion - Architectural decisions - Code generation or refactoring - Documentation updates ## Aspect Files | File | Purpose | |------|---------| | `references/decision-boundaries.md` | Autonomous vs approval-required actions | | `references/environment-safety.md` | Pre-execution verification rules | | `references/external-tools-usage.md` | External tool/MCP boundaries | | `references/documentation-standards.md` | Formatting and structure rules | | `references/orchestration.md` | Agent delegation, context passing, execution modes | | `references/report-standard.md` | Common report format for all agent output | ## Team Workflows | Workflow | File | When | |----------|------|------| | Feature Development | `references/workflow-feature-development.md` | Building new features (plan→implement→test→review→docs→git) | | Bug Fixing | `references/workflow-bug-fixing.md` | Fixing bugs (scout→debug→fix→test→review→capture→git) | | Project Init | `ref
- Purpose
- When Active
- Aspect Files
- Team Workflows
- Quick Reference
- Decision Authority
- Safety Constraints
- Documentation Rules
- Required File Structure
- Never Do
- Related Documents
What does the core skill do?
(ePost) Use when any agent modifies files, makes architectural decisions, or needs safety and documentation rules
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill core-klara-copilot-epost-agent-kit --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.