SkillRepo
Sign InSign Up
Catalog
affaan-m/nanoclaw-repl

affaan-m

nanoclaw-repl

Operate and extend NanoClaw v2, ECC's zero-dependency session-aware REPL built on claude -p.

global
0installs0uses—~200
v1.1Saved Apr 20, 2026

NanoClaw REPL

Use this skill when running or extending scripts/claw.js.

Capabilities

  • persistent markdown-backed sessions
  • model switching with /model
  • dynamic skill loading with /load
  • session branching with /branch
  • cross-session search with /search
  • history compaction with /compact
  • export to md/json/txt with /export
  • session metrics with /metrics

Operating Guidance

  1. Keep sessions task-focused.
  2. Branch before high-risk changes.
  3. Compact after major milestones.
  4. Export before sharing or archival.

Extension Rules

  • keep zero external runtime dependencies
  • preserve markdown-as-database compatibility
  • keep command handlers deterministic and local
Files1
1 files · 1.0 KB

Select a file to preview

Overall Score

52/100

Grade

C

Adequate

Safety

75

Quality

48

Clarity

60

Completeness

35

Summary

NanoClaw REPL is a skill for operating and extending a zero-dependency session-aware command-line interface built on Claude. It guides users through persistent sessions, model switching, skill loading, branching, searching, and session management within the `scripts/claw.js` environment.

Detected Capabilities

Session persistence and managementModel switchingDynamic skill loadingSession branchingCross-session searchHistory compactionExport to multiple formats (markdown, JSON, text)Session metrics and monitoring

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

nanoclaw repl operationsmanage repl sessionsswitch llm modelsbranch session stateexport conversation history

Use Cases

  • Run interactive NanoClaw REPL sessions with persistent markdown-backed storage
  • Switch between LLM models during a conversation using `/model`
  • Load and manage dynamic skills within a session using `/load`
  • Create session branches before making high-risk changes
  • Search across multiple sessions to find relevant context
  • Compact session history and export sessions for sharing or archival

Quality Notes

  • POSITIVE: Clear, concise skill description with explicit scope ('scripts/claw.js')
  • POSITIVE: Well-structured capabilities list makes functionality immediately visible
  • POSITIVE: Operating guidance provides practical best practices (branch before risky changes, compact after milestones)
  • POSITIVE: Extension rules document zero-dependency philosophy and architectural constraints
  • NEGATIVE: No detailed command syntax or examples provided — agent must infer how to invoke each command (e.g., exact format for `/model`, `/load`, `/search`)
  • NEGATIVE: No error handling guidance — what should happen if a command fails or a session is corrupted?
  • NEGATIVE: No documented limitations — maximum session size, supported models, export format constraints
  • NEGATIVE: No edge case coverage — behavior with empty sessions, very large histories, or malformed markdown sessions
  • NEGATIVE: Missing details on session branching workflow — how does the agent create, select, or merge branches?
  • NEGATIVE: No guidance on `/search` scope — does it search session content, filenames, or both? How is search syntax specified?
  • NEGATIVE: Export functionality mentioned but no detail on format options, compatibility, or use cases for each format
Model: claude-haiku-4-5-20251001Analyzed: Apr 20, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

v1.1

Content updated

2026-04-20

Latest
v1.0

Seeded from github.com/affaan-m/everything-claude-code

2026-03-16

Add affaan-m/nanoclaw-repl to your library

Get Started Free

Command Palette

Search for a command to run...