🧠
AI EngineeringGo

LSEL Curator

by modu-ai

LSEL Curator is an AI Engineering skill for Claude Code, published by modu-ai in moai-adk.

1.2K stars220 forkson modu-ai/moai-adkAdded 2026/08/20Repository updated 2026/08/20
agentic-aiagentic-codingagentic-workflowai-agentai-codinganthropicclaudeclaude-codecli-toolcode-generationcode-qualityddddeveloper-toolsgogolangllmmulti-agentspec-driven-developmenttddvibe-coding
Install in seconds
Install LSEL Curator
Copy LSEL Curator into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/modu-ai/moai-adk/tree/main/.claude/skills/hns-lsel-curator ~/.claude/skills/hns-lsel-curator

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/modu-ai/moai-adk.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
.claude/skills/hns-lsel-curator/SKILL.md in modu-ai/moai-adk
Installs to
~/.claude/skills/hns-lsel-curator
Collection
One of 25 skills cataloged from this repository
Category
AI Engineering2451 skills

What LSEL Curator does

LSEL Curator drains the .moai/lessons-inbox.jsonl, filters Bash timeout/sandbox noise, clusters remaining failures by event key, and stages high-signal candidates for the Local Self-Evolution Loop. Use it to turn raw tool failure stubs into curated proposal candidates.

LSEL Curator is cataloged under AI Engineering on DirSkills. LSEL Curator comes from a repository tagged agentic-ai, agentic-coding, agentic-workflow, ai-agent and ai-coding.

Documentation

README

hns-lsel-curator — LSEL CLUSTER + drain engine

Namespace: hns-lsel-* is user-owned dogfood (CLAUDE.local.md §24). This skill is NOT mirrored into internal/template/templates/ — it lives only in this repo. Graduation to moai-lsel-* + 16-language distribution is a separate SPEC (out of scope per spec.md §G).

M1 scope: drain + cluster + stage candidates. NO APPROVE, NO APPLY (M3). M2 scope: drain + cluster + PROPOSE shadow (no APPROVE, no APPLY). The PROPOSE stage emits shadow proposals + self-critiques; APPROVE/APPLY land in M3 via the fresh hns-lsel-applier path. M2 does NOT write to memory/ — the first feedback_*.md topic file is an M3+ deliverable after APPROVE.

What this skill does

This is the opening of the README. Read the full README on GitHub.

Commands LSEL Curator provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

  • /moai

Frequently asked about LSEL Curator

  • What else does modu-ai publish alongside LSEL Curator?

    LSEL Curator is one of 25 skills that DirSkills catalogs from modu-ai/moai-adk, the repository it ships in. Its siblings there include API Patterns Reference, Backend Development and CI Loop. Each one is a separate skill with its own page in this directory, installs the same way LSEL Curator does, and is maintained by modu-ai in that same repository. The rest of the collection is listed on the modu-ai/moai-adk page.

  • How does LSEL Curator compare to other AI Engineering skills?

    LSEL Curator ranks #1199 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of LSEL Curator against them. Open each page to compare what they document and how they install.

More from modu-ai/moai-adk

LSEL Curator is one of 25 skills cataloged on DirSkills from modu-ai/moai-adk.

See all 25 skills
📚
2w ago

API Patterns Reference

API Patterns Reference documents REST and GraphQL API design patterns, error handling conventions, and input validation for backend development. Use it when designing, implementing, or reviewing backend API endpoints.
Quality
1.2K220
⚙️
2w ago

Backend Development

Backend Development covers API design, database integration, microservices, and backend security patterns for building server-side applications. Use it when designing APIs, implementing server logic, authentication, or authorization.
DevOps
1.2K220
🔁
2w ago

CI Loop

CI Loop polls required pull request checks, classifies mechanical vs semantic failures, and applies safe automated patches up to three iterations before escalating to the user. Use it after creating a PR with /moai sync to monitor CI and auto-fix failures.
DevOps
1.2K220
🛠️
2w ago

Claude Code Authoring Kit

Claude Code Authoring Kit is a comprehensive reference for creating and configuring Claude Code extensions, covering Skills, sub-agents, plugins, slash commands, hooks, memory, settings, sandboxing, headless mode, and advanced agent patterns.
AI Engineering
1.2K220
🔀
2w ago

Cross-Model Audit Convergence

Cross-Model Audit Convergence documents how plan-auditor and sync-auditor agents invoke the audit_multi MCP tool to run code review across codex and GLM backends in parallel, converge their verdicts with Claude, and fold per-backend verdicts and a disagreement flag into audit output. Use it when a project sets audit_model to multi.
AI Engineering
1.2K220
🗄️
2w ago

Database Domain Specialist

Database Domain Specialist provides patterns and implementations for PostgreSQL, MongoDB, Redis, Oracle, and cloud databases. Use it for schema design, query optimization, indexing, data modeling, and cloud database selection.
Data
1.2K220