Claude/add egl methodology n h qr i#2
Open
hongsw wants to merge 14 commits into
Open
Conversation
- Add PM Coach plugin with 4 commands: - /pm-coach: Main command for auto-analysis - /request: For task requesters - /receive: For task receivers - /report: For completion reporting - Support both simple (B-type) and strategic (A-type) tasks - Hypothesis-based task design for strategic work - Korean language support Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
…mantic search - Add pdf_research.py unified CLI with index, search, status, config commands - Support hybrid/local/global/naive search modes - Include PyMuPDF for PDF text extraction - Add SKILL.md with Claude integration protocol - Update README.md with all 3 plugins documentation - Add .gitignore for examples/, rag_storage/, trees/ Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Examples are local test data and should not be in the repository. The folder is now properly ignored via .gitignore. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Change author from string to object format - Remove unsupported 'skills' and 'requirements' fields - Add license field - Match format of other working plugins Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add screen3.png showing status check and available commands - Add screen4.png showing indexing and search workflow - Include Korean descriptions for each screenshot Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Features: - Automatic infographic generation using NotebookLM MCP - Web search for latest information - Browser automation for NotebookLM interaction - Korean/English language support Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
…bility - Add frontmatter to domain-research skill (both locations) - Add frontmatter to pdf-research skill - Convert notebooklm-infographic from manifest.json to standard SKILL.md format All skills now follow the standard Claude Code skill format with: - name: skill-name - description: Use when [triggering conditions] This makes skills discoverable via the Skill tool. Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Added user-invocable slash commands alongside existing skills:
**domain-research**
- Command: /domain-research
- Guides conversational intent discovery → 5-step research pipeline
- Supports both Skill tool and slash command invocation
**pdf-research**
- Command: /pdf-research
- Automatic status check → index/search workflow
- Integrates LightRAG semantic search with user-friendly interface
**notebooklm-infographic**
- Converted to full plugin structure (from skills/ to plugins/)
- Command: /infographic (aliases: /ig, /notebook-infographic)
- Automated workflow: web research → structuring → NotebookLM generation
- Created plugin.json and organized directory structure
All plugins now support dual invocation:
- Background knowledge: Skills with YAML frontmatter (for Skill tool)
- User commands: Slash commands in commands/ directory
Directory structure:
```
plugins/{plugin-name}/
.claude-plugin/
plugin.json
commands/
{command-name}.md
skills/{skill-name}/
SKILL.md
```
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Add interactive self-learning skill that enables users to learn Claude Code's core features through a structured STOP protocol (2-phase learning per block). Based on the ai-native-camp/camp-1 curriculum with 7 blocks covering setup, experience, CLI rationale, 7 core features (CLAUDE.md, Skill, MCP, Subagent, Agent Teams, Hook, Plugin), CLI/Git basics, skill creation, and research integration with the existing domain-research skill. https://claude.ai/code/session_01HP4jR1ftkkK1CA2zw1ZYbK
Credit AI Native Camp / Koomook (@Koomook) as the original author of the camp-1 curriculum that the self-learning skill is based on. Added attribution to LICENSE, README.md, SKILL.md, and install.js. https://claude.ai/code/session_01HP4jR1ftkkK1CA2zw1ZYbK
Add self-learning plugin info to Korean intro, plugin table, quick start, installation, plugin details (STOP protocol, 7 learning blocks), and directory structure. Credit ai-native-camp/camp-1 by @Koomook. https://claude.ai/code/session_01HP4jR1ftkkK1CA2zw1ZYbK
…ng skill Integrate the "Agentic Engineer Evolution" narrative into SKILL.md with Minecraft progression metaphor (dirt house → netherite → meta) and add the full evolution chronicle reference document. https://claude.ai/code/session_01HP4jR1ftkkK1CA2zw1ZYbK
- Block 1 (experience.md): Add Stone Age framing + evolution chronicle intro - Block 3 (core-features.md): Add Bronze~Iron Age context + era mapping summary - Block 5 (create-skill.md): Add Diamond Age framing — prompt = behavior - Block 6 (research-integration.md): Add Netherite Age framing — RAG + memory - README.md: Add evolution narrative table with Minecraft era progression Each block now clearly positions itself within the agentic engineer evolution path (dirt house → netherite → meta). https://claude.ai/code/session_01HP4jR1ftkkK1CA2zw1ZYbK
Formalize the novel pedagogy used in self-learning skill as "Evolution-Gated Learning (EGL) — 진화 게이트 학습법": - Add egl-methodology.md: Full definition with 5 structural principles (Evolution Narrative, Mandatory Gates, Recursive Self-Reference, Evolution Metaphor, RAG-as-Pedagogy) - Update SKILL.md: Reference EGL methodology by name - Update all prompt files: Integrate evolution era framing - Update README.md: Describe EGL as the pedagogical foundation EGL is distinct from existing pedagogies in its combination of: 1. Real project timeline as curriculum (not PBL, not case study) 2. STOP protocol as architectural gate (not recommendation) 3. Tool=Teacher=Subject recursive loop (beyond Papert's microworld) 4. RAG pattern consciously applied to education design 5. Game evolution structure as architecture complexity metaphor https://claude.ai/code/session_01HP4jR1ftkkK1CA2zw1ZYbK
hongsw
added a commit
that referenced
this pull request
Feb 18, 2026
Features: - Add self-learning skill (3,288 lines) - Interactive Claude Code learning framework - Block 0-6: Core features, setup, experience, MCP, subagent, agent teams, hooks, plugins - STOP protocol: 2-turn structure (explain → quiz) - Based on ai-native-camp/camp-1 curriculum - Add notebooklm-infographic plugin - Automated infographic generation with NotebookLM - Web search integration for latest information - NotebookLM MCP integration for professional visualizations - Complete automation from search to visualization Plugin Structure Improvements: - Dual invocation support (Skills + slash commands) - domain-research: both /domain-research command and Skill tool invocation - Added commands/domain-research.md for slash command documentation - Multi-skill plugin architecture - domain-research plugin now contains 2 skills: domain-research + self-learning - Updated install.js for multi-skill installation - Migrated skills field from string to array in plugin.json Marketplace: - Updated .claude-plugin/marketplace.json: 3 → 5 plugins - Added self-learning (via domain-research) - Added notebooklm-infographic Changes: +7,711 additions, -720 deletions, 93 files changed Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.