From project-toolkit
Encodes repositories into Forgetful knowledge base using Serena's LSP-powered symbol analysis to create memories, entities, patterns, features, and docs for onboarding and refreshing codebase understanding.
How this skill is triggered — by the user, by Claude, or both
Slash command
/project-toolkit:encode-repo-serenaclaude-sonnet-4-6The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Transform an undocumented codebase into a rich, searchable knowledge repository using Serena's LSP-powered symbol analysis.
Transform an undocumented codebase into a rich, searchable knowledge repository using Serena's LSP-powered symbol analysis.
| Trigger Phrase | Operation |
|---|---|
encode this repository | Full 12-phase encoding pipeline |
populate forgetful with this codebase | Full encoding pipeline |
onboard to this repo | Discovery + foundation phases |
refresh project understanding | Re-run encoding on updated codebase |
build knowledge base for this project | Full encoding pipeline |
Use this skill when:
Use research-and-incorporate instead when:
/encode-repo-serena
/encode-repo-serena ./my-project
"encode this repository"
"populate forgetful with this codebase"
| Input | Output | Duration |
|---|---|---|
| Codebase path | Forgetful memories + entities + docs | 30-60 min |
claude plugins list | grep serenaexecute_forgetful_tool("list_projects", {})/context-hub-setup firstAssess project size, complexity, and structure. Produce a structure map.
Create 5-10 project overview memories covering purpose, tech stack, and entry points.
Create 1-3 dependency memories documenting external libraries and internal references.
Use Serena find_symbol and find_referencing_symbols to produce 10-15 architecture memories.
Create component entities with relationships in Forgetful. Deduplicate before creating.
Document 8-12 recurring code patterns, conventions, and idioms.
Create 1-2 memories per critical feature describing behavior and implementation.
Record design decisions with rationale and alternatives considered.
Store code artifacts (configs, schemas, key files) in Forgetful.
Create a symbol index document with an entry memory for navigation.
Produce long-form documentation summarizing the codebase.
Create an architecture reference document linking all prior phases.
See references/phases.md for full phase details.
0 → 1 → 1B → 2 → 2B → 3 → 4 → 5 → 6 → 6B → 7 → 7B
Guidelines:
find_symbol and find_referencing_symbols| Profile | Total Memories | Documents | Entities |
|---|---|---|---|
| Small Simple | 17-31 | 2 | 3-5 |
| Small Complex | 28-46 | 2 | 5-10 |
| Medium | 38-66 | 2-3 | 10-20 |
| Large | 66-112 | 3-6 | 20-40 |
| Principle | Description |
|---|---|
| Symbol-accurate | Use LSP data, not guesses |
| Atomic | One concept per memory |
| Size | 200-400 words ideal |
| Importance | Most should be 7-8 |
| Linking | Connect related memories |
After encoding, verify all outputs meet quality standards:
See references/validation.md for test commands.
| Avoid | Why | Instead |
|---|---|---|
| Skipping Phase 0 discovery | Wastes effort on wrong project scope | Always assess project size and complexity first |
| Creating non-atomic memories | Pollutes search results, hard to maintain | One concept per memory, 200-400 words |
| Duplicate entities | Bloats knowledge graph, inconsistent links | Deduplicate entities before creating |
| Skipping validation | No confidence in encoding quality | Run validation checklist after completion |
| Document | Content |
|---|---|
| phases.md | Detailed phase workflows |
| templates.md | Entity schemas, memory templates |
| validation.md | Validation test commands |
/context-hub-setup - Setup Forgetful MCP/using-forgetful-memory - Memory best practices/using-serena-symbols - Serena symbol analysisnpx claudepluginhub rjmurillo/ai-agents --plugin project-toolkitEncodes repositories into Forgetful knowledge base using Serena's LSP-powered symbol analysis across 12 phases: discovery, symbols, patterns, features, decisions, and docs. Use for onboarding or refreshing codebase understanding.
Architectural analysis workflow using Serena symbols and Forgetful memory. Use when analyzing project structure, documenting architecture, creating component entities, or building knowledge graphs from code.
Bootstraps rekal memory by scanning a codebase for architecture, conventions, dependencies, and workflows. Use when starting rekal on a new project or re-initializing memory.