From fellowship
Studies reference files from CLAUDE.md and recent git merges to extract patterns in structure, dependencies, error handling, and naming before writing code in unfamiliar areas.
How this skill is triggered — by the user, by Claude, or both
Slash command
/fellowship:gather-loreThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Studies existing code to extract the specific patterns and conventions in play. Run this during research — before planning or writing anything — in areas where conventions matter. The patterns you extract here flow into the plan and constrain implementation downstream.
Studies existing code to extract the specific patterns and conventions in play. Run this during research — before planning or writing anything — in areas where conventions matter. The patterns you extract here flow into the plan and constrain implementation downstream.
Code generation and deviation checking happen later in the workflow: implementation applies these patterns (quest Phase 3 / TDD), and warden verifies compliance (quest Phase 4).
Check CLAUDE.md for a ## Reference Files section. If it exists, read the files listed for the relevant area.
If no reference files are documented, ask the user:
"I need 1-2 examples of files that do something similar to what we're building, that your reviewer would approve of. Can you point me to any?"
If the user can't identify any:
"Let me look at recent merges in this area to find approved patterns." Run:
git log --oneline --diff-filter=A -- [relevant directory] | head -10to find recently added files.
Read each reference file and produce a structured analysis. Be exhaustive — the patterns you miss are the ones that get flagged in review:
## Patterns in [filename]
### Structure
- [How the file is organized — what comes first, ordering]
- [Import grouping and ordering]
- [Export patterns]
### Dependencies
- [How external dependencies are accessed]
- [How internal dependencies are accessed]
- [Any DI/context patterns]
### Error Handling
- [Error types used]
- [How errors are propagated]
- [How errors are surfaced to callers]
### Data Flow
- [Input validation — where and how]
- [Transformations — where data changes shape]
- [Output — how results are returned]
### Naming
- [Variable naming patterns]
- [Function naming patterns]
- [Type/interface naming patterns]
### Things NOT Done
- [Patterns conspicuously absent — no direct DB calls, no raw HTTP, etc.]
Present the analysis: "Here's what I observed. Does this look right? Anything I'm missing or misreading?"
If this study reveals patterns not yet captured in CLAUDE.md, offer to add them:
"I noticed [pattern] in the reference files that isn't documented in CLAUDE.md yet. Want me to add it to the Review Conventions section?"
A structured pattern analysis that serves as a constraint document for downstream work. The patterns extracted here should be carried forward through lembas compaction so they inform the plan and constrain implementation.
npx claudepluginhub justinjdev/fellowshipExtracts existing project coding conventions (naming, file structure, error handling, testing, imports, API design, async patterns) and enforces them on new code. Produces a code style map in memory/patterns.md.
Use when building ANY feature within an existing project - search the current codebase for existing patterns, conventions, similar implementations, and established approaches before writing new code
Analyzes any codebase to extract conventions, patterns, and style via specialized agents for structure, naming, testing, frontend. Generates .claude/codebase-style.md for unfamiliar projects.