Generate optimized project context from codebase scan. Trigger: new project, no CLAUDE.md, /ijfw-summarize
Scanned 9/1/2026
Install to Claude Code
npx -y skills add FerroxLabs/wayland-core --skill ijfw-summarize --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Ijfw Summarize?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/ferroxlabs-ijfw-summarize)More formats (shields.io, HTML) on the badges page.
---
name: ijfw-summarize
description: "Generate optimized project context from codebase scan. Trigger: new project, no CLAUDE.md, /ijfw-summarize"
context: fork
model: haiku
effort: low
---
Scan the codebase and generate an optimized project context file.
## Process
1. Read: package.json, tsconfig.json, Cargo.toml, pyproject.toml, go.mod, Dockerfile,
docker-compose.yml, .env.example, Makefile -- whatever exists.
2. Scan: directory structure (2 levels deep), test framework, linter config, CI config.
3. Detect: language, framework, database, ORM, auth approach, deployment target.
4. Identify: key directories, entry points, API route patterns, shared utilities.
## Output
Write a CLAUDE.md (or platform equivalent) with:
```markdown
# Project Context
Stack: <framework> / <language> / <database>
Architecture: <pattern -- monolith, microservices, serverless, etc.>
Entry: <main entry point(s)>
Tests: <framework + command to run>
Lint: <tool + command>
## Structure
<key directories and their purpose, 1 line each>
## Patterns
<established code patterns to follow, 1 line each>
## Key Files
<important files a new contributor should know about>
```
Rules:
- Max 50 lines. This loads every session.
- No boilerplate explanations. Just facts.
- If uncertain about a pattern, omit it -- don't guess.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.