40 tagged codebase indexing, measured the same way as everything else here.
Browse within: antigravity 16deferred-loading 16diffusion-models 16circular-imports 10code-analysis 10vibe-coding 10code-search 6
Skill Claude CodeCodex
Semantic code and documentation search by meaning. Use codebasepeek to find WHERE code is (saves tokens), codebasesearch to see actual code. For exact identifiers, use grep instead. Search local codebase before using websearch for code/library/API/example questions.
Skill Claude CodeCodex
Preferred local codebase-understanding workflow for Pi and Codex. Start with codebasecontext before shell search or broad reads, then use specialized semantic and graph tools.
Skill Claude CodeCodex
Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, concept art, covers, or batch variants); run the bundled CLI (${SELENESKILLROOT}/scripts/imagegen.py) and require…
Skill Claude CodeCodex
Use when the user asks to generate, remix, poll, list, download, or delete Sora videos via OpenAI’s video API using the bundled CLI (${SELENESKILLROOT}/scripts/sora.py), including requests like “generate AI video,” “Sora,” “video remix,” “download video/thumbnail/spritesheet,” and batch video generation; requires…
Skill Claude CodeCodex
Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (${SELENESKILLROOT}/scripts/texttospeech.py) with built-in voices and require OPENAIAPIKEY for live calls. Custom voice creation is out of scope.
Skill Claude CodeCodex
Diagnose, design, implement, and validate system optimizations while treating correctness, retrieval quality, bounded behavior, and avoided downstream work as primary outcomes. Use for performance, latency, CPU, memory, storage, indexing, search, retrieval, caching, batching, concurrency, tokenizer, database, or…
Skill Claude CodeCodex
Pursue structural signals — dead code, cycles, duplicate exports (twins), hotspots, runtime traces, command/event/pipeline graphs. Use during cleanup, audit, refactor planning, or when investigating "is this used?" questions at module/system scope. Triggers on phrases "follow signals", "find dead code", "find cycles"…
Skill Claude CodeCodex
Score conceptual smear (drift, spread, runtime centrality, authority diversity, drift risk, closure evidence) across two or more task framings on the canonical 0..15 rubric. Use BEFORE running vc-polarize, BEFORE choosing a doctrine cut, or whenever an agent needs structural evidence for the abort/memo/pass/doctrine…
Skill Claude CodeCodex
Structural and literal repository perception before edits, deletes, refactors, or unfamiliar-code work. Use context/repo-view/focus/slice/impact/find/follow to establish scope, dependencies, blast radius, exact occurrences, and analyzer coverage before acting.
Skill Claude CodeCodex
File a new source into the LLM Wiki — create its Sources page, append a log entry, apply the proposed cross-reference edits. Use when the user says "ingest this", "file this source", "add this to the wiki", drops a URL/PDF/clipped article, or pastes notes they want captured. Never auto-applies cross-refs without…
Skill Claude CodeCodex
Health-check the LLM Wiki and offer fixes for each category of finding. Use when the user says "lint the wiki", "audit the wiki", "check wiki health", "clean up the wiki", or after a batch of ingests. Categories covered - orphans, broken links, stale sources, missing pages, tag drift, index parity.
Skill Claude CodeCodex
Answer a question from the LLM Wiki with citations, and optionally file the synthesis back as a concept page. Use when the user asks "what does the wiki say about X", "search the wiki for Y", "summarize what I know about Z", or asks a question that should be grounded in their personal knowledge base rather than…
Skill Claude CodeCodex
Use before answering repository questions about architecture, implementation, symbols, references, dependencies, refactoring impact, data flow, or bugs. Query the local hybrid index first so the agent reads only evidence-bearing file:line ranges instead of scanning the repository.
Skill Claude CodeCodex
Use before answering repository questions about architecture, implementation, symbols, references, dependencies, refactoring impact, data flow, or bugs. Query the local hybrid index first so the agent reads only evidence-bearing file:line ranges instead of scanning the repository.
Skill Claude CodeCodex
Use before answering repository questions about architecture, implementation, symbols, references, dependencies, refactoring impact, data flow, or bugs. Query the local hybrid index first so the agent reads only evidence-bearing file:line ranges instead of scanning the repository.
Skill Claude CodeCodex
Trigger: navegar, analizar o editar TypeScript/JavaScript con el compilador. Use tools AST preparadas, revisadas y vinculadas por hash.
Skill Claude CodeCodex
Generate a complete project index with per-module README files for efficient code navigation. Use when starting work on a new project or after major restructuring. Run once per project.
Skill Claude CodeCodex
Rebuild the index for a specific module or the entire project. Accepts --module flag for targeted rebuild and --m flag for custom instructions.
Skill Claude CodeCodex
Show the current state of the project index: staleness, module coverage, hook health, and recent sync activity. Use to diagnose index issues.