Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 281,786 indexed, measured the same four ways as everything else here.
Turn a user-provided video into an Apple-style, scroll-driven website with smooth canvas video scrubbing, optimized WebP frame sequences, progressive loading, and responsive motion. Use for cinematic product reveals, landing pages, scrollytelling, image-sequence animation, and scroll-controlled video; also optimize…
MCP proxy that compresses prose fields (tool descriptions, etc.) using caveman rules. Same accuracy, fewer context tokens. Runs locally from the caveman-shrink npm package.
Author the plan as a rich, self-contained interactive HTML page FIRST — that page IS the plan of record — then hand it to ox: ox plan save --file plan.html stores it in the ledger, derives the markdown from it, and computes the deterministic badges; ox plan render --file plan.html serves it with the ox chrome…
Search ShotGrid (Flow Production Tracking) entities with the right tool and filter syntax, so queries stay narrow instead of pulling whole projects into context.
Evaluate a planned change against known legacy risks, unknowns and modernization candidates to identify which findings require additional consideration before or after implementation. Use when: Before or during implementation of a Work Item in a legacy project — especially when the Work Item touches areas flagged in…
A guidance skill for Chinese university entrance exam choices, covering both application decisions and deeper checks of schools. It considers scores, rankings, subjects, location, majors, jobs, safety, campus culture and student life from the child’s and family’s point of view.
Gives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package.
MCP server for academic paper search, curation, and multi-platform push. Runs locally from the paper-distill-mcp Python package. Needs 7 environment variables to run.
★not rated 66▲
+1 7mo agoA
tokens not measured
AGPL-3.0
Every AI output has structural blind spots determined by the generation process itself. Future Tokens operations are named, composable instruments that target specific blind spots. They surface new information on every pass because expanding the output changes the blind spot geometry.
MCP server providing ground-truth Unity API documentation (2022/2023/6) -- prevents AI hallucination of signatures, namespaces, and deprecated APIs. Runs locally from the unity-api-mcp Python package. Needs 2 environment variables to run.
★not rated 66 14d agoASocket: warn
tokens not measured
originalMIT
To orchestrate and deploy this execution skill dynamically via Autonomous AI Agent frameworks (LangChain, AutoGen, CrewAI), point your agent environment definition to the repository root and establish runtime parameters.
Scrub AI provenance marks from text and files using the markscrub CLI: invisible Unicode (Layer A), optional statistical rewrite (Layer B), and C2PA/EXIF/XMP/container metadata on PNG/JPEG/SVG/PDF/DOCX/HTML/MD. Use when the user asks to strip watermarks, remove Content Credentials, clean AI metadata, remove invisible…
Add academic papers to Zotero via MCP (DOI/PMID/title); fetch full-text PDFs through a publisher-aware route ladder (Unpaywall → Elsevier/Wiley/Springer TDM → institutional proxy → SFX); PDFs land in a linked-files folder (ZotMoov), never uploaded to Zotero cloud. Also verifies that a downloaded PDF really is that…
ZettelForge v2.0.0 — Production CTI agentic memory system. Hybrid TypeDB (STIX 2.1 ontology) + LanceDB (vector search). Zero external AI dependencies: fastembed for embeddings, llama-cpp-python for LLM. 75% accuracy on CTI queries, 18% on LOCOMO. Use when agents need persistent memory, threat intel retrieval, entity…
Local memory store for AI coding agents — explicit-only, no auto-extraction. Use when: You just refined a conclusion worth keeping across sessions → call clickmemremember Starting a task → derive projectid + tags, call clickmemrecall, load hits into context, then work The user asks "what did we decide about X" → call…
★not rated 66 4mo agoA187 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: