Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 281,995 indexed, measured the same four ways as everything else here.
An industry-research engine that turns a broad business or market question into a sourced strategic report. It uses several research agents to check evidence, challenge conclusions, and assign confidence.
Create, inspect, and edit Excalidraw diagrams as editable .excalidraw JSON files. Use when Codex needs to turn architecture sketches, process flows, user journeys, system diagrams, workshop notes, whiteboard-style visuals, or Mermaid-like node-and-edge specs into an Excalidraw file; modify existing Excalidraw scenes…
Guia prático da API Pública do DataJud (CNJ) — consulta de metadados e movimentações de processos judiciais brasileiros via Elasticsearch em api-publica.datajud.cnj.jus.br. Vai além da documentação oficial: registra conhecimento de produção como a consulta obrigatória pelo alias do tribunal (o curinga apipublica…
MCP server for sports-data APIs (bookmakers, league data, aggregators). Capability-tag system enables cross-provider composition. Runs locally from the sportsdata-mcp Python package.
★not rated 33▲
+1 10d agoA
tokens not measured
originalMIT
Create or refine prompts for photorealistic, everyday SNS-style portraits of clearly adult women, especially natural smartphone snapshots with realistic skin, facial asymmetry, hair texture, casual composition, ambient light, and non-model-like poses. Use when the user asks for a realistic social-media portrait…
A command that runs an existing Memory Bank workflow for planning, implementing, checking, reviewing, and completing development work. The workflow can use project plans or specification tasks.
Local MCP proxy for tool restrictions, response redaction, audit logs, and database schema context. Runs locally from the januscope npm package. Needs 3 environment variables to run.
Generate grounded software feature-task briefs with a small, bounded ideation budget instead of implementing every idea. Read focused source and optional shadow/dream evidence, grow or resume a persistent proposal tree, and obtain independent shortlist judgments. Run only decision-changing probes of existing behavior.…
Use ZulipChat MCP for authorized Zulip messaging, search, drafts, files, and agent session workflows. Apply when the user asks to work in Zulip or connect a coding session to a Zulip topic.
Deploy, verify, and troubleshoot the TFE SAML lab in hal. Use this skill when the user asks to enable SAML SSO for TFE, set up TFE single sign-on, debug SAML redirects or attribute mapping, configure SCIM provisioning for TFE teams, or reset the TFE SSO demo. Triggers include "enable saml", "TFE SSO", "TFE SAML"…
A tool for turning an image or pixel data into a Perler bead pattern: a grid-based craft plan with color codes, coordinates, heavier grid lines, color quantities, and a CSV materials list. It can also redraw an unsatisfactory source image in a simple pixel-art style before making the pattern again.
Set up a saved Slack catch-up profile by choosing its workflowkind, channels, priority people and cadence, so slackcatchmeup returns evidence shaped for an incident room, a support inbox, an exec brief or a launch watch. Use when the user wants a repeatable catch-up or a handoff routine, or asks which channels and…
Design, configure, or manage an AutoHelix experiment for an existing project, including requests such as 'use AutoHelix to improve X'. Use for setup-only preparation, requested launch, or supervision of a bounded run.
A tool that turns customer conversations, meeting notes, and other Feishu records into structured requirement documents. BRD means business requirements document, and PRD means product requirements document.
MCP server "kafka-schema-registry" as configured in aywengo/kafka-schema-reg-mcp. Runs kafka_schema_registry_unified_mcp.py with python. Needs 3 environment variables to run.
★not rated 32 3d agoA
tokens not measured
originalMIT
CONTEXT: Cognitive Order Normalized in Transformer EXtract Truncated. Cross-model context handoff via Progressive Density Layering, MLDoE expert compression, Japanese semantic density, and Negentropic Coherence Lattice validation. Creates portable carry-packets that transfer cognitive state between AI sessions. Use…
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: