Reusable AI skills and capabilities for agent workflows
darkprint
The DarkPrint registry from your terminal and from an agent session: clone, validate, export and import blueprints, report runs, serve the registry over MCP on stdio, and carry the blueprint-writing skill.
...morekunjshah
Single-shot completion against any coding model — local Ollama, any OpenAI-compatible endpoint, or Anthropic. Configure a model, hint which services it can call, send a prompt, get a response.
...moreGitHub Actions
YuanZao (元造) — a zero-dependency Python 3.8+ skill scaffold generator: validates naming (yotta- prefix / lowercase-hyphen / YuanX Chinese name / non-overwrite), renders a full release-compliant scaffold from an embedded template (SKILL.md, bilingual four-
...moreGitHub Actions
argus-reviewer — open-source vision-model E2E testing harness. Record, replay, heal, and assert with any OpenRouter model under a hard budget cap.
...moreaustin-starks
Build a queryable SQLite lake of U.S. congressional trading disclosures (House PTRs and Senate eFD filings) from official sources: discovery, PDF decrypt/render, OCR, consensus model extraction, resumable sync, and integrity audits.
...morerakramprakash
Firecrawl component for Convex: scrape, map, and search the web, and run durable crawls with reactive progress.
GitHub Actions
The OIML SMART house shell — the chrome machinery every OIML SMART site mounts (federation header and footer frames, nav rendering, minisite nav, hero, docs layout, theme runtime, design tokens, the AI assistant island). The package ships machinery only:
...moreGitHub Actions
Athena React SDK — Build AI-powered chat applications with the Athena platform
GitHub Actions
The Konneal engine: the publisher-agnostic build pipeline and API plane for standards intelligence (retrieval, answer contract, verdicts, evaluation).
...morethink-in-universe
Verify NEAR AI Cloud attestation evidence in TypeScript
sethconvex
Metered, budget-governed AI Gateway usage for Convex: cost & usage tracking, per-user/per-action/global spend/token/rate limits, request logging, re-run, and an Agent-component adapter.
...morethanos_heimdall
Command line access to the Heimdall API.
arjunc137
An OpenRouter provider integration for Effect AI SDK
rksfn
Context-aware voice input for pi. Speak a request, get a formulated prompt at the cursor.
safwan-o
Local voice input plugin for OpenCode (V2 TUI port)
crissu3
Voice control for DSH web: speech-to-text into the composer (with auto-send) and spoken playback of assistant replies via the Web Speech API
...moreGitHub Actions
Fast PDF classification and text extraction. Detect text-based vs scanned PDFs, extract text by region with quality checks. Native Rust performance via napi-rs.
...morejosehernandezdeves
Librería JavaScript para extraer, normalizar, parsear y validar comprobantes de Pago Móvil venezolanos mediante OCR, con utilidades de conversión USD/VES basadas en la tasa oficial del BCV.
...moreman0l
Server-side AI bot tracking for indiestack analytics. Detects AI assistants, AI search systems and training crawlers requesting pages on your site — from Next.js proxy, Cloudflare Workers/Pages, Express, Hono or any web-standard handler.
...morescotscottmca
Bug-fixing agent crew for GitHub Copilot and Claude Code: an orchestrator that beams down mapper, investigator, basher and pr-writer.
...moresoumo444
Local Context Engine for AI coding assistants — scans your project and generates a clean, token-optimized project-context.md
...morekhosla
Multi-agent supervisor extension for pi
GitHub Actions
One-shot scaffolder for a shared agent setup across Claude Code, Codex, opencode, Mistral Vibe, and Cursor.
240xu
Themis — tech-lead lifecycle governance for DeepSeek Harness: 22 governance tools plus capability discovery (classify/state/plan/evidence/gates/release/install audits, context/evidence/progress analysis, mutation preview). No writes, no subprocesses, no n
...more