deeporbit
claudecodexPortable DeepOrbit workflows for Obsidian research, retrieval, writing, tasks, calendar, and vault maintenance.
33 skills · 33 commands · 1 MCP server · hooks
Every plugin for OpenAI Codex on GitHub — repos with a .codex-plugin/plugin.json or a Codex marketplace. Install with codex plugin marketplace add owner/repo then codex plugin add name@marketplace. Many work in both tools; see Claude Code plugins.
Portable DeepOrbit workflows for Obsidian research, retrieval, writing, tasks, calendar, and vault maintenance.
33 skills · 33 commands · 1 MCP server · hooks
Full BDB Agent OS suite: 200+ curated skills, 46 subagents and the fabric pipelines for Claude Code. Gate hooks and MCP servers are installed by the AOS installer.
15 commands · 46 agents
TYPO3 development, upgrades and quality workflows from webconsulting.at, with credited upstream skills.
61 skills
Full-stack AI-assisted development: spec-driven workflow, role-based agent team, orchestrator, scaffolder, lifecycle upgrades, quality-gate and eval enforcement.
24 skills · 23 commands · 10 agents · 2 MCP servers · hooks
Multi-agent skill ecosystem for structured software development. 58 skills and 26 specialized agents with quality gates, code exploration, and evidence-based review.
57 skills · hooks
AI assistant for product managers: research, concepts, requirements, Jira tasks, planning, reports, meetings, people and team context — across Jira, Confluence, Figma and your notes.
33 skills · 7 commands · 3 agents · 12 MCP servers · hooks
Route marketing briefs to the right specialist skill, diagnose before prescribing, challenge assumptions, and turn decisions into measurable tactics.
30 skills · 24 agents
Vietnamese-friendly Codex kit for building, fixing, reviewing, deploying, and operating real software projects from plain-language prompts.
47 skills
Documentation quality and freshness enforcer — detect staleness, check accuracy, measure coverage, and auto-generate docs across any language and doc framework
35 skills · 5 commands · 5 agents · hooks
Set up Threadify, then learn from mature posts and prepare the next six drafts through one private growth loop.
45 skills · 1 MCP server
Intent-Driven Development framework plugin — automates the IDD workflow with role-specific tools for stakeholder interviews, artifact generation, and structured documentation
16 skills · 15 commands · 14 agents
Open-source content lifecycle plugin — 22 skills, 13 agents, 10 quality gates, 43-pattern AI humanizer, run auditor, real .docx output with C2PA signing (EU AI Act Article 50), and a measure-audit-plan loop that compounds per brand. Installs on Claude Code, Cowork, Codex, Cursor, Copilot CLI, Antigravity, Hermes, OpenClaw, Grok + 35+ Agent Skills platforms.
22 skills · 9 commands · 13 agents
A monthly content calendar in, finished on-brand social creative out — and when no calendar exists, /ideate-month plans the month from brand pillars, live signals, and last month's MEASURED wins (/ingest-performance ranks analytics exports with sample floors — flat months say so honestly). AI images and video via provider chains where nothing fails silently, 9-platform copy with mechanism-aware CTAs, human approval gates, C2PA signed for EU AI Act Article 50. 21 skills, live model+price lookup.
21 skills · 18 commands · 5 agents
ElevenLabs voice AI — text-to-speech, voice agents, and speech engine skills, plus agent management via the ElevenLabs hosted MCP server.
42 skills
Domino Data Lab skills for Workspaces, Jobs, Projects, data, experiments, model deployment and monitoring, apps, governance, and the Domino APIs.
35 skills · 3 agents · 1 MCP server · hooks
AI PM workflow plugin that turns non-developer ideas into PRD, AC, policy, measurement, decision logs, and structural wireframes.
12 skills · 13 commands · 11 agents · hooks
Complete Flutter and Dart delivery collection
37 skills
Dart, architecture, state, data, and testing skills
37 skills
Flutter UI, effects, layout, motion, navigation, accessibility, and localization skills
37 skills
Complete Flutter and Dart delivery collection
37 skills
Dart, architecture, state, data, and testing skills
37 skills
Flutter UI, effects, layout, motion, navigation, accessibility, and localization skills
37 skills
Akka SDK development tools — setup, spec-driven development, test, build, deploy
12 skills · 23 commands · 1 MCP server
Search arXiv, fetch paper metadata, and read full-text content via MCP. STDIO or Streamable HTTP.
35 skills · 1 MCP server
Codex workflows for controlled recursive repository improvement with ClimbHill.ai.
30 skills · 1 MCP server
CF Powers — structured development workflows for Claude Code and Codex
20 skills · 4 commands · 5 agents · hooks
30 AI skills for forensic professionals & law enforcement officials. Developed by Rohas Nagpal.
30 skills
Devflow Native continuity skills for project truth, evidence, handoffs, and local execution rules.
14 skills · 14 commands · 1 MCP server · hooks
Core BSV blockchain operations including live BRC lookup (Beersy + GitHub), BitCom and off-chain standards, key derivation (Type42, BIP32, BAP), ORDFS content gateway, script templates, message signing, wallet operations, identity management, and JungleBus real-time blockchain streaming.
28 skills · 1 agent
An agent-engineering plugin for Claude Code: twenty-five fg-* skills. fg-security audits a codebase for exploitable vulnerabilities (methodology vendored from cloudflare/security-audit-skill, MIT) with artefacts kept outside the repo, and routes severity-gated findings into fix-forward plans. fg-debug diagnoses hard bugs conversationally (vendored from mattpocock/skills' diagnosing-bugs, MIT), then stops at diagnosis. It routes by state before size: an active failed task returns to fg-run even when trivial; only independent diagnoses branch to fg-quick or an approved fix-forward plan. A red command counts as a persistent eval only when durable; raw captures stay outside the repo and every exit cleans temporary artefacts. Unattended drives always skip it (ADR 260907-140655). Three form a loop that takes one task through a single cycle of ask·plan → execute → done: ask·plan (fg-ask) is grill-with-docs-style conversational grilling, execute (fg-run) picks a task from the backlog (Run all supported) and runs it as a Dynamic Workflow, and seal (fg-done) decides the retro — writing a retro log when there is something to learn and asking once only when a promotion to docs or evals clears the bar — then seals the task and guards against re-runs, via a deterministic seal script (forge-done.sh/.js) shared by every seal path (ADR-0030). Twenty-two more sit outside the loop: fg-learn batch-promotes the learnings unattended seals deferred; fg-map maps the codebase into .forge/codebase/ with parallel subagents so grilling reads a map instead of re-exploring the code (cuts context rot); fg-quick is a lightweight lane for trivial tasks that grills lightly, logs one line to .forge/quick/LOG.md, runs directly without formal artifacts (no ADR/plan/retro), and bails to fg-ask if the task turns out non-trivial; fg-status is a read-only reporter that surveys .forge/ and prints where every task stands plus the single next step you need (writes nothing, never auto-runs); fg-next derives th
26 skills · hooks