Skill Claude CodeCodex
Add the OpenAgents Workspace channel so this NanoClaw Agent Group can be driven from an OpenAgents Workspace.
not rated 4.1k
+21 today A SkillSpector: pass 26 tokens
original Apache-2.0
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
not rated 4.0k
+9 yesterday A SkillSpector: warn 64 tokens
AGPL-3.0
gnhf
75Skill Claude CodeCodex
Use when the user asks to run GNHF, says they are going to sleep or leaving and wants an agent-managed coding run, asks to supervise, steer, or review an active GNHF run, or gives feedback on GNHF results.
not rated 4.0k
+40
changed 5d ago A 55 tokens
copy · 92% MIT
cascadeflow
76Skill Claude CodeCodex
Use when building, extending, or debugging AI agents with cascadeflow (agent runtime intelligence layer) — installing cascadeflow (Python) or @cascadeflow/core/@cascadeflow/langchain (TypeScript); using CascadeAgent, ModelConfig, harness APIs (cascadeflow.init, cascadeflow.run, @agent from cascadeflow.harness…
not rated 4.0k
+12 yesterday A SkillSpector: warn 231 tokens
original MIT
modlens
77Skill Claude Code
Plug-in vision for text-only models. Hard rule: when a file path or URL with an image extension (.png, .jpg, .jpeg, .webp, .gif, .heic, .heif) appears anywhere in the conversation (typed by the user, injected as a [Image: source: ] line, or inside a tag) and you cannot see that image's content, run this skill on it…
not rated 3.9k
+63
changed 2d ago A Socket: passSnyk: passSkillSpector: pass 240 tokens
original MIT
Skill Claude CodeCodex
Use when the user wants Codex to record a Linux desktop or browser workflow and turn it into a reusable skill. Requires the Record & Replay event-stream MCP server.
not rated 3.8k
+28 today A SkillSpector: pass 38 tokens
original MIT
Skill Claude CodeCodex ✓ vendor
Skill "[object Object]" from microsoft/apm, covering what this package does, getting started, available primitives and included workflows.
not rated 3.8k
+36 today A SkillSpector: pass 8 tokens
original MIT
Skill Claude CodeCodex
Review how the lean-ctx ctx MCP tools performed in the current session and file upstream issues for confirmed problems. Use when the user asks to review/audit lean-ctx tool performance, says "lean-ctx review", asks why ctx tools failed or fell back to native tools, or wants to report a lean-ctx bug.
not rated 3.7k
+29 yesterday A SkillSpector: warn 73 tokens
original Apache-2.0
Skill Codex
A connection that lets ChatGPT help plan and review coding work while Codex edits files, runs commands, tests code, and handles execution.
not rated 3.7k
+1.3k
changed 5d ago C SkillSpector: warn 90 tokens
original MIT
Skill Claude CodeCodex
Entry point for new work. Determines the best action path or work decomposition (update existing spec, create new spec, mixed decomposition, or no spec needed) and refines ideas through structured dialogue.
not rated 3.7k
+7 3mo ago A SkillSpector: warn 44 tokens
original MIT
Skill Claude Code needs its repo ✓ vendor
Add a new tool/command to any Azure MCP toolset. Full lifecycle from scaffolding through PR submission. USE WHEN: add new command, create tool, new MCP tool, scaffold command, implement operation, add azure service tool, create new toolset.
not rated 3.7k
+11
changed 8d ago A SkillSpector: pass 59 tokens
original MIT
refine-live
84Skill Claude CodeCodex
In-chat fallback for the Timeline Inspector Refine agent. Use when the user runs /refine live, asks to "refine live", "go live", or answer refine jobs — but ONLY when no persistent agent is wired (no npx transitions-refine live). Prefer npx transitions-refine live for run-and-forget (relay spawns agent per click, no…
not rated 3.5k
+34 7d ago A SkillSpector: warn 103 tokens
Skill Claude CodeCodex
Use when user needs expert help, wants to summon a specialist, says "help me with", "I need guidance", or has a task requiring domain expertise. Creates and manages a growing collection of expert agents.
not rated 3.5k
+3 15d ago A SkillSpector: warn 48 tokens
google-antigravity/antigravity-sdk-python
Skill Claude CodeCodex
Design, implement, and debug autonomous AI agents and multi-agent systems using the Google Antigravity (AGY) SDK. ACTIVATE this skill when the user wants to create, configure, or orchestrate Google Antigravity agents.
not rated 3.3k
+40
changed 5d ago A SkillSpector: pass 53 tokens
original Apache-2.0
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or iterate on skill quality. Triggers: "create a skill", "make a…
not rated 3.3k
+18 13d ago A Socket: passSnyk: warnSkillSpector: pass 214 tokens
original MIT
claude-api
88Skill Claude CodeCodex
Use this skill when the user is building against Anthropic APIs or SDKs, including @anthropic-ai/sdk, anthropic, or Agent SDK integrations.
not rated 3.3k
+3 28d ago A SkillSpector: pass 0 tokens
Skill Claude CodeCodex
Inspect and safely update Atlas user preferences through Atlas's config.toml.
not rated 3.3k
+85 today A SkillSpector: warn 19 tokens
original MIT
Skill Claude Code
Use OpenBiliClaw's versioned Agent Bridge CLI to read multi-source recommendations, profile state, dialogue, probes, saved lists, and submit explicit feedback.
not rated 3.2k
+41 today A SkillSpector: pass 40 tokens
original MIT
acpx
91Skill Codex
Use acpx as a headless ACP CLI for agent-to-agent communication, including prompt/exec/sessions workflows, session scoping, queueing, permissions, output formats, system-prompt overrides, and multi-agent flows authored with defineFlow/decision/decisionEdge.
not rated 3.2k
+17
changed 2d ago A SkillSpector: warn 57 tokens
original MIT
ai-agent-dev
92Skill Claude CodeCodex
A Chinese-language interview-question guide for roles focused on AI-agent development. It covers agent design, language-model calls, tool integration, MCP, retrieval-augmented generation, context management, and multiple agents working together.
not rated 3.2k
+29 26d ago A SkillSpector: pass 59 tokens
AGPL-3.0
Skill Claude CodeCodex
Create, list, read, message, wait on, fork, rename, archive, and pin Codex threads (sidebar tasks), plus automations and app navigation, using the app-native codexapp tools. Use when the session uses a custom (non-OpenAI) model, for example deepseek-v4-flash or mimo-v2.5, and the user asks to create a thread or a new…
not rated 3.1k
+40 yesterday A SkillSpector: warn 138 tokens
original MIT
loop-library
94Skill Codex
Compatibility alias for Loopy. Use only when an existing installation or older instruction explicitly invokes loop-library; use Loopy for new installations and requests. Provides the same discovery, recommendation, audit, repair, adaptation, guided crafting, bounded execution, run debrief, project loop saving, and…
not rated 3.1k
+17 1mo ago A Socket: passSnyk: warnSkillSpector: pass 65 tokens
original MIT
GoogleCloudPlatform/professional-services
Skill Claude CodeCodex
This skill should be used when the user wants to evaluate an AI agent end-to-end: scaffold an evaluation, design metrics that test a real hypothesis, make an agent measurable, audit generated eval config, read evaluation results, or run an improvement ("hill climbing") loop. Covers evaluation methodology, metric…
not rated 3.1k yesterday A SkillSpector: pass 123 tokens
original Apache-2.0
Skill Claude CodeCodex
Install and configure Mnemosyne as a Hermes Agent memory provider — local SQLite with vector search, episodic consolidation, and temporal knowledge graphs.
not rated 3.1k
+77 today A SkillSpector: pass 34 tokens
original MIT
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: