Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Skill Claude CodeCodex
Speak a short spoken alert to the user via the vox text-to-speech CLI whenever you hand the turn back to them — a task finished (pass or fail, however long it took), you're blocked and need input/a decision/approval, something broke, or you're about to go quiet on a long job. Assume the user is NOT watching the…
Skill Claude CodeCodex
Observe and debug your OpenClaw agent with Korveo — local-first AI observability. Records every LLM call, tool call, and decision; view at localhost:3000. Use when the user asks: "show my agent traces", "why did my agent fail", "how much did my last run cost", "open korveo", "debug my agent", or "show recent traces".
Skill Claude CodeCodex
Use when running or participating in a council audit (altered-frame review).
Skill Claude CodeCodex needs its repo
Guides and validates architecture-aware ports of PyTorch/Hugging Face models to Apple MLX, inspects existing local MLX projects, and plans evidence-gated optimizations for Apple Silicon. Use when the user asks to run, port, convert, inspect, quantize, benchmark, or fix a model (LLM, VLM, audio/TTS/ASR, diffusion, SSM…
parijatmukherjee/openclaw-hawkins
Skill Claude CodeCodex
Communication specialist for the OpenClaw multi-agent system. Use this skill when the task involves: drafting or sending emails, posting to Discord or other chat platforms, scheduling calendar events, sending notifications, or any outbound communication on behalf of the user. Always drafts before sending and requires…
Skill Claude CodeCodex
Customer-support humanoid answering the support mailbox over email, human-governed.
Skill Codex
Use when completed work makes claims — "done", "tests pass", "it works", "ready to launch" — that must be verified before they are believed. Re-derive each claim from the work itself and report CONFIRMED / REFUTED / UNVERIFIABLE with evidence. Fast claim-verification by default; the deterministic production-readiness…
Skill Claude CodeCodex
Leave inline review notes on a worktree's diff inside a running xNaut window. Steers the user's diff viewer; never opens its own.
Skill Claude CodeCodex
Use when the user wants to install, list, sync, remove, or manage AI coding-agent skills on this machine. Scribe manages a canonical skill store and links skills into Claude Code, Cursor, Codex, and other supported tools.
Skill Claude CodeCodex
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
Skill Claude CodeCodex
Skill "adrgen" from stefanrossmeier/ai-craftkit, covering adrgen skill, purpose, modes, mode 1: discover and mode 2: generate.
Skill Claude CodeCodex
This directory is reserved for a future installable skill that will call the Scivly backend API.
songoao25/dsh-virtual-product-team
Skill Claude CodeCodex
A development and quality process for building software, testing it, and checking it for security problems. It separates implementation, quality assurance, and security review while coordinating their handoffs.
microsoft/Build26-DEM332-from-zero-to-teammate-in-25-minutes-build-a-teams-agent-live
Skill Claude CodeCodex ✓ vendor
Use this skill whenever the user mentions Microsoft Teams in a development context — whether they're building, integrating, configuring, debugging, or just asking questions. Covers bots, message extensions, embedded web apps, Adaptive Cards, dialogs, SSO, infrastructure, the Teams Developer CLI/SDK, and general Teams…
render-examples/nanobot-render
Skill Claude CodeCodex
Sustained objectives via longtask / completegoal — idempotent goal wording, project-style modular work, early web/doc research, Runtime Context metadata.
Skill Claude CodeCodex
Site Reliability Engineer - virtual employee.
Skill Claude CodeCodex
Persistent memory graph procedures for this codebase. Use when investigating past regressions, checking known invariants or anti-patterns before modifying high-risk code, recording new nodes after bug fixes or decisions, or archiving permanently resolved regressions.
Skill Codex
Recruit ChatGPT Pro as an external expert ally for complex engineering, research, review, or artifact work through the user's Codex in-app Browser or Chrome. Package safe context, open a dedicated Pro conversation, monitor long-running work, recover and download deliverables, and independently validate them. Use when…
Skill Codex
Use when designing, iterating, or auditing a Multica agent squad. Pick topology, write a leader charter and role instructions, and keep only necessary hard gates. Strong models; few rules; every rule must earn its place with evidence.
Skill Claude CodeCodex
Use in repos coordinated by the Nexus CLI, especially when NEXUSCONSTITUTION.md, NEXUSQUEUE.md, NEXUSSTANDUP.md, or .nexus/ exists, or when the user asks about Nexus start/claim/release/doctor/status/next.
smallTechOrg/zero-shot-claude-boilerplate
Skill Claude Code
Turn a zero-shot idea into a perfectly-working, thoroughly-tested, spec-driven agent. One intake round (which also collects the API keys into .env), then the agent-builder builds one phase at a time — autonomous within a phase, with a human testing gate between phases. Also used to add a new capability to an existing…
Skill Claude CodeCodex
A browser-automation skill for searching South Korean court-auction listings on courtauction.go.kr and organising results in an Excel file.
Skill Claude Code
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
pas-mllr/claude-code-skills-journalism-osint
Skill Claude CodeCodex
A comprehensive guide for building scroll-driven narrative experiences using SvelteKit 5 and Svelte 5's runes.
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: