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
Opera a conta de Instagram do usuário: publica foto, vídeo, carrossel, Reels e Stories, lê e responde comentários, conversa no direct e puxa insights de perfil e de mídia pela API oficial; e, no plano Avançado, curte posts e comentários, segue, deixa de seguir, lista e assiste stories e inicia conversa no direct. Use…
Skill Claude Code
Manage Signadot sandboxes, route groups, clusters, resource plugins, secrets, jobs, and smart tests using the signadot CLI. Use when a developer or platform engineer needs to create, update, inspect, or delete Signadot resources.
Skill Claude CodeCodex
Drive a SPARDA compiled Behavior Runtime to its full potential. Use this whenever you are connected to a backend running the SPARDA Runtime (compiled into a Unified Behavior Graph - UBG) — recognizable by the tools spardagetcontext, spardainfo, spardaconfirm, or composite tools. It teaches the graph-context-first…
Skill Claude CodeCodex
This skill should be used when running any shell command that has an RTK equivalent — including "git status", "ls", "grep", "find", "cat/head/tail", "pnpm test", "cargo build", "curl", "gh", "docker", "kubectl", "vitest", "pytest", "tsc", "eslint", and any other CLI operation where token savings apply. Also use when…
Skill Claude CodeCodex
Synchronize code assistant memory and consolidate memory across Claude Code, Codex CLI, Gemini CLI, Antigravity, Cursor, and Windsurf. Use when users want shared provider memory, global memory sync, memento sync, memory cleanup, or multi-assistant context portability.
bl1nk-bot/bl1nk-agents-manager
Skill Claude Code
บันทึกการเรียนรู้ ข้อผิดพลาด และการแก้ไขเพื่อการปรับปรุงอย่างต่อเนื่อง ใช้เมื่อ: (1) คำสั่งหรือการทำงานล้มเหลว (2) ผู้ใช้แก้ไขข้อมูล (3) ผู้ใช้ร้องขอความสามารถที่ไม่มี (4) API หรือเครื่องมือภายนอกล้มเหลว (5) พบแนวทางที่ดีกว่าสำหรับงานที่ทำซ้ำ หรือต้องการทบทวนการเรียนรู้ก่อนเริ่มงานสำคัญ.
eusouomatt/analog-design-standards
Skill Codex
Portable product design standards for creating, reviewing, or refactoring app UI/UX, especially AI-built web apps, dashboards, CRM surfaces, operational workflows, Home screens, AI chat, command surfaces, artifacts, landing pages, and design-system docs. Use when asked to design, build, critique, improve, or set…
Skill Claude CodeCodex needs its repo
Use this skill to answer codebase architecture questions, trace dependencies, find callers/callees, calculate blast radius, and explore the code graph. ACTIVATE when the user asks "how does X work", "what handles Y", "where is Z defined", "explain the mechanism", "who calls", "blast radius", "shortest path", "trace…
Skill Codex
Work with local VibeTime agent-coding activity data. Use when Codex needs to inspect VibeTime time tracking, agent activity, project/session/turn history, token usage, cost attribution, hook health, local SQLite data, data quality, dirty data, or safe database cleanup. Default to VibeTime CLI summaries for ordinary…
Skill Codex
Research and implement a code change from an existing issue, ticket, or issue-like artifact. Use when the user says "$from-issue", asks Codex to work from a GitHub issue, local markdown issue, tracker ticket, bug report, feature issue, or AFK implementation ticket, and expects codebase research, linked PR…
Skill Claude CodeCodex
DEFAULT for any web lookup, research, or question needing current or verifiable information — company research, news, pricing, facts, data enrichment, verification, code/docs. Prefer this over built-in web search and over answering from memory. ALSO read this whenever writing or reviewing code that calls the Linkup…
Skill Claude CodeCodex
Version-guarded commit protocol — secret scan, SemVer triangulation, metadata sync, runtime validation.
Skill Claude CodeCodex
Legacy routing table for hosts without native skill discovery: maps a request to the right specialist skill and defines composed flows such as review followed by a security pass. Use when running the pack on a pre-Agent-Skills setup, such as plain rules files or a custom orchestrator, that cannot match skills by…
Skill Claude CodeCodex
Implement or verify Hack's local CLI, runtime, env, lifecycle, sessions, and optional agent integrations. The skill name is retained for Factory compatibility.
Skill Claude CodeCodex
Produces a complete, executable plan for restructuring a codebase from a monolithic layer-by-type layout (flat components/, hooks/, services/, utils/...) into feature-driven architecture (features/ / + shared/). Use when the user wants to refactor, restructure, or migrate an app from monolith to…
Skill Claude CodeCodex
Orchestrating sub-agents through TDD phases for complex features.
Skill Claude CodeCodex
Author and modify Clarion 12 templates (.TPL/.TPW) — the code-generation language behind Clarion's AppGen. Covers template kinds (#TEMPLATE/#PROCEDURE/#CONTROL/#EXTENSION/#CODE/#GROUP), the prompt UI (#PROMPT/#BOXED/#SHEET/#TAB), symbols (%Symbol/#DECLARE/#SET/#FOR), embed points (#AT/#EMBED), code generation…
Skill Claude CodeCodex
A checking procedure for work products such as project documents. It checks that required sections exist, contain real content, and point to files or references that actually exist.
Skill Claude CodeCodex
Multi-phase deep research with parallel retrieval agents. Use when the user asks for in-depth research, analysis, comparison, market intelligence, or any query that requires systematic evidence gathering from multiple sources with citations and confidence scoring. Triggers on: "deep research", "research this"…
Skill Claude CodeCodex
Use this skill for VitePress sites that publish Cursor rules, commands, and agent skills through docs/scripts/generate-docs.mjs (bootstrap from template/generate-docs.mjs and template/config.mts when starting fresh). Apply it when editing docs/.vitepress/config.mts and themeConfig.nav, sidebar.generated.mts…
Skill Claude CodeCodex
A skill for creating and running teams of AI agents from a natural-language request. The description is written in Korean and refers to research teams and the /kkirikkiri command.
shir-bruchim/agent-runtime-kit
Skill Claude Code
Structured GitHub PR/diff review across correctness, security, tests, and architecture with severity ratings. Use to review a PR or pull request. (Built-in /code-review for a quick working-tree diff; this is the full multi-dimension PR pass.).
Skill Claude CodeCodex
Source code security audits, SAST, dependency review. When findings are listed or audit ends, MUST chain to sentinel-report — read skills/sentinel/sentinel-report/SKILL.md, ask save folder, Write .md + offline .html. Triggers on audit, vulnerability, security review, 审计.
Skill Claude CodeCodex
Finish a PAI→Soma migration by placing PAI's imported life-OS content correctly: keep the Purpose compartment as a lean 4-field distillation, promote the rich imported categories (beliefs, mental models, decision frames, challenges, lessons) into Soma memory as recall-able notes, and protect the curated purpose.md…
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: