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.
Comprehensive full-stack development and engineering skill merging Perplexity Computer's built-in dev tools with Claude Code's engineering team skills. Covers architecture, frontend, backend, fullstack, QA/testing, DevOps/CI-CD, security, debugging, TDD, code review, and more. Use when writing code, debugging…
Tailors resumes and cover letters for job applications using LinkedIn Parsing System (LPS) optimization. Use this skill when the user requests: (1) Creating or updating a resume for a specific job posting, (2) Writing or customizing a cover letter for a role, (3) Optimizing application materials for ATS/LPS systems…
Clone an existing video ad onto a new product using Seedance 2.0 through the optional Arcads MCP server. Analyzes the source with arcadsanalyzemedia, adapts its structure, generates via arcadsgeneratevideoseedance20, and polls with arcadswatchasset. Use only when the user explicitly requests Arcads MCP or has selected…
Reviews and grades an agent skill directory (SKILL.md plus supporting resources) for specification compliance, clarity, token efficiency, safety, robustness, and portability. Produces an evidence-cited weighted score and grade, P1/P2/P3 findings with minimal patch text, and a machine-readable verdict with structured…
Use when the user asks Codex App to run a project for a duration, keep working automatically, auto-improve a project, continue in the background, use human checkpoints only for risky actions, resume/pause/cancel/status an automation, or run a long autonomous project loop with self-review and reviewer subagents.
Adapt an agent to run on BenchFlow (ACP) and verify it behaves identically inside the eval harness vs standalone — closing the eval↔prod gap. Use when adding a new agent to this repo or checking an existing one for eval/prod behavior parity.
A workflow that turns podcast or spoken-audio files into preview vertical videos sized 1080×1920, with Chinese subtitles, chapter scenes, a progress bar, and themed colours.
Play Texas Hold'em poker against 3 AI opponents with optional coaching. Use this skill whenever the user wants to play poker, practice poker, learn poker strategy, improve their poker game, play cards, or mentions Texas Hold'em. Also trigger when the user says things like 'deal me in', 'let's play some hands', 'poker…
A Chinese-language writing guide for producing natural, human-readable Chinese text, including articles, documentation, proposals, emails, and product copy.
Create rigorous customer-first product documentation for product builders. Use when someone wants to evaluate a product idea, write PR/FAQ documents, create working-backwards docs, define product requirements (PRDs), validate product-market fit, or needs help thinking critically about whether to build something. Helps…
Trợ lý Project Manager toàn diện, tích hợp Jira & Confluence qua Atlassian MCP. Gồm 3 nhóm chức năng: [Lập kế hoạch & Tài liệu] Sprint Planning (capacity, Sprint Goal) — Roadmap (quý/năm, milestone) — PRD (goals, scope, requirements) — User Story (chuẩn INVEST, tạo Jira issue) — Meeting Notes (action items, push Jira…
Produce a complete narrated Vox-style motion-graphics explainer video end to end on the Higgsfield MCP, plus the four jobs around it — build a permanent custom style key, scan the news for today's most explainable story, explain Eric's own business, or stand up a whole series with a bible and an episode slate.…
Write, check and query aontu definitions — a JSON superset where documents UNIFY instead of overwriting. Use when a repository holds .aontu files, when configuration must satisfy a schema rather than merely parse, or when you need to ask what a configuration says at a path and why it says it.
Generate T28 28nm IO rings from text or image requirements. Handles signal classification, device mapping, semantic intent generation, confirmed layout config, Cadence SKILL script generation, Virtuoso schematic/layout execution, screenshots, and DRC/LVS/PEX verification. Use for T28 IO ring generation, layout…
Safety, privacy, cost management, and frank advice for building always-on AI agents with episodic memory. Covers data hygiene, privacy risk surfaces, runaway cost prevention, scope creep, psychological effects of persistent AI companions, and responsible deployment patterns. This is the skill that tells you what can…
Build, modify, materialize, run, and verify DataCoolie projects. Use for workspace bootstrap, metadata authoring, environment overlays, capability checks, runners, notebooks, custom functions, narrow unsupported adapters, local tests, immutable builds, and project-owned build/CI automation. This is the sole…
Building or revising Astro dashboard detail pages backed by repo-tracked JSON and browser-side charts. Use when adding docs routes like /tests, /images, or /applications that must render real evidence, explicit unavailable states, GitHub Pages-safe static output, and dense table sections without crushed columns.
A skill for creating, changing, shortening, restoring, or reviewing instructions for prompts, agents, skills, and project rule files. It organizes rules around purpose, context, actions, results, and boundaries.
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: