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 Codex
Design, scaffold, audit, and upgrade Model Context Protocol servers. Use when the user asks to build or migrate an MCP server, adopt MCP 2026-07-28, add dual-era support, create an MCP integration, expose an API or data source through MCP tools/resources/prompts, add OAuth or API-key auth to an MCP endpoint, run an…
Skill Claude Code needs its repo
Run the pre-real-Serum-test checklist on one or more .SerumPreset files -- automated CBOR wire-type scan plus a human-readable summary -- then hand off to the user for the real load-it-in-Serum test. Use this after any generatepreset/editpreset call on serum-mcp, or whenever a preset file needs to be verified before…
Skill Claude Code
Global one-shot autoskill skill library injection for earthbench executor smoke and evaluation.
Hongda-Zhao/bio-gene-to-reference-tree
Skill Claude CodeCodex
Orchestrate this repository's end-to-end auditable protein or nucleotide gene-tree workflow. Use when a request spans several stages or the active stage is unclear; select one task adapter, then follow the canonical Skill and its review gates.
Skill Codex
Use when producing Chinese talking-head motion videos from SRT files, including subtitle cleanup, scene segmentation, motion planning, scene generation, or Remotion rendering.
agentprism/agentprism-workflows
Skill Claude CodeCodex
Write and run deterministic AgentPrism workflow scripts through the MCP workflow tool. Use for workflow DSL syntax, live backend/model/mode discovery with action:"config", agent routing, structured output, explicit checkpoints, composition, run status, pause, stop, result retrieval, and same-run resume.
rolfie-han/hanxiaoyu-visual-story-comic
Skill Codex
A skill for turning an authorized story, script, article, or outline into a coherent multi-page comic. It plans characters, scenes, props, page layouts, image prompts, and continuity checks.
Skill Claude Code
Scaffold Claude Code hook configs by reading your existing settings and skills.
Xanthus-Sanslab/jianying-ai-mcp
Skill Codex
A video-editing skill for understanding videos through timestamped transcripts and selected frames, then planning and creating Jianying or CapCut China desktop drafts.
vesperchinn/learn-anything-skill
Skill Claude CodeCodex
Use when the user wants to learn a new field through a structured study repository, create a study plan, learn from supplied PDFs, slide decks, Markdown, TXT, Word docs, or webpage exports, assess understanding through exercises and stage tests, or build a capstone project. Best for multi-session learning workflows…
Skill Claude Code
Supprime les marques d'écriture IA dans un texte français. À utiliser pour relire ou réécrire du texte afin qu'il sonne humain. Adaptation française du skill « humanizer » de blader/humanizer, fondée sur le guide Wikipédia « Signs of AI writing ». Repère et corrige l'inflation de portée, le langage promotionnel, les…
Skill Claude CodeCodex
Use when a user asks Codex to recommend, install, update, or inspect specialized coding subagents for Claude Code, Codex, OpenCode, or multiple targets in the current repository.
Skill Codex
Create reproducible before-and-after evidence for software changes using annotated PNG, JPEG, MP4, backend HTTP scenarios, verified web flows, or Android/iOS app checks. Use for Playwright or Chrome DevTools MCP verification, UI/design fixes, visual regressions, interaction recordings, Android adb or iOS Simulator…
Skill Claude CodeCodex
Edit and assemble CapCut desktop drafts programmatically with Claude via the capcut MCP server, and run the full short-video pipeline behind them: record → captions (WhisperFlow) → motion graphics (HyperFrames) → probe/encode (ffprobe/ffmpeg) → assemble, trim, split, caption a CapCut draft. Use when the user wants to…
Skill Claude CodeCodex
Skill da REST API do Asaas na MCP.AI: 211 endpoints em /api/asaas. Conta digital e cobranças no Asaas com a API REST oficial v3 completa (api.asaas.com), saldo, cobranças (boleto/PIX/cartão), assinaturas, parcelamentos, links de pagamento, split, antecipações, transferências, PIX, extrato, notas fiscais e subcontas.…
Skill Codex
Adapt an AI response for dyslex.ai readability. Use when a user asks for clearer, easier-to-read, less overwhelming, more structured, or accessibility-oriented wording without losing technical detail.
Skill Claude CodeCodex
Use this skill whenever the user wants to search, navigate, or understand source code in a large codebase — even when they don't say "OpenGrok". Trigger for: finding where a function or class is defined, tracking where something is called or referenced, reading a remote source file, checking who last changed a line…
Skill Claude CodeCodex
Search and navigate local markdown via MCP. Use when the user asks to search docs, find a README section, list headings/TOC, extract code examples by language, read frontmatter, or grep internal wikis and ADRs on disk.
Skill Claude CodeCodex
Orchestrate multi-agent epistemic triangulation: diverge across research dimensions, detect overlaps and contradictions, verify deeply, then converge into a validated synthesis. Swarm parallelism serves epistemic robustness — not merely speed.
Skill Claude CodeCodex
Ktor server patterns including routing DSL, plugins, authentication, Koin DI, kotlinx.serialization, WebSockets, and testApplication testing. Use when building a Ktor server — routing, plugins, auth, DI, serialization, or tests.
Skill Claude CodeCodex
Create, schedule, and manage social media posts via Typefully. ALWAYS use this skill when asked to draft, schedule, post, or check tweets, posts, threads, or social media content for Twitter/X, LinkedIn, Threads, Bluesky, or Mastodon, or when the user drops a Typefully draft URL such as https://typefully.com/?a= &d= .
Skill Claude CodeCodex
Best practices for designing and structuring agent skills: SKILL.md frontmatter rules, triggers, progressive disclosure, and when to use scripts vs references.
Skill Claude CodeCodex
Use the API harness to drive Agentweaver through its REST API, capture the complete request/response evidence, and emit a normalized agentweaver.persona-judge-verdict/v1 JSON verdict. It is for backend/API end-to-end validation; use the UI or MCP harness for those surfaces.
Skill Claude Code
A project setup and update skill for ai-standards, a collection of standards used to guide coding agents. It checks the current installation and asks which new capabilities to enable.
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: