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 Code
Use when reviewing Go, Python, or TypeScript code for invariants left to runtime, convention, or type assertions: tightening a domain model after prototyping, reducing casts and type-system bypasses, reviewing optionality and discriminated unions, or establishing a safety baseline before a refactor. Defaults to the…
Skill Claude CodeCodex
Design, write, test, deploy, and configure Art Blocks transfer hook contracts in Solidity. Use when an artist or developer wants a contract that runs on every mint and transfer of a project's tokens — recording provenance on chain, emitting richer events, or restricting when a token may move. Covers the ITransferHook…
walterkken/doc-driven-engineering-software-skills
Skill Codex
Build, modify, run, and inspect Abaqus models and jobs using documentation matched to the installed release. Use for CAE scripting, INP generation, parameter studies, ODB extraction, Python-runtime mismatches, and failed Abaqus analyses. Separate script generation, solver completion, and engineering validation.
Skill Claude Code
The shape every agent-written message to a person must have before Forge will accept it: the three intents, the two audiences, the five cells they make, the rules each cell holds, and the eight doors those cells are read at. Read this when a write was refused with a rule id, before writing a comment or a question…
Skill Claude Code
This skill is designed to facilitate the generation and delivery of knock-knock jokes in a conversational context. It is intended to be used when the user has requested a knock-knock joke or when the assistant determines that a knock-knock joke would be contextually appropriate and welcome.
zingspark/create-harness-vibe-coding
Skill Codex
Design engineering principles for making interfaces feel polished. Use when building UI components, reviewing frontend code, implementing animations, hover states, shadows, borders, typography, icons, micro-interactions, enter/exit animations, or any visual detail work. Supports quick and full review modes. Triggers…
Skill Claude CodeCodex
Build explainer diagrams as HTML+SVG scenes in one consistent visual grammar (pixel-font title, mono subtitle, blue/orange cards and arrows, dashed containers, network circles, stat tiles, a one-line callout) and shoot each to a PNG with puppeteer. Use whenever a concept, story, trace, comparison, or set of numbers…
Skill Claude CodeCodex
A generic senior-engineer operating playbook. MANDATORY for every coding task — plan before you type, test before you claim, debug from evidence, review your own diff.
Skill Claude Code
Review a PR with JIRA validation, architecture checks, impact analysis, and interactive recommendations.
Skill Claude CodeCodex
Show live long-task progress as one Discord/Telegram card that is edited in place. Use when a task will take more than a couple of minutes or many items (research, enrichment, batch writes).
Skill Claude CodeCodex
Use Ennodia MCP to organize independent model attempts, discover and compare skills, and verify results against whole-task acceptance and cost.
Skill Codex
Prepare a source-read-only daily engineering brief with GitHub pull requests, today's Google Calendar agenda, current-quarter Transport planning links, incident.io on-call and incident context, previous-working-day activity, and cross-org signals. Use for morning check-ins, daily planning, or an engineering omni-view.
huangxinxinyu/xinyu-s-skill-set
Skill Claude CodeCodex
A writing-editing guide that identifies and rewrites specified signs of AI-generated prose.
Skill Claude CodeCodex
Build, adapt, or review native iOS and iPadOS apps with Apple frameworks and selectively retrieved components, interaction recipes, and verification guidance from native.offbr.co. Use for SwiftUI product work, web-to-native migrations, and native UI audits.
CitiesSkylinesModding/agents-plugins
Skill Claude CodeCodex
Sweeps this repo's Cities: Skylines II prose after a game update. Use when the game has updated, when the decompile holds a newer version than the references claim, or when a baseline line lags the installed game.
Skill Claude CodeCodex
How to build, run, test and ship a project on a machine running Crundi, working through the Crundi interface — using the crundi MCP tools (services, forwards, tunnels, browser, terminals, secrets, kanban, mindmap, schedules, notifications) instead of shelling out, and running dev servers on ports that are safe to take…
Skill Claude CodeCodex
A handoff tool that exports an approved Matrix design into a bounded task package for another coding agent. Matrix is a workflow that tracks a change from design to implementation.
agent-ecosystem/agent-skill-implementation
Skill Claude CodeCodex
Benchmark skill whose description stays under the spec's 1024-character limit when counted in Unicode code points but runs past it when counted in UTF-16 code units or UTF-8 bytes. Use when asked to probe description length units. The head marker MAGPIE-OBSIDIAN-1240 sits near the start and a tail marker sits at the…
Skill Claude CodeCodex
Structure, author, and validate persistent specification artifacts (think.md and plan.md) from business needs before agents write code. Use when a Think Planner agent or planning session creates architectural analysis or phased implementation checklists, or when CI validates specification readiness on issue creation.
Skill Claude CodeCodex
Apply Agent Decision Comments when changing or reviewing code in repositories that use ADCs.
Skill Claude CodeCodex
A task method that requires each requested result to be matched with evidence showing whether it was completed or verified.
Skill Claude CodeCodex
Sets up Intlayer developer tooling - ESLint / oxlint rules, the Language Server (LSP), the VS Code extension, the MCP server, CI/CD automation and the Chrome extension. Use when the user asks to "lint hardcoded strings", "setup Go-to-Definition for dictionary keys", "install the Intlayer MCP", or "automate…
Skill Codex
Recommend available skills or MCP tools using TypeSafe Jev, or explicitly choose one next skill. Use when the user requests capability advice, candidate inspection, selection evaluation, or reusable host integration. Native client selection remains the default and fallback.
Skill Claude CodeCodex
Build, test, and improve programs that use typed decision models such as Laya, Jev, or any compatible choice/score/noul backend. Use this skill whenever the user asks to classify, score, gate, route, extract, triage, moderate, or make other bounded judgments from text or structured state, especially when they mention…
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: